feat: Add Chinese documentation and Docker Compose configurations for DeepTutor and llama.cpp

- Created README.zh.md for DeepTutor with comprehensive features, installation steps, and usage instructions in Chinese. - Added docker-compose.yaml for DeepTutor to define services, environment variables, and resource limits. - Introduced .env.example for llama.cpp with configuration options for server settings and resource management. - Added README.md and README.zh.md for llama.cpp detailing features, prerequisites, quick start guides, and API documentation. - Implemented docker-compose.yaml for llama.cpp to support various server configurations (CPU, CUDA, ROCm) and CLI usage.
feat: add MoltBot service with configuration files and documentation
2026-02-01 16:08:44 +08:00 · 2026-01-30 10:12:03 +08:00 · 2026-01-29 17:37:44 +08:00 · 2026-01-25 22:59:55 +08:00 · 2026-01-22 10:48:31 +08:00 · 2026-01-20 14:18:28 +08:00
67 changed files with 3935 additions and 121 deletions
--- a/.vscode/extensions.json
+++ b/.vscode/extensions.json
@@ -1,6 +1,7 @@
 {
  "recommendations": [
    "yzhang.markdown-all-in-one",
-    "DavidAnson.vscode-markdownlint"
+    "DavidAnson.vscode-markdownlint",
+    "redhat.vscode-yaml"
  ]
 }
--- a/.vscode/settings.json
+++ b/.vscode/settings.json
@@ -13,6 +13,12 @@
      "strings": "off"
    }
  },
+  "[yaml]": {
+    "editor.formatOnSave": true
+  },
+  "[dockercompose]": {
+    "editor.formatOnSave": true
+  },
  "files.eol": "\n",
  "cSpell.enabled": false
 }
--- a/README.md
+++ b/README.md
@@ -12,7 +12,7 @@ These services require building custom Docker images from source.
 | [goose](./builds/goose)                     | 1.18.0  |
 | [IOPaint](./builds/io-paint)                | 1.6.0   |
 | [K3s inside DinD](./builds/k3s-inside-dind) | 0.2.2   |
-| [MinerU vLLM](./builds/mineru)              | 2.7.1   |
+| [MinerU vLLM](./builds/mineru)              | 2.7.2   |

 ## Supported Services

@@ -34,6 +34,7 @@ These services require building custom Docker images from source.
 | [Clash](./src/clash)                                           | 1.18.0               |
 | [ClickHouse](./src/clickhouse)                                 | 24.11.1              |
 | [Conductor](./src/conductor)                                   | latest               |
+| [DeepTutor](./apps/deeptutor)                                  | latest               |
 | [Dify](./apps/dify)                                            | 0.18.2               |
 | [DNSMasq](./src/dnsmasq)                                       | 2.91                 |
 | [Dockge](./src/dockge)                                         | 1                    |
@@ -44,11 +45,13 @@ These services require building custom Docker images from source.
 | [Easy Dataset](./apps/easy-dataset)                            | 1.5.1                |
 | [Elasticsearch](./src/elasticsearch)                           | 8.16.1               |
 | [etcd](./src/etcd)                                             | 3.6.0                |
+| [FalkorDB](./src/falkordb)                                     | v4.14.11             |
 | [Firecrawl](./src/firecrawl)                                   | latest               |
+| [Flowise](./src/flowise)                                       | 3.0.12               |
 | [frpc](./src/frpc)                                             | 0.65.0               |
 | [frps](./src/frps)                                             | 0.65.0               |
 | [Gitea Runner](./src/gitea-runner)                             | 0.2.13               |
-| [Gitea](./src/gitea)                                           | 1.24.6               |
+| [Gitea](./src/gitea)                                           | 1.25.4-rootless      |
 | [GitLab Runner](./src/gitlab-runner)                           | 17.10.1              |
 | [GitLab](./src/gitlab)                                         | 17.10.4-ce.0         |
 | [GPUStack](./src/gpustack)                                     | v0.5.3               |
@@ -58,6 +61,7 @@ These services require building custom Docker images from source.
 | [Halo](./src/halo)                                             | 2.21.9               |
 | [Harbor](./src/harbor)                                         | v2.12.0              |
 | [HashiCorp Consul](./src/consul)                               | 1.20.3               |
+| [InfluxDB](./src/influxdb)                                     | 2.8.0                |
 | [Jenkins](./src/jenkins)                                       | 2.486-lts            |
 | [JODConverter](./src/jodconverter)                             | latest               |
 | [Kestra](./src/kestra)                                         | latest-full          |
@@ -69,6 +73,8 @@ These services require building custom Docker images from source.
 | [LibreOffice](./src/libreoffice)                               | latest               |
 | [libSQL Server](./src/libsql)                                  | latest               |
 | [LiteLLM](./src/litellm)                                       | main-stable          |
+| [llama.cpp](./src/llama.cpp)                                   | server               |
+| [LMDeploy](./src/lmdeploy)                                     | v0.11.1              |
 | [Logstash](./src/logstash)                                     | 8.16.1               |
 | [MariaDB Galera Cluster](./src/mariadb-galera)                 | 11.7.2               |
 | [Memos](./src/memos)                                           | 0.25.3               |
@@ -77,6 +83,7 @@ These services require building custom Docker images from source.
 | [Minecraft Bedrock Server](./src/minecraft-bedrock-server)     | latest               |
 | [MinIO](./src/minio)                                           | 0.20251015           |
 | [MLflow](./src/mlflow)                                         | v2.20.2              |
+| [MoltBot](./apps/moltbot)                                      | main                 |
 | [MongoDB ReplicaSet Single](./src/mongodb-replicaset-single)   | 8.2.3                |
 | [MongoDB ReplicaSet](./src/mongodb-replicaset)                 | 8.2.3                |
 | [MongoDB Standalone](./src/mongodb-standalone)                 | 8.2.3                |
@@ -93,9 +100,10 @@ These services require building custom Docker images from source.
 | [Odoo](./src/odoo)                                             | 19.0                 |
 | [Ollama](./src/ollama)                                         | 0.12.0               |
 | [Open WebUI](./src/open-webui)                                 | main                 |
-| [Phoenix (Arize)](./src/phoenix)                               | 12.28.1-nonroot      |
+| [Phoenix (Arize)](./src/phoenix)                               | 12.31.2-nonroot      |
 | [Pingora Proxy Manager](./src/pingora-proxy-manager)           | v1.0.3               |
 | [Open WebUI Rust](./src/open-webui-rust)                       | latest               |
+| [OpenCode](./src/opencode)                                     | 1.1.27               |
 | [OpenCoze](./apps/opencoze)                                    | See Docs             |
 | [OpenCut](./src/opencut)                                       | latest               |
 | [OpenList](./src/openlist)                                     | latest               |
@@ -106,6 +114,7 @@ These services require building custom Docker images from source.
 | [Overleaf](./src/overleaf)                                     | 5.2.1                |
 | [PocketBase](./src/pocketbase)                                 | 0.30.0               |
 | [Podman](./src/podman)                                         | v5.7.1               |
+| [Pogocache](./src/pogocache)                                   | 1.3.1                |
 | [Portainer](./src/portainer)                                   | 2.27.3-alpine        |
 | [Portkey AI Gateway](./src/portkey-gateway)                    | latest               |
 | [PostgreSQL](./src/postgres)                                   | 17.6                 |
@@ -117,10 +126,11 @@ These services require building custom Docker images from source.
 | [Redpanda](./src/redpanda)                                     | v24.3.1              |
 | [Redis Cluster](./src/redis-cluster)                           | 8.2.1                |
 | [Redis](./src/redis)                                           | 8.2.1                |
-| [Renovate](./src/renovate)                                     | 42.52.5-full         |
+| [Renovate](./src/renovate)                                     | 42.85.4-full         |
 | [Restate Cluster](./src/restate-cluster)                       | 1.5.3                |
 | [Restate](./src/restate)                                       | 1.5.3                |
 | [SearXNG](./src/searxng)                                       | 2025.1.20-1ce14ef99  |
+| [Selenium](./src/selenium)                                     | 144.0-20260120       |
 | [SigNoz](./src/signoz)                                         | 0.55.0               |
 | [Sim](./apps/sim)                                              | latest               |
 | [Stable Diffusion WebUI](./apps/stable-diffusion-webui-docker) | latest               |
--- a/README.zh.md
+++ b/README.zh.md
@@ -12,7 +12,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [goose](./builds/goose)                     | 1.18.0 |
 | [IOPaint](./builds/io-paint)                | 1.6.0  |
 | [K3s inside DinD](./builds/k3s-inside-dind) | 0.2.2  |
-| [MinerU vLLM](./builds/mineru)              | 2.7.1  |
+| [MinerU vLLM](./builds/mineru)              | 2.7.2  |

 ## 已经支持的服务

@@ -34,6 +34,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Clash](./src/clash)                                           | 1.18.0                |
 | [ClickHouse](./src/clickhouse)                                 | 24.11.1               |
 | [Conductor](./src/conductor)                                   | latest                |
+| [DeepTutor](./apps/deeptutor)                                  | latest                |
 | [Dify](./apps/dify)                                            | 0.18.2                |
 | [DNSMasq](./src/dnsmasq)                                       | 2.91                  |
 | [Dockge](./src/dockge)                                         | 1                     |
@@ -44,11 +45,13 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Easy Dataset](./apps/easy-dataset)                            | 1.5.1                 |
 | [Elasticsearch](./src/elasticsearch)                           | 8.16.1                |
 | [etcd](./src/etcd)                                             | 3.6.0                 |
+| [FalkorDB](./src/falkordb)                                     | v4.14.11              |
 | [Firecrawl](./src/firecrawl)                                   | latest                |
+| [Flowise](./src/flowise)                                       | 3.0.12                |
 | [frpc](./src/frpc)                                             | 0.65.0                |
 | [frps](./src/frps)                                             | 0.65.0                |
 | [Gitea Runner](./src/gitea-runner)                             | 0.2.13                |
-| [Gitea](./src/gitea)                                           | 1.24.6                |
+| [Gitea](./src/gitea)                                           | 1.25.4-rootless       |
 | [GitLab Runner](./src/gitlab-runner)                           | 17.10.1               |
 | [GitLab](./src/gitlab)                                         | 17.10.4-ce.0          |
 | [GPUStack](./src/gpustack)                                     | v0.5.3                |
@@ -58,6 +61,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Halo](./src/halo)                                             | 2.21.9                |
 | [Harbor](./src/harbor)                                         | v2.12.0               |
 | [HashiCorp Consul](./src/consul)                               | 1.20.3                |
+| [InfluxDB](./src/influxdb)                                     | 2.8.0                 |
 | [Jenkins](./src/jenkins)                                       | 2.486-lts             |
 | [JODConverter](./src/jodconverter)                             | latest                |
 | [Kestra](./src/kestra)                                         | latest-full           |
@@ -69,6 +73,8 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [LibreOffice](./src/libreoffice)                               | latest                |
 | [libSQL Server](./src/libsql)                                  | latest                |
 | [LiteLLM](./src/litellm)                                       | main-stable           |
+| [llama.cpp](./src/llama.cpp)                                   | server                |
+| [LMDeploy](./src/lmdeploy)                                     | v0.11.1               |
 | [Logstash](./src/logstash)                                     | 8.16.1                |
 | [MariaDB Galera Cluster](./src/mariadb-galera)                 | 11.7.2                |
 | [Memos](./src/memos)                                           | 0.25.3                |
@@ -77,6 +83,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Minecraft Bedrock Server](./src/minecraft-bedrock-server)     | latest                |
 | [MinIO](./src/minio)                                           | 0.20251015            |
 | [MLflow](./src/mlflow)                                         | v2.20.2               |
+| [MoltBot](./apps/moltbot)                                      | main                  |
 | [MongoDB ReplicaSet Single](./src/mongodb-replicaset-single)   | 8.2.3                 |
 | [MongoDB ReplicaSet](./src/mongodb-replicaset)                 | 8.2.3                 |
 | [MongoDB Standalone](./src/mongodb-standalone)                 | 8.2.3                 |
@@ -93,9 +100,10 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Odoo](./src/odoo)                                             | 19.0                  |
 | [Ollama](./src/ollama)                                         | 0.12.0                |
 | [Open WebUI](./src/open-webui)                                 | main                  |
-| [Phoenix (Arize)](./src/phoenix)                               | 12.28.1-nonroot       |
+| [Phoenix (Arize)](./src/phoenix)                               | 12.31.2-nonroot       |
 | [Pingora Proxy Manager](./src/pingora-proxy-manager)           | v1.0.3                |
 | [Open WebUI Rust](./src/open-webui-rust)                       | latest                |
+| [OpenCode](./src/opencode)                                     | 1.1.27                |
 | [OpenCoze](./apps/opencoze)                                    | See Docs              |
 | [OpenCut](./src/opencut)                                       | latest                |
 | [OpenList](./src/openlist)                                     | latest                |
@@ -106,6 +114,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Overleaf](./src/overleaf)                                     | 5.2.1                 |
 | [PocketBase](./src/pocketbase)                                 | 0.30.0                |
 | [Podman](./src/podman)                                         | v5.7.1                |
+| [Pogocache](./src/pogocache)                                   | 1.3.1                 |
 | [Portainer](./src/portainer)                                   | 2.27.3-alpine         |
 | [Portkey AI Gateway](./src/portkey-gateway)                    | latest                |
 | [PostgreSQL](./src/postgres)                                   | 17.6                  |
@@ -117,10 +126,11 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [Redpanda](./src/redpanda)                                     | v24.3.1               |
 | [Redis Cluster](./src/redis-cluster)                           | 8.2.1                 |
 | [Redis](./src/redis)                                           | 8.2.1                 |
-| [Renovate](./src/renovate)                                     | 42.52.5-full          |
+| [Renovate](./src/renovate)                                     | 42.85.4-full          |
 | [Restate Cluster](./src/restate-cluster)                       | 1.5.3                 |
 | [Restate](./src/restate)                                       | 1.5.3                 |
 | [SearXNG](./src/searxng)                                       | 2025.1.20-1ce14ef99   |
+| [Selenium](./src/selenium)                                     | 144.0-20260120        |
 | [SigNoz](./src/signoz)                                         | 0.55.0                |
 | [Sim](./apps/sim)                                              | latest                |
 | [Stable Diffusion WebUI](./apps/stable-diffusion-webui-docker) | latest                |
--- a/apps/deeptutor/.env.example
+++ b/apps/deeptutor/.env.example
@@ -0,0 +1,97 @@
+# DeepTutor Configuration
+# Copy this file to .env and fill in your API keys
+
+#! ==================================================
+#! General Settings
+#! ==================================================
+
+# Timezone (default: UTC)
+TZ=UTC
+
+# User and Group ID for file permissions (default: 1000)
+# Adjust if your host user has a different UID/GID
+PUID=1000
+PGID=1000
+
+# Global registry prefix (optional)
+# Example: registry.example.com/ or leave empty for Docker Hub/GHCR
+GLOBAL_REGISTRY=
+
+#! ==================================================
+#! DeepTutor Version
+#! ==================================================
+
+# Image version (default: latest)
+# Available tags: latest, v0.5.x
+# See: https://github.com/HKUDS/DeepTutor/pkgs/container/deeptutor
+DEEPTUTOR_VERSION=latest
+
+#! ==================================================
+#! Port Configuration
+#! ==================================================
+
+# Backend port (internal: 8001)
+BACKEND_PORT=8001
+# Host port override for backend
+DEEPTUTOR_BACKEND_PORT_OVERRIDE=8001
+
+# Frontend port (internal: 3782)
+FRONTEND_PORT=3782
+# Host port override for frontend
+DEEPTUTOR_FRONTEND_PORT_OVERRIDE=3782
+
+#! ==================================================
+#! API Base URLs
+#! ==================================================
+
+# Internal API base URL (used by frontend to communicate with backend)
+NEXT_PUBLIC_API_BASE=http://localhost:8001
+
+# External API base URL (for cloud deployment, set to your public URL)
+# Example: https://your-server.com:8001
+# For local deployment, use the same as NEXT_PUBLIC_API_BASE
+NEXT_PUBLIC_API_BASE_EXTERNAL=http://localhost:8001
+
+#! ==================================================
+#! LLM API Keys (Required)
+#! ==================================================
+
+# OpenAI API Key (Required)
+# Get from: https://platform.openai.com/api-keys
+OPENAI_API_KEY=sk-your-openai-api-key-here
+
+# OpenAI Base URL (default: https://api.openai.com/v1)
+# For OpenAI-compatible APIs (e.g., Azure OpenAI, custom endpoints)
+OPENAI_BASE_URL=https://api.openai.com/v1
+
+# Default LLM Model (default: gpt-4o)
+# Options: gpt-4o, gpt-4-turbo, gpt-4, gpt-3.5-turbo, etc.
+DEFAULT_MODEL=gpt-4o
+
+#! ==================================================
+#! Additional LLM API Keys (Optional)
+#! ==================================================
+
+# Anthropic API Key (Optional, for Claude models)
+# Get from: https://console.anthropic.com/
+ANTHROPIC_API_KEY=
+
+# Perplexity API Key (Optional, for web search)
+# Get from: https://www.perplexity.ai/settings/api
+PERPLEXITY_API_KEY=
+
+# DashScope API Key (Optional, for Alibaba Cloud models)
+# Get from: https://dashscope.console.aliyun.com/
+DASHSCOPE_API_KEY=
+
+#! ==================================================
+#! Resource Limits
+#! ==================================================
+
+# CPU limits (default: 4.00 cores limit, 1.00 cores reservation)
+DEEPTUTOR_CPU_LIMIT=4.00
+DEEPTUTOR_CPU_RESERVATION=1.00
+
+# Memory limits (default: 8G limit, 2G reservation)
+DEEPTUTOR_MEMORY_LIMIT=8G
+DEEPTUTOR_MEMORY_RESERVATION=2G
--- a/apps/deeptutor/README.md
+++ b/apps/deeptutor/README.md
@@ -0,0 +1,248 @@
+# DeepTutor
+
+[中文说明](README.zh.md) | English
+
+## Overview
+
+DeepTutor is an AI-powered personalized learning assistant that transforms any document into an interactive learning experience with multi-agent intelligence. It helps you solve problems, generate questions, conduct research, collaborate on writing, organize notes, and guides you through learning paths.
+
+**Project:** <https://github.com/HKUDS/DeepTutor>  
+**License:** Apache-2.0  
+**Documentation:** <https://hkuds.github.io/DeepTutor/>
+
+## Features
+
+- **Problem Solving** — Detailed step-by-step solutions with visual diagrams
+- **Question Generation** — Adaptive questions based on your knowledge level
+- **Research Assistant** — Deep research with multi-agent collaboration
+- **Co-Writer** — Interactive idea generation and writing assistance
+- **Smart Notebook** — Organize and retrieve learning materials efficiently
+- **Guided Learning** — Personalized learning paths and progress tracking
+- **Multi-Agent System** — Specialized agents for different learning tasks
+- **RAG Integration** — LightRAG and RAG-Anything for knowledge retrieval
+- **Code Execution** — Built-in code playground for practice
+
+## Quick Start
+
+### Prerequisites
+
+- Docker and Docker Compose
+- OpenAI API key (required)
+- Optional: Anthropic, Perplexity, or DashScope API keys
+
+### Installation
+
+1. **Clone this repository**
+
+    ```bash
+    git clone <your-compose-anything-repo>
+    cd apps/deeptutor
+    ```
+
+2. **Configure environment**
+
+    ```bash
+    cp .env.example .env
+    # Edit .env and add your API keys
+    ```
+
+    **Required configuration:**
+    - `OPENAI_API_KEY` — Your OpenAI API key
+
+    **Optional configuration:**
+    - `ANTHROPIC_API_KEY` — For Claude models
+    - `PERPLEXITY_API_KEY` — For web search
+    - `DASHSCOPE_API_KEY` — For Alibaba Cloud models
+    - Adjust ports if needed (default: 8001 for backend, 3782 for frontend)
+    - Set `NEXT_PUBLIC_API_BASE_EXTERNAL` for cloud deployments
+
+3. **Optional: Custom agent configuration**
+
+    Create a `config/agents.yaml` file to customize agent behaviors (see [documentation](https://hkuds.github.io/DeepTutor/guide/config.html) for details).
+
+4. **Start the service**
+
+    ```bash
+    docker compose up -d
+    ```
+
+    First run takes approximately 30-60 seconds to initialize.
+
+5. **Access the application**
+
+      - **Frontend:** <http://localhost:3782>
+      - **Backend API:** <http://localhost:8001>
+      - **API Documentation:** <http://localhost:8001/docs>
+
+## Usage
+
+### Create Knowledge Base
+
+1. Navigate to <http://localhost:3782/knowledge>
+2. Click "New Knowledge Base"
+3. Upload documents (supports PDF, DOCX, TXT, Markdown, HTML, etc.)
+4. Wait for processing to complete
+
+### Learning Modes
+
+- **Solve** — Get step-by-step solutions to problems
+- **Question** — Generate practice questions based on your materials
+- **Research** — Deep research with multi-agent collaboration
+- **Co-Writer** — Interactive writing and idea generation
+- **Notebook** — Organize and manage your learning materials
+- **Guide** — Follow personalized learning paths
+
+### Advanced Features
+
+- **Code Execution** — Practice coding directly in the interface
+- **Visual Diagrams** — Automatic diagram generation for complex concepts
+- **Export** — Download your work as PDF or Markdown
+- **Multi-language** — Support for multiple languages
+
+## Configuration
+
+### Environment Variables
+
+Key environment variables (see [.env.example](.env.example) for all options):
+
+| Variable                 | Default    | Description               |
+| ------------------------ | ---------- | ------------------------- |
+| `OPENAI_API_KEY`         | (required) | Your OpenAI API key       |
+| `DEFAULT_MODEL`          | `gpt-4o`   | Default LLM model         |
+| `BACKEND_PORT`           | `8001`     | Backend server port       |
+| `FRONTEND_PORT`          | `3782`     | Frontend application port |
+| `DEEPTUTOR_CPU_LIMIT`    | `4.00`     | CPU limit (cores)         |
+| `DEEPTUTOR_MEMORY_LIMIT` | `8G`       | Memory limit              |
+
+### Ports
+
+- **8001** — Backend API server
+- **3782** — Frontend web interface
+
+### Volumes
+
+- `deeptutor_data` — User data, knowledge bases, and learning materials
+- `./config` — Custom agent configurations (optional)
+
+## Resource Requirements
+
+**Minimum:**
+
+- CPU: 1 core
+- Memory: 2GB
+- Disk: 2GB + space for knowledge bases
+
+**Recommended:**
+
+- CPU: 4 cores
+- Memory: 8GB
+- Disk: 10GB+
+
+## Supported Models
+
+DeepTutor supports multiple LLM providers:
+
+- **OpenAI** — GPT-4, GPT-4 Turbo, GPT-3.5 Turbo
+- **Anthropic** — Claude 3 (Opus, Sonnet, Haiku)
+- **Perplexity** — For web search integration
+- **DashScope** — Alibaba Cloud models
+- **OpenAI-compatible APIs** — Any API compatible with OpenAI format
+
+## Troubleshooting
+
+### Backend fails to start
+
+- Verify `OPENAI_API_KEY` is set correctly in `.env`
+- Check logs: `docker compose logs -f`
+- Ensure ports 8001 and 3782 are not in use
+- Verify sufficient disk space for volumes
+
+### Frontend cannot connect to backend
+
+- Confirm backend is running: visit <http://localhost:8001/docs>
+- For cloud deployments, set `NEXT_PUBLIC_API_BASE_EXTERNAL` to your public URL
+- Check firewall settings
+
+### Knowledge base processing fails
+
+- Ensure sufficient memory (recommended 8GB+)
+- Check document format is supported
+- Review logs for specific errors
+
+### API rate limits
+
+- Monitor your API usage on provider dashboards
+- Consider upgrading your API plan
+- Use different models for different tasks
+
+## Security Notes
+
+- **API Keys** — Keep your API keys secure, never commit them to version control
+- **Network Exposure** — For production deployments, use HTTPS and proper authentication
+- **Data Privacy** — User data is stored in Docker volumes; ensure proper backup and security
+- **Resource Limits** — Set appropriate CPU and memory limits to prevent resource exhaustion
+
+## Updates
+
+To update to the latest version:
+
+```bash
+# Pull the latest image
+docker compose pull
+
+# Recreate containers
+docker compose up -d
+```
+
+To update to a specific version, edit `DEEPTUTOR_VERSION` in `.env` and run:
+
+```bash
+docker compose up -d
+```
+
+## Advanced Usage
+
+### Custom Agent Configuration
+
+Create `config/agents.yaml` to customize agent behaviors:
+
+```yaml
+agents:
+  solver:
+    model: gpt-4o
+    temperature: 0.7
+  researcher:
+    model: gpt-4-turbo
+    max_tokens: 4000
+```
+
+See [official documentation](https://hkuds.github.io/DeepTutor/guide/config.html) for detailed configuration options.
+
+### Cloud Deployment
+
+For cloud deployment, additional configuration is needed:
+
+1. Set public URL in `.env`:
+
+    ```env
+    NEXT_PUBLIC_API_BASE_EXTERNAL=https://your-domain.com:8001
+    ```
+
+2. Configure reverse proxy (nginx/Caddy) for HTTPS
+3. Ensure proper firewall rules
+4. Consider using environment-specific secrets management
+
+### Using Different Embedding Models
+
+DeepTutor uses `text-embedding-3-large` by default. To use different embedding models, refer to the [official documentation](https://hkuds.github.io/DeepTutor/guide/config.html).
+
+## Links
+
+- **GitHub:** <https://github.com/HKUDS/DeepTutor>
+- **Documentation:** <https://hkuds.github.io/DeepTutor/>
+- **Issues:** <https://github.com/HKUDS/DeepTutor/issues>
+- **Discussions:** <https://github.com/HKUDS/DeepTutor/discussions>
+
+## License
+
+DeepTutor is licensed under the Apache-2.0 License. See the [official repository](https://github.com/HKUDS/DeepTutor) for details.
--- a/apps/deeptutor/README.zh.md
+++ b/apps/deeptutor/README.zh.md
@@ -0,0 +1,248 @@
+# DeepTutor
+
+中文说明 | [English](README.md)
+
+## 概述
+
+DeepTutor 是一个 AI 驱动的个性化学习助手，通过多智能体系统将任何文档转化为交互式学习体验。它可以帮助您解决问题、生成题目、进行研究、协作写作、整理笔记，并引导您完成学习路径。
+
+**项目地址：** <https://github.com/HKUDS/DeepTutor>  
+**许可证：** Apache-2.0  
+**文档：** <https://hkuds.github.io/DeepTutor/>
+
+## 功能特性
+
+- **问题求解** — 提供详细的分步解决方案和可视化图表
+- **题目生成** — 根据您的知识水平生成自适应题目
+- **研究助手** — 通过多智能体协作进行深度研究
+- **协作写作** — 交互式创意生成和写作辅助
+- **智能笔记** — 高效组织和检索学习材料
+- **引导学习** — 个性化学习路径和进度跟踪
+- **多智能体系统** — 针对不同学习任务的专业智能体
+- **RAG 集成** — 使用 LightRAG 和 RAG-Anything 进行知识检索
+- **代码执行** — 内置代码练习环境
+
+## 快速开始
+
+### 前置要求
+
+- Docker 和 Docker Compose
+- OpenAI API 密钥（必需）
+- 可选：Anthropic、Perplexity 或 DashScope API 密钥
+
+### 安装步骤
+
+1. **克隆仓库**
+
+    ```bash
+    git clone <your-compose-anything-repo>
+    cd apps/deeptutor
+    ```
+
+2. **配置环境变量**
+
+    ```bash
+    cp .env.example .env
+    # 编辑 .env 文件并添加您的 API 密钥
+    ```
+
+    **必需配置：**
+    - `OPENAI_API_KEY` — 您的 OpenAI API 密钥
+
+    **可选配置：**
+    - `ANTHROPIC_API_KEY` — 用于 Claude 模型
+    - `PERPLEXITY_API_KEY` — 用于网络搜索
+    - `DASHSCOPE_API_KEY` — 用于阿里云模型
+    - 如需调整端口（默认：后端 8001，前端 3782）
+    - 云端部署时设置 `NEXT_PUBLIC_API_BASE_EXTERNAL`
+
+3. **可选：自定义智能体配置**
+
+    创建 `config/agents.yaml` 文件以自定义智能体行为（详见[文档](https://hkuds.github.io/DeepTutor/guide/config.html)）。
+
+4. **启动服务**
+
+    ```bash
+    docker compose up -d
+    ```
+
+    首次运行需要约 30-60 秒初始化。
+
+5. **访问应用**
+
+      - **前端界面：** <http://localhost:3782>
+      - **后端 API：** <http://localhost:8001>
+      - **API 文档：** <http://localhost:8001/docs>
+
+## 使用方法
+
+### 创建知识库
+
+1. 访问 <http://localhost:3782/knowledge>
+2. 点击"新建知识库"
+3. 上传文档（支持 PDF、DOCX、TXT、Markdown、HTML 等）
+4. 等待处理完成
+
+### 学习模式
+
+- **求解（Solve）** — 获取问题的分步解决方案
+- **题目（Question）** — 基于学习材料生成练习题
+- **研究（Research）** — 通过多智能体协作进行深度研究
+- **协作写作（Co-Writer）** — 交互式写作和创意生成
+- **笔记（Notebook）** — 组织和管理学习材料
+- **引导（Guide）** — 遵循个性化学习路径
+
+### 高级功能
+
+- **代码执行** — 在界面中直接练习编码
+- **可视化图表** — 为复杂概念自动生成图表
+- **导出** — 将您的工作下载为 PDF 或 Markdown
+- **多语言支持** — 支持多种语言
+
+## 配置说明
+
+### 环境变量
+
+主要环境变量（所有选项见 [.env.example](.env.example)）：
+
+| 变量                     | 默认值   | 描述                 |
+| ------------------------ | -------- | -------------------- |
+| `OPENAI_API_KEY`         | （必需） | 您的 OpenAI API 密钥 |
+| `DEFAULT_MODEL`          | `gpt-4o` | 默认 LLM 模型        |
+| `BACKEND_PORT`           | `8001`   | 后端服务器端口       |
+| `FRONTEND_PORT`          | `3782`   | 前端应用端口         |
+| `DEEPTUTOR_CPU_LIMIT`    | `4.00`   | CPU 限制（核心数）   |
+| `DEEPTUTOR_MEMORY_LIMIT` | `8G`     | 内存限制             |
+
+### 端口说明
+
+- **8001** — 后端 API 服务器
+- **3782** — 前端 Web 界面
+
+### 数据卷
+
+- `deeptutor_data` — 用户数据、知识库和学习材料
+- `./config` — 自定义智能体配置（可选）
+
+## 资源要求
+
+**最低配置：**
+
+- CPU：1 核心
+- 内存：2GB
+- 磁盘：2GB + 知识库所需空间
+
+**推荐配置：**
+
+- CPU：4 核心
+- 内存：8GB
+- 磁盘：10GB+
+
+## 支持的模型
+
+DeepTutor 支持多个 LLM 提供商：
+
+- **OpenAI** — GPT-4、GPT-4 Turbo、GPT-3.5 Turbo
+- **Anthropic** — Claude 3（Opus、Sonnet、Haiku）
+- **Perplexity** — 用于网络搜索集成
+- **DashScope** — 阿里云模型
+- **OpenAI 兼容 API** — 任何与 OpenAI 格式兼容的 API
+
+## 故障排查
+
+### 后端启动失败
+
+- 验证 `.env` 中的 `OPENAI_API_KEY` 是否正确设置
+- 查看日志：`docker compose logs -f`
+- 确保端口 8001 和 3782 未被占用
+- 验证数据卷有足够的磁盘空间
+
+### 前端无法连接后端
+
+- 确认后端正在运行：访问 <http://localhost:8001/docs>
+- 云端部署时，将 `NEXT_PUBLIC_API_BASE_EXTERNAL` 设置为您的公网 URL
+- 检查防火墙设置
+
+### 知识库处理失败
+
+- 确保有足够的内存（推荐 8GB+）
+- 检查文档格式是否支持
+- 查看日志了解具体错误
+
+### API 速率限制
+
+- 在提供商控制台监控 API 使用情况
+- 考虑升级 API 计划
+- 为不同任务使用不同模型
+
+## 安全提示
+
+- **API 密钥** — 妥善保管您的 API 密钥，切勿提交到版本控制系统
+- **网络暴露** — 生产环境部署时，使用 HTTPS 和适当的身份验证
+- **数据隐私** — 用户数据存储在 Docker 卷中，请确保适当的备份和安全措施
+- **资源限制** — 设置合适的 CPU 和内存限制以防止资源耗尽
+
+## 更新
+
+更新到最新版本：
+
+```bash
+# 拉取最新镜像
+docker compose pull
+
+# 重新创建容器
+docker compose up -d
+```
+
+更新到特定版本，编辑 `.env` 中的 `DEEPTUTOR_VERSION` 并运行：
+
+```bash
+docker compose up -d
+```
+
+## 高级用法
+
+### 自定义智能体配置
+
+创建 `config/agents.yaml` 以自定义智能体行为：
+
+```yaml
+agents:
+  solver:
+    model: gpt-4o
+    temperature: 0.7
+  researcher:
+    model: gpt-4-turbo
+    max_tokens: 4000
+```
+
+详细配置选项请参见[官方文档](https://hkuds.github.io/DeepTutor/guide/config.html)。
+
+### 云端部署
+
+云端部署需要额外配置：
+
+1. 在 `.env` 中设置公网 URL：
+
+    ```env
+    NEXT_PUBLIC_API_BASE_EXTERNAL=https://your-domain.com:8001
+    ```
+
+2. 配置反向代理（nginx/Caddy）以支持 HTTPS
+3. 确保适当的防火墙规则
+4. 考虑使用特定环境的密钥管理
+
+### 使用不同的嵌入模型
+
+DeepTutor 默认使用 `text-embedding-3-large`。要使用不同的嵌入模型，请参考[官方文档](https://hkuds.github.io/DeepTutor/guide/config.html)。
+
+## 相关链接
+
+- **GitHub：** <https://github.com/HKUDS/DeepTutor>
+- **文档：** <https://hkuds.github.io/DeepTutor/>
+- **问题反馈：** <https://github.com/HKUDS/DeepTutor/issues>
+- **讨论区：** <https://github.com/HKUDS/DeepTutor/discussions>
+
+## 许可证
+
+DeepTutor 使用 Apache-2.0 许可证。详情请参见[官方仓库](https://github.com/HKUDS/DeepTutor)。
--- a/apps/deeptutor/docker-compose.yaml
+++ b/apps/deeptutor/docker-compose.yaml
@@ -0,0 +1,68 @@
+# DeepTutor: AI-Powered Personalized Learning Assistant
+# https://github.com/HKUDS/DeepTutor
+# Transform any document into an interactive learning experience with multi-agent intelligence
+
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  deeptutor:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-ghcr.io}/hkuds/deeptutor:${DEEPTUTOR_VERSION:-latest}
+    ports:
+      - "${DEEPTUTOR_BACKEND_PORT_OVERRIDE:-8001}:${BACKEND_PORT:-8001}"
+      - "${DEEPTUTOR_FRONTEND_PORT_OVERRIDE:-3782}:${FRONTEND_PORT:-3782}"
+    volumes:
+      - deeptutor_data:/app/data
+      - ./config:/app/config:ro
+    environment:
+      - TZ=${TZ:-UTC}
+      # Backend port
+      - BACKEND_PORT=${BACKEND_PORT:-8001}
+      # Frontend port
+      - FRONTEND_PORT=${FRONTEND_PORT:-3782}
+      # API base URLs
+      - NEXT_PUBLIC_API_BASE=${NEXT_PUBLIC_API_BASE:-http://localhost:8001}
+      - NEXT_PUBLIC_API_BASE_EXTERNAL=${NEXT_PUBLIC_API_BASE_EXTERNAL:-http://localhost:8001}
+      # LLM API Keys
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - OPENAI_BASE_URL=${OPENAI_BASE_URL:-https://api.openai.com/v1}
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+      - PERPLEXITY_API_KEY=${PERPLEXITY_API_KEY:-}
+      - DASHSCOPE_API_KEY=${DASHSCOPE_API_KEY:-}
+      # Default LLM model
+      - DEFAULT_MODEL=${DEFAULT_MODEL:-gpt-4o}
+      # User ID and Group ID for permission management
+      - PUID=${PUID:-1000}
+      - PGID=${PGID:-1000}
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "curl",
+          "-f",
+          "http://localhost:${BACKEND_PORT:-8001}/health",
+          "||",
+          "exit",
+          "1",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    deploy:
+      resources:
+        limits:
+          cpus: ${DEEPTUTOR_CPU_LIMIT:-4.00}
+          memory: ${DEEPTUTOR_MEMORY_LIMIT:-8G}
+        reservations:
+          cpus: ${DEEPTUTOR_CPU_RESERVATION:-1.00}
+          memory: ${DEEPTUTOR_MEMORY_RESERVATION:-2G}
+
+volumes:
+  deeptutor_data:
--- a/apps/moltbot/.env.example
+++ b/apps/moltbot/.env.example
@@ -0,0 +1,54 @@
+# MoltBot Environment Configuration
+# Copy this file to .env and configure the values
+
+# Timezone (default: UTC)
+TZ=UTC
+
+# Global container registry prefix (optional)
+# Examples: docker.io/, ghcr.io/, your-registry.com/
+GLOBAL_REGISTRY=
+
+# MoltBot Version
+# Use 'main' for latest, or specific version tag like 'v2026.1.27'
+MOLTBOT_VERSION=main
+
+# === Gateway Configuration ===
+# Gateway access token (REQUIRED - generate a secure random token)
+# Example: openssl rand -hex 32
+MOLTBOT_GATEWAY_TOKEN=your-secure-token-here
+
+# Gateway bind address
+# Options: loopback (127.0.0.1), lan (0.0.0.0 for LAN access)
+MOLTBOT_GATEWAY_BIND=lan
+
+# Gateway internal port (default: 18789)
+MOLTBOT_GATEWAY_PORT=18789
+
+# Gateway host port override (default: 18789)
+MOLTBOT_GATEWAY_PORT_OVERRIDE=18789
+
+# Bridge port override (default: 18790)
+MOLTBOT_BRIDGE_PORT_OVERRIDE=18790
+
+# === Model API Keys (Optional - if not using OAuth) ===
+# Anthropic Claude API Key
+ANTHROPIC_API_KEY=
+
+# OpenAI API Key
+OPENAI_API_KEY=
+
+# Claude AI Session Keys (for web session auth)
+CLAUDE_AI_SESSION_KEY=
+CLAUDE_WEB_SESSION_KEY=
+CLAUDE_WEB_COOKIE=
+
+# === Resource Limits ===
+# Gateway service resource limits
+MOLTBOT_CPU_LIMIT=2.0
+MOLTBOT_MEMORY_LIMIT=2G
+MOLTBOT_CPU_RESERVATION=1.0
+MOLTBOT_MEMORY_RESERVATION=1G
+
+# CLI service resource limits
+MOLTBOT_CLI_CPU_LIMIT=1.0
+MOLTBOT_CLI_MEMORY_LIMIT=512M
--- a/apps/moltbot/README.md
+++ b/apps/moltbot/README.md
@@ -0,0 +1,214 @@
+# MoltBot
+
+MoltBot is a personal AI assistant that runs on your own devices. It integrates with multiple messaging platforms (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, Microsoft Teams, WebChat) and provides AI-powered assistance across all your channels.
+
+## Features
+
+- **Multi-channel Support**: WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, Microsoft Teams, Matrix, Zalo, WebChat
+- **Local-first Gateway**: Single control plane for sessions, channels, tools, and events
+- **Multi-agent Routing**: Route inbound channels to isolated agents with per-agent sessions
+- **Voice Wake + Talk Mode**: Always-on speech for macOS/iOS/Android with ElevenLabs
+- **Live Canvas**: Agent-driven visual workspace with A2UI
+- **First-class Tools**: Browser, canvas, nodes, cron, sessions, and channel-specific actions
+- **Companion Apps**: macOS menu bar app + iOS/Android nodes
+- **Skills Platform**: Bundled, managed, and workspace skills with install gating
+
+## Quick Start
+
+1. Copy the example environment file:
+
+   ```bash
+   cp .env.example .env
+   ```
+
+2. Generate a secure gateway token:
+
+   ```bash
+   # Using OpenSSL
+   openssl rand -hex 32
+   
+   # Or using Python
+   python3 -c "import secrets; print(secrets.token_hex(32))"
+   ```
+
+3. Edit `.env` and set at least:
+   - `MOLTBOT_GATEWAY_TOKEN` - Your generated token
+   - `ANTHROPIC_API_KEY` or `OPENAI_API_KEY` - If using API key auth
+
+4. Start the gateway:
+
+   ```bash
+   docker compose up -d
+   ```
+
+5. Access the Control UI:
+   - Open <http://localhost:18789> in your browser
+   - Enter your gateway token when prompted
+
+## Configuration
+
+### Gateway Access
+
+The gateway can be accessed in two ways:
+
+- **Loopback** (`MOLTBOT_GATEWAY_BIND=loopback`): Only accessible from the host machine (127.0.0.1)
+- **LAN** (`MOLTBOT_GATEWAY_BIND=lan`): Accessible from your local network (0.0.0.0)
+
+For production deployments, consider:
+
+- Using Tailscale Serve/Funnel for secure remote access
+- Setting up SSH tunnels
+- Implementing reverse proxy with authentication
+
+### Model Configuration
+
+MoltBot supports multiple AI model providers:
+
+- **Anthropic Claude** (Recommended): Claude Pro/Max with OAuth or API key
+- **OpenAI**: ChatGPT/Codex with OAuth or API key
+- **Custom Providers**: Configure via the Control UI or config file
+
+Set API keys in `.env` or use OAuth authentication through the onboarding wizard.
+
+### Channel Integration
+
+To connect messaging platforms:
+
+1. **WhatsApp**: Use the CLI to link device
+
+   ```bash
+   docker compose run --rm moltbot-cli channels login
+   ```
+
+2. **Telegram**: Set `TELEGRAM_BOT_TOKEN` in config
+
+3. **Discord**: Set `DISCORD_BOT_TOKEN` in config
+
+4. **Slack**: Set `SLACK_BOT_TOKEN` and `SLACK_APP_TOKEN` in config
+
+See the [official documentation](https://docs.molt.bot/channels) for detailed setup instructions.
+
+## Using the CLI
+
+The CLI service is available via the `cli` profile:
+
+```bash
+# Run onboarding wizard
+docker compose run --rm --service-ports moltbot-cli onboard
+
+# List providers
+docker compose run --rm moltbot-cli providers list
+
+# Send a message
+docker compose run --rm moltbot-cli message send --to +1234567890 --message "Hello"
+
+# Check health
+docker compose run --rm moltbot-cli health --port 18789
+```
+
+## Security Considerations
+
+1. **Gateway Token**: Keep your gateway token secure. This is the authentication method for the Control UI and WebSocket connections.
+
+2. **DM Access**: By default, MoltBot uses pairing mode for direct messages from unknown senders. They receive a pairing code that you must approve.
+
+3. **Network Exposure**: If exposing the gateway beyond localhost, use proper authentication and encryption:
+   - Set up Tailscale for secure remote access
+   - Use SSH tunnels
+   - Implement reverse proxy with HTTPS and authentication
+
+4. **API Keys**: Never commit API keys to version control. Use `.env` file or secrets management.
+
+5. **Sandbox Mode**: For group/channel safety, enable sandbox mode to run non-main sessions in Docker containers.
+
+## Advanced Configuration
+
+### Resource Limits
+
+Adjust CPU and memory limits in `.env`:
+
+```env
+MOLTBOT_CPU_LIMIT=2.0
+MOLTBOT_MEMORY_LIMIT=2G
+MOLTBOT_CPU_RESERVATION=1.0
+MOLTBOT_MEMORY_RESERVATION=1G
+```
+
+### Persistent Data
+
+Data is stored in two Docker volumes:
+
+- `moltbot_config`: Configuration files and credentials (~/.clawdbot)
+- `moltbot_workspace`: Agent workspace and skills (~/clawd)
+
+To backup your data:
+
+```bash
+docker run --rm -v moltbot_config:/data -v $(pwd):/backup alpine tar czf /backup/moltbot-config-backup.tar.gz /data
+docker run --rm -v moltbot_workspace:/data -v $(pwd):/backup alpine tar czf /backup/moltbot-workspace-backup.tar.gz /data
+```
+
+### Custom Configuration File
+
+Create a custom config file at `~/.clawdbot/moltbot.json` (inside the container):
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "model": {
+        "primary": "anthropic/claude-opus-4-5",
+        "fallbacks": ["anthropic/claude-sonnet-4-5", "openai/gpt-4o"]
+      }
+    }
+  }
+}
+```
+
+## Troubleshooting
+
+### Gateway Won't Start
+
+1. Check logs: `docker compose logs moltbot-gateway`
+2. Verify gateway token is set in `.env`
+3. Ensure port 18789 is not already in use
+
+### Can't Access Control UI
+
+1. Verify gateway bind setting matches your access method
+2. Check firewall rules if accessing from another machine
+3. Ensure container is healthy: `docker compose ps`
+
+### Model API Errors
+
+1. Verify API keys are correctly set in `.env`
+2. Check API key validity and quota
+3. Review logs for specific error messages
+
+### Run Doctor Command
+
+The doctor command helps diagnose common issues:
+
+```bash
+docker compose run --rm moltbot-cli doctor
+```
+
+## Documentation
+
+- [Official Website](https://molt.bot)
+- [Full Documentation](https://docs.molt.bot)
+- [Getting Started Guide](https://docs.molt.bot/start/getting-started)
+- [Configuration Reference](https://docs.molt.bot/gateway/configuration)
+- [Security Guide](https://docs.molt.bot/gateway/security)
+- [Docker Installation](https://docs.molt.bot/install/docker)
+- [GitHub Repository](https://github.com/moltbot/moltbot)
+
+## License
+
+MoltBot is released under the MIT License. See the [LICENSE](https://github.com/moltbot/moltbot/blob/main/LICENSE) file for details.
+
+## Community
+
+- [Discord](https://discord.gg/clawd)
+- [GitHub Discussions](https://github.com/moltbot/moltbot/discussions)
+- [Issues](https://github.com/moltbot/moltbot/issues)
--- a/apps/moltbot/README.zh.md
+++ b/apps/moltbot/README.zh.md
@@ -0,0 +1,214 @@
+# MoltBot
+
+MoltBot 是一个运行在你自己设备上的个人 AI 助手。它集成了多个消息平台（WhatsApp、Telegram、Slack、Discord、Google Chat、Signal、iMessage、Microsoft Teams、WebChat），并在所有频道上提供 AI 驱动的帮助。
+
+## 功能特性
+
+- **多频道支持**：WhatsApp、Telegram、Slack、Discord、Google Chat、Signal、iMessage、BlueBubbles、Microsoft Teams、Matrix、Zalo、WebChat
+- **本地优先网关**：会话、频道、工具和事件的统一控制平面
+- **多代理路由**：将入站频道路由到具有独立会话的隔离代理
+- **语音唤醒 + 对话模式**：macOS/iOS/Android 上的永久在线语音支持（使用 ElevenLabs）
+- **实时画布**：由代理驱动的可视化工作空间，支持 A2UI
+- **一流工具**：浏览器、画布、节点、定时任务、会话和特定频道的操作
+- **配套应用**：macOS 菜单栏应用 + iOS/Android 节点
+- **技能平台**：内置、托管和工作区技能，支持安装门控
+
+## 快速开始
+
+1. 复制示例环境文件：
+
+   ```bash
+   cp .env.example .env
+   ```
+
+2. 生成安全的网关令牌：
+
+   ```bash
+   # 使用 OpenSSL
+   openssl rand -hex 32
+   
+   # 或使用 Python
+   python3 -c "import secrets; print(secrets.token_hex(32))"
+   ```
+
+3. 编辑 `.env` 文件，至少设置：
+   - `MOLTBOT_GATEWAY_TOKEN` - 你生成的令牌
+   - `ANTHROPIC_API_KEY` 或 `OPENAI_API_KEY` - 如果使用 API 密钥认证
+
+4. 启动网关：
+
+   ```bash
+   docker compose up -d
+   ```
+
+5. 访问控制界面：
+   - 在浏览器中打开 <http://localhost:18789>
+   - 在提示时输入你的网关令牌
+
+## 配置
+
+### 网关访问
+
+网关可以通过两种方式访问：
+
+- **回环地址**（`MOLTBOT_GATEWAY_BIND=loopback`）：仅从主机访问（127.0.0.1）
+- **局域网**（`MOLTBOT_GATEWAY_BIND=lan`）：从本地网络访问（0.0.0.0）
+
+对于生产部署，建议：
+
+- 使用 Tailscale Serve/Funnel 进行安全的远程访问
+- 设置 SSH 隧道
+- 实现带认证的反向代理
+
+### 模型配置
+
+MoltBot 支持多个 AI 模型提供商：
+
+- **Anthropic Claude**（推荐）：Claude Pro/Max，支持 OAuth 或 API 密钥
+- **OpenAI**：ChatGPT/Codex，支持 OAuth 或 API 密钥
+- **自定义提供商**：通过控制界面或配置文件进行配置
+
+在 `.env` 文件中设置 API 密钥，或通过入门向导使用 OAuth 认证。
+
+### 频道集成
+
+连接消息平台：
+
+1. **WhatsApp**：使用 CLI 链接设备
+
+   ```bash
+   docker compose run --rm moltbot-cli channels login
+   ```
+
+2. **Telegram**：在配置中设置 `TELEGRAM_BOT_TOKEN`
+
+3. **Discord**：在配置中设置 `DISCORD_BOT_TOKEN`
+
+4. **Slack**：在配置中设置 `SLACK_BOT_TOKEN` 和 `SLACK_APP_TOKEN`
+
+详细设置说明请参阅[官方文档](https://docs.molt.bot/channels)。
+
+## 使用命令行界面
+
+CLI 服务可通过 `cli` 配置文件使用：
+
+```bash
+# 运行入门向导
+docker compose run --rm --service-ports moltbot-cli onboard
+
+# 列出提供商
+docker compose run --rm moltbot-cli providers list
+
+# 发送消息
+docker compose run --rm moltbot-cli message send --to +1234567890 --message "你好"
+
+# 检查健康状态
+docker compose run --rm moltbot-cli health --port 18789
+```
+
+## 安全注意事项
+
+1. **网关令牌**：保护好你的网关令牌。这是控制界面和 WebSocket 连接的认证方式。
+
+2. **私信访问**：默认情况下，MoltBot 对来自未知发送者的私信使用配对模式。他们会收到一个配对码，你必须批准。
+
+3. **网络暴露**：如果在 localhost 之外暴露网关，请使用适当的认证和加密：
+   - 设置 Tailscale 进行安全的远程访问
+   - 使用 SSH 隧道
+   - 实现带 HTTPS 和认证的反向代理
+
+4. **API 密钥**：永远不要将 API 密钥提交到版本控制。使用 `.env` 文件或密钥管理。
+
+5. **沙箱模式**：为了群组/频道安全，启用沙箱模式以在 Docker 容器中运行非主会话。
+
+## 高级配置
+
+### 资源限制
+
+在 `.env` 文件中调整 CPU 和内存限制：
+
+```env
+MOLTBOT_CPU_LIMIT=2.0
+MOLTBOT_MEMORY_LIMIT=2G
+MOLTBOT_CPU_RESERVATION=1.0
+MOLTBOT_MEMORY_RESERVATION=1G
+```
+
+### 持久化数据
+
+数据存储在两个 Docker 卷中：
+
+- `moltbot_config`：配置文件和凭据（~/.clawdbot）
+- `moltbot_workspace`：代理工作区和技能（~/clawd）
+
+备份数据：
+
+```bash
+docker run --rm -v moltbot_config:/data -v $(pwd):/backup alpine tar czf /backup/moltbot-config-backup.tar.gz /data
+docker run --rm -v moltbot_workspace:/data -v $(pwd):/backup alpine tar czf /backup/moltbot-workspace-backup.tar.gz /data
+```
+
+### 自定义配置文件
+
+在 `~/.clawdbot/moltbot.json`（容器内）创建自定义配置文件：
+
+```json
+{
+  "agents": {
+    "defaults": {
+      "model": {
+        "primary": "anthropic/claude-opus-4-5",
+        "fallbacks": ["anthropic/claude-sonnet-4-5", "openai/gpt-4o"]
+      }
+    }
+  }
+}
+```
+
+## 故障排除
+
+### 网关无法启动
+
+1. 检查日志：`docker compose logs moltbot-gateway`
+2. 验证网关令牌是否在 `.env` 中设置
+3. 确保端口 18789 未被占用
+
+### 无法访问控制界面
+
+1. 验证网关绑定设置是否与你的访问方式匹配
+2. 如果从另一台机器访问，检查防火墙规则
+3. 确保容器健康：`docker compose ps`
+
+### 模型 API 错误
+
+1. 验证 API 密钥是否在 `.env` 中正确设置
+2. 检查 API 密钥有效性和配额
+3. 查看日志中的具体错误消息
+
+### 运行诊断命令
+
+诊断命令可帮助诊断常见问题：
+
+```bash
+docker compose run --rm moltbot-cli doctor
+```
+
+## 文档
+
+- [官方网站](https://molt.bot)
+- [完整文档](https://docs.molt.bot)
+- [入门指南](https://docs.molt.bot/start/getting-started)
+- [配置参考](https://docs.molt.bot/gateway/configuration)
+- [安全指南](https://docs.molt.bot/gateway/security)
+- [Docker 安装](https://docs.molt.bot/install/docker)
+- [GitHub 仓库](https://github.com/moltbot/moltbot)
+
+## 许可证
+
+MoltBot 使用 MIT 许可证发布。详情请参阅 [LICENSE](https://github.com/moltbot/moltbot/blob/main/LICENSE) 文件。
+
+## 社区
+
+- [Discord](https://discord.gg/clawd)
+- [GitHub 讨论](https://github.com/moltbot/moltbot/discussions)
+- [问题跟踪](https://github.com/moltbot/moltbot/issues)
--- a/apps/moltbot/docker-compose.yaml
+++ b/apps/moltbot/docker-compose.yaml
@@ -0,0 +1,88 @@
+# MoltBot - Personal AI Assistant Docker Compose Configuration
+# Official Repository: https://github.com/moltbot/moltbot
+# Documentation: https://docs.molt.bot
+
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  moltbot-gateway:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-ghcr.io}/moltbot/moltbot:${MOLTBOT_VERSION:-main}
+    environment:
+      - TZ=${TZ:-UTC}
+      - HOME=/home/node
+      - NODE_ENV=production
+      - TERM=xterm-256color
+      # Gateway configuration
+      - CLAWDBOT_GATEWAY_TOKEN=${MOLTBOT_GATEWAY_TOKEN}
+      - CLAWDBOT_GATEWAY_BIND=${MOLTBOT_GATEWAY_BIND:-lan}
+      - CLAWDBOT_GATEWAY_PORT=${MOLTBOT_GATEWAY_PORT:-18789}
+      # Optional: Model API keys (if not using OAuth)
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - CLAUDE_AI_SESSION_KEY=${CLAUDE_AI_SESSION_KEY:-}
+      - CLAUDE_WEB_SESSION_KEY=${CLAUDE_WEB_SESSION_KEY:-}
+      - CLAUDE_WEB_COOKIE=${CLAUDE_WEB_COOKIE:-}
+    volumes:
+      - moltbot_config:/home/node/.clawdbot
+      - moltbot_workspace:/home/node/clawd
+    ports:
+      - "${MOLTBOT_GATEWAY_PORT_OVERRIDE:-18789}:18789"
+      - "${MOLTBOT_BRIDGE_PORT_OVERRIDE:-18790}:18790"
+    command:
+      - node
+      - dist/index.js
+      - gateway
+      - --bind
+      - "${MOLTBOT_GATEWAY_BIND:-lan}"
+      - --port
+      - "18789"
+    healthcheck:
+      test: ["CMD", "node", "dist/index.js", "health", "--port", "18789"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    deploy:
+      resources:
+        limits:
+          cpus: ${MOLTBOT_CPU_LIMIT:-2.0}
+          memory: ${MOLTBOT_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${MOLTBOT_CPU_RESERVATION:-1.0}
+          memory: ${MOLTBOT_MEMORY_RESERVATION:-1G}
+
+  moltbot-cli:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-ghcr.io}/moltbot/moltbot:${MOLTBOT_VERSION:-main}
+    environment:
+      - TZ=${TZ:-UTC}
+      - HOME=/home/node
+      - TERM=xterm-256color
+      - BROWSER=echo
+      - CLAUDE_AI_SESSION_KEY=${CLAUDE_AI_SESSION_KEY:-}
+      - CLAUDE_WEB_SESSION_KEY=${CLAUDE_WEB_SESSION_KEY:-}
+      - CLAUDE_WEB_COOKIE=${CLAUDE_WEB_COOKIE:-}
+    volumes:
+      - moltbot_config:/home/node/.clawdbot
+      - moltbot_workspace:/home/node/clawd
+    stdin_open: true
+    tty: true
+    entrypoint: ["node", "dist/index.js"]
+    profiles:
+      - cli
+    deploy:
+      resources:
+        limits:
+          cpus: ${MOLTBOT_CLI_CPU_LIMIT:-1.0}
+          memory: ${MOLTBOT_CLI_MEMORY_LIMIT:-512M}
+
+volumes:
+  moltbot_config:
+  moltbot_workspace:
--- a/builds/microsandbox/README.md
+++ b/builds/microsandbox/README.md
@@ -102,7 +102,7 @@ docker compose run --rm microsandbox --help
 ### Environment Variables

 | Variable                          | Description                           | Default     |
-| --------------------------------- | -------------------------------------- | --------- |
+| --------------------------------- | ------------------------------------- | ----------- |
 | `MICROSANDBOX_VERSION`            | MicroSandbox version                  | `latest`    |
 | `DEBIAN_VERSION`                  | Debian base image version             | `13.2-slim` |
 | `MICROSANDBOX_AUTO_PULL_IMAGES`   | Auto pull base images on build        | `true`      |
--- a/builds/microsandbox/README.zh.md
+++ b/builds/microsandbox/README.zh.md
@@ -102,7 +102,7 @@ docker compose run --rm microsandbox --help
 ### 环境变量

 | 变量                              | 描述                          | 默认值      |
-| --------------------------------- | ------------------------ | ----------- |
+| --------------------------------- | ----------------------------- | ----------- |
 | `MICROSANDBOX_VERSION`            | MicroSandbox 版本             | `latest`    |
 | `DEBIAN_VERSION`                  | Debian 基础镜像版本           | `13.2-slim` |
 | `MICROSANDBOX_AUTO_PULL_IMAGES`   | 构建时自动拉取基础镜像        | `true`      |
--- a/builds/microsandbox/docker-compose.yaml
+++ b/builds/microsandbox/docker-compose.yaml
@@ -23,7 +23,7 @@ services:
        - DEBIAN_VERSION=${DEBIAN_VERSION:-13.2-slim}
        - MICROSANDBOX_VERSION=${MICROSANDBOX_VERSION:-}
        - MICROSANDBOX_AUTO_PULL_IMAGES=${MICROSANDBOX_AUTO_PULL_IMAGES:-true}
-    image: ${GLOBAL_REGISTRY:-ghcr.io/zerocore-ai/}microsandbox:${MICROSANDBOX_VERSION:-latest}
+    image: ${GLOBAL_REGISTRY:-ghcr.io}/zerocore-ai/microsandbox:${MICROSANDBOX_VERSION:-latest}
    ports:
      - "${MICROSANDBOX_PORT_OVERRIDE:-5555}:${MICROSANDBOX_PORT:-5555}"
    # Privileged mode and relaxed security profiles are required for KVM access
--- a/builds/mineru/.env.example
+++ b/builds/mineru/.env.example
@@ -1,5 +1,5 @@
 # MinerU Docker image
-MINERU_VERSION=2.7.1
+MINERU_VERSION=2.7.3

 # Port configurations
 MINERU_PORT_OVERRIDE_VLLM=30000
--- a/builds/mineru/Dockerfile
+++ b/builds/mineru/Dockerfile
@@ -19,7 +19,7 @@ RUN apt-get update && \
    rm -rf /var/lib/apt/lists/*

 # Install mineru latest
-RUN python3 -m pip install -U 'mineru[core]>=2.7.1' --break-system-packages && \
+RUN python3 -m pip install -U 'mineru[core]>=2.7.3' --break-system-packages && \
    python3 -m pip cache purge

 # Download models and update the configuration file
--- a/builds/mineru/README.md
+++ b/builds/mineru/README.md
@@ -39,7 +39,7 @@ mineru -p demo.pdf -o ./output -b vlm-http-client -u http://localhost:30000

 ## Configuration

- `MINERU_VERSION`: The version for MinerU, default is `2.7.1`.
+- `MINERU_VERSION`: The version for MinerU, default is `2.7.3`.
 - `MINERU_PORT_OVERRIDE_VLLM`: The host port for the VLLM server, default is `30000`.
 - `MINERU_PORT_OVERRIDE_API`: The host port for the API service, default is `8000`.
 - `MINERU_PORT_OVERRIDE_GRADIO`: The host port for the Gradio WebUI, default is `7860`.
--- a/builds/mineru/README.zh.md
+++ b/builds/mineru/README.zh.md
@@ -39,7 +39,7 @@ mineru -p demo.pdf -o ./output -b vlm-http-client -u http://localhost:30000

 ## 配置

- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.7.1`。
+- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.7.3`。
 - `MINERU_PORT_OVERRIDE_VLLM`: VLLM 服务器的主机端口，默认为 `30000`。
 - `MINERU_PORT_OVERRIDE_API`: API 服务的主机端口，默认为 `8000`。
 - `MINERU_PORT_OVERRIDE_GRADIO`: Gradio WebUI 的主机端口，默认为 `7860`。
--- a/builds/mineru/docker-compose.yaml
+++ b/builds/mineru/docker-compose.yaml
@@ -8,7 +8,7 @@ x-defaults: &defaults

 x-mineru-vllm: &mineru-vllm
  <<: *defaults
-  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.7.1}
+  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.7.3}
  build:
    context: .
    dockerfile: Dockerfile
@@ -45,29 +45,10 @@ services:
      - ${MINERU_PORT_OVERRIDE_VLLM:-30000}:30000
    entrypoint: mineru-openai-server
    command:
-      # ==================== Engine Selection ====================
-      # WARNING: Only ONE engine can be enabled at a time!
-      # Choose 'vllm' OR 'lmdeploy' (uncomment one line below)
-      - --engine vllm
-      # --engine lmdeploy
-
-      # ==================== vLLM Engine Parameters ====================
-      # Uncomment if using --engine vllm
-      - --host 0.0.0.0
-      - --port 30000
-      # Multi-GPU configuration (increase throughput)
-      # --data-parallel-size 2
-      # Single GPU memory optimization (reduce if VRAM insufficient)
-      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if issues persist
-
-      # ==================== LMDeploy Engine Parameters ====================
-      # Uncomment if using --engine lmdeploy
-      # --server-name 0.0.0.0
-      # --server-port 30000
-      # Multi-GPU configuration (increase throughput)
-      # --dp 2
-      # Single GPU memory optimization (reduce if VRAM insufficient)
-      # --cache-max-entry-count 0.5  # Try 0.4 or lower if issues persist
+      --host 0.0.0.0
+      --port 30000
+      # --data-parallel-size 2  # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
+      # --gpu-memory-utilization 0.9 # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
      interval: 30s
@@ -82,21 +63,11 @@ services:
      - ${MINERU_PORT_OVERRIDE_API:-8000}:8000
    entrypoint: mineru-api
    command:
-      # ==================== Server Configuration ====================
-      - --host 0.0.0.0
-      - --port 8000
-
-      # ==================== vLLM Engine Parameters ====================
-      # Multi-GPU configuration
-      # --data-parallel-size 2
-      # Single GPU memory optimization
-      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient
-
-      # ==================== LMDeploy Engine Parameters ====================
-      # Multi-GPU configuration
-      # --dp 2
-      # Single GPU memory optimization
-      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
+      --host 0.0.0.0
+      --port 8000
+      # parameters for vllm-engine
+      # --data-parallel-size 2  # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
+      # --gpu-memory-utilization 0.5  # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
    healthcheck:
      test:
        [
@@ -105,7 +76,7 @@ services:
          "--no-verbose",
          "--tries=1",
          "--spider",
-          "http://localhost:8000/health",
+          "http://localhost:8000/docs",
        ]
      interval: 30s
      timeout: 10s
@@ -119,30 +90,13 @@ services:
      - ${MINERU_PORT_OVERRIDE_GRADIO:-7860}:7860
    entrypoint: mineru-gradio
    command:
-      # ==================== Gradio Server Configuration ====================
-      - --server-name 0.0.0.0
-      - --server-port 7860
-
-      # ==================== Gradio Feature Settings ====================
-      # --enable-api false  # Disable API endpoint
-      # --max-convert-pages 20  # Limit conversion page count
-
-      # ==================== Engine Selection ====================
-      # WARNING: Only ONE engine can be enabled at a time!
-
-      # Option 1: vLLM Engine (recommended for most users)
-      - --enable-vllm-engine true
-      # Multi-GPU configuration
-      # --data-parallel-size 2
-      # Single GPU memory optimization
-      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient
-
-      # Option 2: LMDeploy Engine
-      # --enable-lmdeploy-engine true
-      # Multi-GPU configuration
-      # --dp 2
-      # Single GPU memory optimization
-      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
+      --server-name 0.0.0.0
+      --server-port 7860
+      # --enable-api false  # If you want to disable the API, set this to false
+      # --max-convert-pages 20  # If you want to limit the number of pages for conversion, set this to a specific number
+      # parameters for vllm-engine
+      # --data-parallel-size 2  # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
+      # --gpu-memory-utilization 0.5  # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
    healthcheck:
      test:
        [
--- a/src/bytebot/docker-compose.yaml
+++ b/src/bytebot/docker-compose.yaml
@@ -24,7 +24,15 @@ services:
          cpus: ${BYTEBOT_DESKTOP_CPU_RESERVATION:-1.0}
          memory: ${BYTEBOT_DESKTOP_MEMORY_RESERVATION:-2G}
    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9990/"]
+      test:
+        [
+          "CMD",
+          "wget",
+          "--no-verbose",
+          "--tries=1",
+          "--spider",
+          "http://localhost:9990/",
+        ]
      interval: 30s
      timeout: 10s
      retries: 3
@@ -56,7 +64,15 @@ services:
          cpus: ${BYTEBOT_AGENT_CPU_RESERVATION:-0.5}
          memory: ${BYTEBOT_AGENT_MEMORY_RESERVATION:-512M}
    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9991/health"]
+      test:
+        [
+          "CMD",
+          "wget",
+          "--no-verbose",
+          "--tries=1",
+          "--spider",
+          "http://localhost:9991/health",
+        ]
      interval: 30s
      timeout: 10s
      retries: 3
@@ -83,7 +99,15 @@ services:
          cpus: ${BYTEBOT_UI_CPU_RESERVATION:-0.25}
          memory: ${BYTEBOT_UI_MEMORY_RESERVATION:-256M}
    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9992/"]
+      test:
+        [
+          "CMD",
+          "wget",
+          "--no-verbose",
+          "--tries=1",
+          "--spider",
+          "http://localhost:9992/",
+        ]
      interval: 30s
      timeout: 10s
      retries: 3
--- a/src/falkordb/.env.example
+++ b/src/falkordb/.env.example
@@ -0,0 +1,18 @@
+# FalkorDB Version
+# Latest stable version can be found at https://hub.docker.com/r/falkordb/falkordb/tags
+FALKORDB_VERSION=v4.14.11
+
+# Port configuration
+# Port for Redis protocol (Graph Database)
+FALKORDB_PORT_OVERRIDE=6379
+# Port for FalkorDB Browser UI
+FALKORDB_BROWSER_PORT_OVERRIDE=3000
+
+# Resource limits
+FALKORDB_CPU_LIMIT=1.00
+FALKORDB_MEMORY_LIMIT=2G
+FALKORDB_CPU_RESERVATION=0.25
+FALKORDB_MEMORY_RESERVATION=512M
+
+# Timezone
+TZ=UTC
--- a/src/falkordb/README.md
+++ b/src/falkordb/README.md
@@ -0,0 +1,31 @@
+# FalkorDB
+
+[FalkorDB](https://falkordb.com/) is a low-latency property graph database that leverages sparse matrices and linear algebra for high-performance graph queries. It is a community-driven fork of RedisGraph, optimized for large-scale knowledge graphs and AI-powered applications.
+
+## Getting Started
+
+1. Copy `.env.example` to `.env` and adjust the configuration as needed.
+2. Start the service:
+
+   ```bash
+   docker compose up -d
+   ```
+
+3. Access the FalkorDB Browser at `http://localhost:3000`.
+4. Connect to the database using `redis-cli` or any Redis-compatible client on port `6379`.
+
+## Environment Variables
+
+| Variable                         | Description                  | Default    |
+| -------------------------------- | ---------------------------- | ---------- |
+| `FALKORDB_VERSION`               | Version of FalkorDB image    | `v4.14.11` |
+| `FALKORDB_PORT_OVERRIDE`         | Host port for Redis protocol | `6379`     |
+| `FALKORDB_BROWSER_PORT_OVERRIDE` | Host port for Browser UI     | `3000`     |
+| `FALKORDB_CPU_LIMIT`             | Maximum CPU cycles           | `1.00`     |
+| `FALKORDB_MEMORY_LIMIT`          | Maximum memory               | `2G`       |
+
+## Resources
+
+- [Official Documentation](https://docs.falkordb.com/)
+- [GitHub Repository](https://github.com/FalkorDB/FalkorDB)
+- [Docker Hub](https://hub.docker.com/r/falkordb/falkordb)
--- a/src/falkordb/README.zh.md
+++ b/src/falkordb/README.zh.md
@@ -0,0 +1,31 @@
+# FalkorDB
+
+[FalkorDB](https://falkordb.com/) 是一个低延迟的属性图数据库，利用稀疏矩阵和线性代数实现高性能图查询。它是 RedisGraph 的社区驱动分支，针对大规模知识图谱和 AI 驱动的应用进行了优化。
+
+## 快速开始
+
+1. 将 `.env.example` 复制为 `.env` 并根据需要调整配置。
+2. 启动服务：
+
+   ```bash
+   docker compose up -d
+   ```
+
+3. 通过 `http://localhost:3000` 访问 FalkorDB Browser 界面。
+4. 使用 `redis-cli` 或任何兼容 Redis 的客户端连接到 `6379` 端口。
+
+## 环境变量
+
+| 变量名                           | 描述                 | 默认值     |
+| -------------------------------- | -------------------- | ---------- |
+| `FALKORDB_VERSION`               | FalkorDB 镜像版本    | `v4.14.11` |
+| `FALKORDB_PORT_OVERRIDE`         | Redis 协议的主机端口 | `6379`     |
+| `FALKORDB_BROWSER_PORT_OVERRIDE` | 浏览器界面的主机端口 | `3000`     |
+| `FALKORDB_CPU_LIMIT`             | 最大 CPU 使用率      | `1.00`     |
+| `FALKORDB_MEMORY_LIMIT`          | 最大内存限制         | `2G`       |
+
+## 相关资源
+
+- [官方文档](https://docs.falkordb.com/)
+- [GitHub 仓库](https://github.com/FalkorDB/FalkorDB)
+- [Docker Hub](https://hub.docker.com/r/falkordb/falkordb)
--- a/src/falkordb/docker-compose.yaml
+++ b/src/falkordb/docker-compose.yaml
@@ -0,0 +1,36 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  falkordb:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}falkordb/falkordb:${FALKORDB_VERSION:-v4.14.11}
+    ports:
+      - "${FALKORDB_PORT_OVERRIDE:-6379}:6379"
+      - "${FALKORDB_BROWSER_PORT_OVERRIDE:-3000}:3000"
+    volumes:
+      - falkordb_data:/data
+    environment:
+      - TZ=${TZ:-UTC}
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 10s
+    deploy:
+      resources:
+        limits:
+          cpus: ${FALKORDB_CPU_LIMIT:-1.00}
+          memory: ${FALKORDB_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${FALKORDB_CPU_RESERVATION:-0.25}
+          memory: ${FALKORDB_MEMORY_RESERVATION:-512M}
+
+volumes:
+  falkordb_data:
--- a/src/flowise/.env.example
+++ b/src/flowise/.env.example
@@ -0,0 +1,21 @@
+# Global Registry Prefix (optional)
+# GLOBAL_REGISTRY=
+
+# Flowise Image Version
+FLOWISE_VERSION=3.0.12
+
+# Timezone
+TZ=UTC
+
+# Port to bind to on the host machine
+FLOWISE_PORT_OVERRIDE=3000
+
+# Resource Limits
+FLOWISE_CPU_LIMIT=1
+FLOWISE_MEMORY_LIMIT=1024M
+FLOWISE_CPU_RESERVATION=0.5
+FLOWISE_MEMORY_RESERVATION=512M
+
+# Optional basic auth (leave empty to disable)
+# FLOWISE_USERNAME=
+# FLOWISE_PASSWORD=
--- a/src/flowise/README.md
+++ b/src/flowise/README.md
@@ -0,0 +1,32 @@
+# Flowise
+
+[English](./README.md) | [中文](./README.zh.md)
+
+Quick start: <https://docs.flowiseai.com>.
+
+This service deploys Flowise, a visual LLM orchestration platform.
+
+## Services
+
+- `flowise`: The Flowise service.
+
+## Configuration
+
+- `GLOBAL_REGISTRY`: The registry prefix for the Flowise image, default is empty.
+- `FLOWISE_VERSION`: The version of the Flowise image, default is `3.0.12`.
+- `TZ`: The timezone for the container, default is `UTC`.
+- `FLOWISE_PORT_OVERRIDE`: The host port for Flowise, default is `3000`.
+- `FLOWISE_CPU_LIMIT`: The CPU limit for the Flowise service, default is `1`.
+- `FLOWISE_MEMORY_LIMIT`: The memory limit for the Flowise service, default is `1024M`.
+- `FLOWISE_CPU_RESERVATION`: The CPU reservation for the Flowise service, default is `0.5`.
+- `FLOWISE_MEMORY_RESERVATION`: The memory reservation for the Flowise service, default is `512M`.
+- `FLOWISE_USERNAME`: Optional basic auth username. Leave empty to disable.
+- `FLOWISE_PASSWORD`: Optional basic auth password. Leave empty to disable.
+
+## Volumes
+
+- `flowise_data`: A volume for storing Flowise data.
+
+## Notes
+
+- The health check uses the `/api/v1/ping` endpoint.
--- a/src/flowise/README.zh.md
+++ b/src/flowise/README.zh.md
@@ -0,0 +1,32 @@
+# Flowise
+
+[English](./README.md) | [中文](./README.zh.md)
+
+快速开始：<https://docs.flowiseai.com>。
+
+此服务用于部署 Flowise，一个可视化的 LLM 编排平台。
+
+## 服务
+
+- `flowise`：Flowise 服务。
+
+## 配置
+
+- `GLOBAL_REGISTRY`：Flowise 镜像的仓库前缀，默认为空。
+- `FLOWISE_VERSION`：Flowise 镜像版本，默认是 `3.0.12`。
+- `TZ`：容器时区，默认是 `UTC`。
+- `FLOWISE_PORT_OVERRIDE`：Flowise 的宿主机端口，默认是 `3000`。
+- `FLOWISE_CPU_LIMIT`：Flowise 服务的 CPU 限制，默认是 `1`。
+- `FLOWISE_MEMORY_LIMIT`：Flowise 服务的内存限制，默认是 `1024M`。
+- `FLOWISE_CPU_RESERVATION`：Flowise 服务的 CPU 预留，默认是 `0.5`。
+- `FLOWISE_MEMORY_RESERVATION`：Flowise 服务的内存预留，默认是 `512M`。
+- `FLOWISE_USERNAME`：可选的基础认证用户名，不设置则禁用。
+- `FLOWISE_PASSWORD`：可选的基础认证密码，不设置则禁用。
+
+## 数据卷
+
+- `flowise_data`：用于存储 Flowise 数据的卷。
+
+## 说明
+
+- 健康检查使用 `/api/v1/ping` 端点。
--- a/src/flowise/docker-compose.yaml
+++ b/src/flowise/docker-compose.yaml
@@ -0,0 +1,44 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  flowise:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}flowiseai/flowise:${FLOWISE_VERSION:-3.0.12}
+    ports:
+      - "${FLOWISE_PORT_OVERRIDE:-3000}:3000"
+    volumes:
+      - flowise_data:/root/.flowise
+    environment:
+      - TZ=${TZ:-UTC}
+      - PORT=3000
+      - FLOWISE_USERNAME=${FLOWISE_USERNAME:-}
+      - FLOWISE_PASSWORD=${FLOWISE_PASSWORD:-}
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "node",
+          "-e",
+          "require('http').get('http://localhost:3000/api/v1/ping',res=>process.exit(res.statusCode===200?0:1)).on('error',()=>process.exit(1))"
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 20s
+    deploy:
+      resources:
+        limits:
+          cpus: ${FLOWISE_CPU_LIMIT:-1}
+          memory: ${FLOWISE_MEMORY_LIMIT:-1024M}
+        reservations:
+          cpus: ${FLOWISE_CPU_RESERVATION:-0.5}
+          memory: ${FLOWISE_MEMORY_RESERVATION:-512M}
+
+volumes:
+  flowise_data:
--- a/src/gitea-runner/.env.example
+++ b/src/gitea-runner/.env.example
@@ -1,5 +1,5 @@
 # Gitea Runner version
-GITEA_RUNNER_VERSION=0.2.13-dind
+GITEA_RUNNER_VERSION=0.2.13

 # Gitea instance URL
 INSTANCE_URL=http://localhost:3000
--- a/src/gitea-runner/config.yaml
+++ b/src/gitea-runner/config.yaml
@@ -36,7 +36,7 @@ runner:
  # It works when something like `uses: actions/checkout@v4` is used and DEFAULT_ACTIONS_URL is set to github,
  # and github_mirror is not empty. In this case,
  # it replaces https://github.com with the value here, which is useful for some special network environments.
-  github_mirror: ''
+  github_mirror: ""
  # The labels of a runner are used to determine which jobs the runner can run, and how to run them.
  # Like: "macos-arm64:host" or "ubuntu-latest:docker://docker.gitea.com/runner-images:ubuntu-latest"
  # Find more images provided by Gitea at https://gitea.com/docker.gitea.com/runner-images .
--- a/src/gitea/.env.example
+++ b/src/gitea/.env.example
@@ -1,5 +1,5 @@
 # Gitea Version
-GITEA_VERSION=1.25.2-rootless
+GITEA_VERSION=1.25.4-rootless

 # Database configuration
 GITEA_DB_TYPE=postgres
--- a/src/gitea/docker-compose.yaml
+++ b/src/gitea/docker-compose.yaml
@@ -9,7 +9,7 @@ x-defaults: &defaults
 services:
  gitea:
    <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}gitea/gitea:${GITEA_VERSION:-1.25.2-rootless}
+    image: ${GLOBAL_REGISTRY:-}gitea/gitea:${GITEA_VERSION:-1.25.4-rootless}
    environment:
      - USER_UID=1000
      - USER_GID=1000
--- a/src/influxdb/.env.example
+++ b/src/influxdb/.env.example
@@ -0,0 +1,33 @@
+# InfluxDB Version
+INFLUXDB_VERSION=2.8.0
+
+# Timezone
+TZ=UTC
+
+# Initialization mode (setup or upgrade)
+INFLUXDB_INIT_MODE=setup
+
+# Admin user credentials
+INFLUXDB_ADMIN_USERNAME=admin
+INFLUXDB_ADMIN_PASSWORD=changeme123456
+
+# Organization name
+INFLUXDB_ORG=myorg
+
+# Default bucket name
+INFLUXDB_BUCKET=mybucket
+
+# Retention period (0 means infinite)
+INFLUXDB_RETENTION=0
+
+# Admin token for API access
+INFLUXDB_ADMIN_TOKEN=mytoken123456
+
+# Port to bind to on the host machine
+INFLUXDB_PORT_OVERRIDE=8086
+
+# Resource limits
+INFLUXDB_CPU_LIMIT=2.0
+INFLUXDB_MEMORY_LIMIT=2G
+INFLUXDB_CPU_RESERVATION=0.5
+INFLUXDB_MEMORY_RESERVATION=512M
--- a/src/influxdb/README.md
+++ b/src/influxdb/README.md
@@ -0,0 +1,169 @@
+# InfluxDB
+
+InfluxDB is a high-performance, open-source time series database designed for handling high write and query loads. It is ideal for storing and analyzing metrics, events, and real-time analytics data.
+
+## Features
+
+- **Time Series Optimized**: Purpose-built for time-stamped data
+- **High Performance**: Fast writes and queries for time series data
+- **SQL-like Query Language**: Flux and InfluxQL for flexible data querying
+- **Built-in UI**: Web-based interface for data exploration and visualization
+- **Retention Policies**: Automatic data expiration and downsampling
+- **Multi-tenancy**: Organizations and buckets for data isolation
+
+## Quick Start
+
+1. Copy the environment file and customize it:
+
+   ```bash
+   cp .env.example .env
+   ```
+
+2. Edit `.env` to configure your InfluxDB instance:
+   - `INFLUXDB_ADMIN_USERNAME`: Admin username (default: admin)
+   - `INFLUXDB_ADMIN_PASSWORD`: Admin password (default: changeme123456)
+   - `INFLUXDB_ORG`: Organization name (default: myorg)
+   - `INFLUXDB_BUCKET`: Default bucket name (default: mybucket)
+   - `INFLUXDB_ADMIN_TOKEN`: API access token (default: mytoken123456)
+
+3. Start InfluxDB:
+
+   ```bash
+   docker compose up -d
+   ```
+
+4. Access the InfluxDB UI at `http://localhost:8086`
+
+## Configuration
+
+### Environment Variables
+
+| Variable                  | Description                         | Default          |
+| ------------------------- | ----------------------------------- | ---------------- |
+| `INFLUXDB_VERSION`        | InfluxDB version                    | `2.8.0`          |
+| `TZ`                      | Timezone                            | `UTC`            |
+| `INFLUXDB_INIT_MODE`      | Initialization mode (setup/upgrade) | `setup`          |
+| `INFLUXDB_ADMIN_USERNAME` | Admin username                      | `admin`          |
+| `INFLUXDB_ADMIN_PASSWORD` | Admin password                      | `changeme123456` |
+| `INFLUXDB_ORG`            | Organization name                   | `myorg`          |
+| `INFLUXDB_BUCKET`         | Default bucket name                 | `mybucket`       |
+| `INFLUXDB_RETENTION`      | Retention period (0 for infinite)   | `0`              |
+| `INFLUXDB_ADMIN_TOKEN`    | Admin API token                     | `mytoken123456`  |
+| `INFLUXDB_PORT_OVERRIDE`  | Host port binding                   | `8086`           |
+
+### Volumes
+
+- `influxdb_data`: Stores time series data
+- `influxdb_config`: Stores configuration files
+
+## Usage
+
+### Accessing the Web UI
+
+Open your browser and navigate to:
+
+```text
+http://localhost:8086
+```
+
+Login with the credentials configured in your `.env` file.
+
+### Using the CLI
+
+Execute commands inside the container:
+
+```bash
+docker compose exec influxdb influx
+```
+
+### Writing Data
+
+Using the Flux query language:
+
+```bash
+docker compose exec influxdb influx write \
+  --bucket mybucket \
+  --org myorg \
+  'measurement,tag=value field=42'
+```
+
+### Querying Data
+
+Query data using the CLI:
+
+```bash
+docker compose exec influxdb influx query \
+  --org myorg \
+  'from(bucket: "mybucket") |> range(start: -1h)'
+```
+
+## API Access
+
+InfluxDB provides a RESTful API for programmatic access:
+
+```bash
+curl -X POST "http://localhost:8086/api/v2/query?org=myorg" \
+  -H "Authorization: Token mytoken123456" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "from(bucket: \"mybucket\") |> range(start: -1h)"}'
+```
+
+## Backup and Restore
+
+### Backup
+
+```bash
+docker compose exec influxdb influx backup /var/lib/influxdb2/backup
+docker compose cp influxdb:/var/lib/influxdb2/backup ./backup
+```
+
+### Restore
+
+```bash
+docker compose cp ./backup influxdb:/var/lib/influxdb2/backup
+docker compose exec influxdb influx restore /var/lib/influxdb2/backup
+```
+
+## Security Considerations
+
+1. **Change Default Credentials**: Always change the default admin password and token in production
+2. **Use Strong Tokens**: Generate cryptographically secure tokens for API access
+3. **Network Security**: Consider using a reverse proxy with HTTPS in production
+4. **Access Control**: Use InfluxDB's built-in authorization system to limit access
+
+## Troubleshooting
+
+### Container won't start
+
+Check the logs:
+
+```bash
+docker compose logs influxdb
+```
+
+### Cannot access web UI
+
+Ensure port 8086 is not in use:
+
+```bash
+netstat -an | grep 8086
+```
+
+### Data persistence
+
+Verify volumes are properly mounted:
+
+```bash
+docker compose exec influxdb ls -la /var/lib/influxdb2
+```
+
+## References
+
+- [Official Documentation](https://docs.influxdata.com/influxdb/v2/)
+- [Flux Query Language](https://docs.influxdata.com/flux/v0/)
+- [Docker Hub](https://hub.docker.com/_/influxdb)
+- [GitHub Repository](https://github.com/influxdata/influxdb)
+
+## License
+
+InfluxDB is available under the MIT License. See the [LICENSE](https://github.com/influxdata/influxdb/blob/master/LICENSE) file for more information.
--- a/src/influxdb/README.zh.md
+++ b/src/influxdb/README.zh.md
@@ -0,0 +1,169 @@
+# InfluxDB
+
+InfluxDB 是一个高性能的开源时序数据库，专为处理高写入和查询负载而设计。它非常适合存储和分析指标、事件以及实时分析数据。
+
+## 功能特性
+
+- **时序优化**：专为时间戳数据而构建
+- **高性能**：快速的时序数据写入和查询
+- **类 SQL 查询语言**：Flux 和 InfluxQL 提供灵活的数据查询
+- **内置 UI**：基于 Web 的数据探索和可视化界面
+- **保留策略**：自动数据过期和降采样
+- **多租户**：通过组织和桶实现数据隔离
+
+## 快速开始
+
+1. 复制环境配置文件并自定义：
+
+   ```bash
+   cp .env.example .env
+   ```
+
+2. 编辑 `.env` 文件配置您的 InfluxDB 实例：
+   - `INFLUXDB_ADMIN_USERNAME`：管理员用户名（默认：admin）
+   - `INFLUXDB_ADMIN_PASSWORD`：管理员密码（默认：changeme123456）
+   - `INFLUXDB_ORG`：组织名称（默认：myorg）
+   - `INFLUXDB_BUCKET`：默认桶名称（默认：mybucket）
+   - `INFLUXDB_ADMIN_TOKEN`：API 访问令牌（默认：mytoken123456）
+
+3. 启动 InfluxDB：
+
+   ```bash
+   docker compose up -d
+   ```
+
+4. 访问 InfluxDB UI：`http://localhost:8086`
+
+## 配置说明
+
+### 环境变量
+
+| 变量                      | 说明                        | 默认值           |
+| ------------------------- | --------------------------- | ---------------- |
+| `INFLUXDB_VERSION`        | InfluxDB 版本               | `2.8.0`          |
+| `TZ`                      | 时区                        | `UTC`            |
+| `INFLUXDB_INIT_MODE`      | 初始化模式（setup/upgrade） | `setup`          |
+| `INFLUXDB_ADMIN_USERNAME` | 管理员用户名                | `admin`          |
+| `INFLUXDB_ADMIN_PASSWORD` | 管理员密码                  | `changeme123456` |
+| `INFLUXDB_ORG`            | 组织名称                    | `myorg`          |
+| `INFLUXDB_BUCKET`         | 默认桶名称                  | `mybucket`       |
+| `INFLUXDB_RETENTION`      | 保留期限（0 表示永久）      | `0`              |
+| `INFLUXDB_ADMIN_TOKEN`    | 管理员 API 令牌             | `mytoken123456`  |
+| `INFLUXDB_PORT_OVERRIDE`  | 主机端口绑定                | `8086`           |
+
+### 数据卷
+
+- `influxdb_data`：存储时序数据
+- `influxdb_config`：存储配置文件
+
+## 使用方法
+
+### 访问 Web UI
+
+在浏览器中打开：
+
+```text
+http://localhost:8086
+```
+
+使用 `.env` 文件中配置的凭据登录。
+
+### 使用命令行
+
+在容器内执行命令：
+
+```bash
+docker compose exec influxdb influx
+```
+
+### 写入数据
+
+使用 Flux 查询语言：
+
+```bash
+docker compose exec influxdb influx write \
+  --bucket mybucket \
+  --org myorg \
+  'measurement,tag=value field=42'
+```
+
+### 查询数据
+
+使用 CLI 查询数据：
+
+```bash
+docker compose exec influxdb influx query \
+  --org myorg \
+  'from(bucket: "mybucket") |> range(start: -1h)'
+```
+
+## API 访问
+
+InfluxDB 提供 RESTful API 用于编程访问：
+
+```bash
+curl -X POST "http://localhost:8086/api/v2/query?org=myorg" \
+  -H "Authorization: Token mytoken123456" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "from(bucket: \"mybucket\") |> range(start: -1h)"}'
+```
+
+## 备份与恢复
+
+### 备份
+
+```bash
+docker compose exec influxdb influx backup /var/lib/influxdb2/backup
+docker compose cp influxdb:/var/lib/influxdb2/backup ./backup
+```
+
+### 恢复
+
+```bash
+docker compose cp ./backup influxdb:/var/lib/influxdb2/backup
+docker compose exec influxdb influx restore /var/lib/influxdb2/backup
+```
+
+## 安全注意事项
+
+1. **修改默认凭据**：在生产环境中务必修改默认的管理员密码和令牌
+2. **使用强令牌**：为 API 访问生成加密安全的令牌
+3. **网络安全**：生产环境中考虑使用带 HTTPS 的反向代理
+4. **访问控制**：使用 InfluxDB 的内置授权系统限制访问
+
+## 故障排除
+
+### 容器无法启动
+
+查看日志：
+
+```bash
+docker compose logs influxdb
+```
+
+### 无法访问 Web UI
+
+确保端口 8086 未被占用：
+
+```bash
+netstat -an | grep 8086
+```
+
+### 数据持久化
+
+验证数据卷是否正确挂载：
+
+```bash
+docker compose exec influxdb ls -la /var/lib/influxdb2
+```
+
+## 参考资源
+
+- [官方文档](https://docs.influxdata.com/influxdb/v2/)
+- [Flux 查询语言](https://docs.influxdata.com/flux/v0/)
+- [Docker Hub](https://hub.docker.com/_/influxdb)
+- [GitHub 仓库](https://github.com/influxdata/influxdb)
+
+## 许可证
+
+InfluxDB 采用 MIT 许可证发布。详情请参阅 [LICENSE](https://github.com/influxdata/influxdb/blob/master/LICENSE) 文件。
--- a/src/influxdb/docker-compose.yaml
+++ b/src/influxdb/docker-compose.yaml
@@ -0,0 +1,45 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  influxdb:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}influxdb:${INFLUXDB_VERSION:-2.8.0}
+    environment:
+      TZ: ${TZ:-UTC}
+      # InfluxDB v2 initialization
+      DOCKER_INFLUXDB_INIT_MODE: ${INFLUXDB_INIT_MODE:-setup}
+      DOCKER_INFLUXDB_INIT_USERNAME: ${INFLUXDB_ADMIN_USERNAME:-admin}
+      DOCKER_INFLUXDB_INIT_PASSWORD: ${INFLUXDB_ADMIN_PASSWORD:-changeme123456}
+      DOCKER_INFLUXDB_INIT_ORG: ${INFLUXDB_ORG:-myorg}
+      DOCKER_INFLUXDB_INIT_BUCKET: ${INFLUXDB_BUCKET:-mybucket}
+      DOCKER_INFLUXDB_INIT_RETENTION: ${INFLUXDB_RETENTION:-0}
+      DOCKER_INFLUXDB_INIT_ADMIN_TOKEN: ${INFLUXDB_ADMIN_TOKEN:-mytoken123456}
+    volumes:
+      - influxdb_data:/var/lib/influxdb2
+      - influxdb_config:/etc/influxdb2
+    ports:
+      - "${INFLUXDB_PORT_OVERRIDE:-8086}:8086"
+    deploy:
+      resources:
+        limits:
+          cpus: ${INFLUXDB_CPU_LIMIT:-2.0}
+          memory: ${INFLUXDB_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${INFLUXDB_CPU_RESERVATION:-0.5}
+          memory: ${INFLUXDB_MEMORY_RESERVATION:-512M}
+    healthcheck:
+      test: ["CMD", "influx", "ping"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+
+volumes:
+  influxdb_data:
+  influxdb_config:
--- a/src/llama.cpp/.env.example
+++ b/src/llama.cpp/.env.example
@@ -0,0 +1,106 @@
+# =============================================================================
+# llama.cpp Configuration
+# https://github.com/ggml-org/llama.cpp
+# LLM inference in C/C++ with support for various hardware accelerators
+# =============================================================================
+
+# -----------------------------------------------------------------------------
+# General Settings
+# -----------------------------------------------------------------------------
+
+# Timezone for the container (default: UTC)
+TZ=UTC
+
+# Global registry prefix (optional)
+# Example: docker.io/, ghcr.io/, registry.example.com/
+GHCR_REGISTRY=ghcr.io/
+
+# -----------------------------------------------------------------------------
+# Server Configuration
+# -----------------------------------------------------------------------------
+
+# Server image variant
+# Options: server (CPU), server-cuda (NVIDIA GPU), server-rocm (AMD GPU),
+#          server-musa (Moore Threads GPU), server-intel (Intel GPU),
+#          server-vulkan (Vulkan GPU)
+LLAMA_CPP_SERVER_VARIANT=server
+
+# Server port override (default: 8080)
+LLAMA_CPP_SERVER_PORT_OVERRIDE=8080
+
+# Model path inside the container
+# You need to mount your model file to this path
+# Example: /models/llama-2-7b-chat.Q4_K_M.gguf
+LLAMA_CPP_MODEL_PATH=/models/model.gguf
+
+# Context size (number of tokens)
+# Larger values allow for more context but require more memory
+# Default: 512, Common values: 512, 2048, 4096, 8192, 16384, 32768
+LLAMA_CPP_CONTEXT_SIZE=512
+
+# Number of GPU layers to offload
+# 0 = CPU only, 99 = all layers on GPU (for GPU variants)
+# For CPU variant, keep this at 0
+LLAMA_CPP_GPU_LAYERS=0
+
+# Number of GPUs to use (for CUDA variant)
+LLAMA_CPP_GPU_COUNT=1
+
+# Server CPU limit (in cores)
+LLAMA_CPP_SERVER_CPU_LIMIT=4.0
+
+# Server CPU reservation (in cores)
+LLAMA_CPP_SERVER_CPU_RESERVATION=2.0
+
+# Server memory limit
+LLAMA_CPP_SERVER_MEMORY_LIMIT=8G
+
+# Server memory reservation
+LLAMA_CPP_SERVER_MEMORY_RESERVATION=4G
+
+# -----------------------------------------------------------------------------
+# CLI Configuration (Light variant)
+# -----------------------------------------------------------------------------
+
+# CLI image variant
+# Options: light (CPU), light-cuda (NVIDIA GPU), light-rocm (AMD GPU),
+#          light-musa (Moore Threads GPU), light-intel (Intel GPU),
+#          light-vulkan (Vulkan GPU)
+LLAMA_CPP_CLI_VARIANT=light
+
+# Default prompt for CLI mode
+LLAMA_CPP_PROMPT=Hello, how are you?
+
+# CLI CPU limit (in cores)
+LLAMA_CPP_CLI_CPU_LIMIT=2.0
+
+# CLI CPU reservation (in cores)
+LLAMA_CPP_CLI_CPU_RESERVATION=1.0
+
+# CLI memory limit
+LLAMA_CPP_CLI_MEMORY_LIMIT=4G
+
+# CLI memory reservation
+LLAMA_CPP_CLI_MEMORY_RESERVATION=2G
+
+# -----------------------------------------------------------------------------
+# Full Toolkit Configuration
+# -----------------------------------------------------------------------------
+
+# Full image variant (includes model conversion tools)
+# Options: full (CPU), full-cuda (NVIDIA GPU), full-rocm (AMD GPU),
+#          full-musa (Moore Threads GPU), full-intel (Intel GPU),
+#          full-vulkan (Vulkan GPU)
+LLAMA_CPP_FULL_VARIANT=full
+
+# Full CPU limit (in cores)
+LLAMA_CPP_FULL_CPU_LIMIT=2.0
+
+# Full CPU reservation (in cores)
+LLAMA_CPP_FULL_CPU_RESERVATION=1.0
+
+# Full memory limit
+LLAMA_CPP_FULL_MEMORY_LIMIT=4G
+
+# Full memory reservation
+LLAMA_CPP_FULL_MEMORY_RESERVATION=2G
--- a/src/llama.cpp/README.md
+++ b/src/llama.cpp/README.md
@@ -0,0 +1,245 @@
+# llama.cpp
+
+[中文文档](README.zh.md)
+
+[llama.cpp](https://github.com/ggml-org/llama.cpp) is a high-performance C/C++ implementation for LLM inference with support for various hardware accelerators.
+
+## Features
+
+- **Fast Inference**: Optimized C/C++ implementation for efficient LLM inference
+- **Multiple Backends**: CPU, CUDA (NVIDIA), ROCm (AMD), MUSA (Moore Threads), Intel GPU, Vulkan
+- **OpenAI-compatible API**: Server mode with OpenAI-compatible REST API
+- **CLI Support**: Interactive command-line interface for quick testing
+- **Model Conversion**: Full toolkit includes tools to convert and quantize models
+- **GGUF Format**: Support for the efficient GGUF model format
+- **Cross-platform**: Linux (x86-64, ARM64, s390x), Windows, macOS
+
+## Prerequisites
+
+- Docker and Docker Compose installed
+- At least 4GB of RAM (8GB+ recommended)
+- For GPU variants:
+  - **CUDA**: NVIDIA GPU with [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia-container-toolkit)
+  - **ROCm**: AMD GPU with proper ROCm drivers
+  - **MUSA**: Moore Threads GPU with mt-container-toolkit
+- GGUF format model file (e.g., from [Hugging Face](https://huggingface.co/models?library=gguf))
+
+## Quick Start
+
+### 1. Server Mode (CPU)
+
+```bash
+# Copy and configure environment
+cp .env.example .env
+
+# Edit .env and set your model path
+# LLAMA_CPP_MODEL_PATH=/models/your-model.gguf
+
+# Place your GGUF model in a directory, then update docker-compose.yaml
+# to mount it, e.g.:
+# volumes:
+#   - ./models:/models
+
+# Start the server
+docker compose --profile server up -d
+
+# Test the server (OpenAI-compatible API)
+curl http://localhost:8080/v1/models
+
+# Chat completion request
+curl http://localhost:8080/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "messages": [
+      {"role": "user", "content": "Hello!"}
+    ]
+  }'
+```
+
+### 2. Server Mode with NVIDIA GPU
+
+```bash
+# Edit .env
+# Set LLAMA_CPP_GPU_LAYERS=99 to offload all layers to GPU
+
+# Start GPU-accelerated server
+docker compose --profile cuda up -d
+
+# The server will automatically use NVIDIA GPU
+```
+
+### 3. Server Mode with AMD GPU
+
+```bash
+# Edit .env
+# Set LLAMA_CPP_GPU_LAYERS=99 to offload all layers to GPU
+
+# Start GPU-accelerated server
+docker compose --profile rocm up -d
+
+# The server will automatically use AMD GPU
+```
+
+### 4. CLI Mode
+
+```bash
+# Edit .env and configure model path and prompt
+
+# Run CLI
+docker compose --profile cli up
+
+# For interactive mode, use:
+docker compose run --rm llama-cpp-cli \
+  -m /models/your-model.gguf \
+  -p "Your prompt here" \
+  -n 512
+```
+
+### 5. Full Toolkit (Model Conversion)
+
+```bash
+# Start the full container
+docker compose --profile full up -d
+
+# Execute commands inside the container
+docker compose exec llama-cpp-full bash
+
+# Inside container, you can use conversion tools
+# Example: Convert a Hugging Face model
+# python3 convert_hf_to_gguf.py /models/source-model --outfile /models/output.gguf
+```
+
+## Configuration
+
+### Environment Variables
+
+Key environment variables (see [.env.example](.env.example) for all options):
+
+| Variable                         | Description                                                   | Default              |
+| -------------------------------- | ------------------------------------------------------------- | -------------------- |
+| `LLAMA_CPP_SERVER_VARIANT`       | Server image variant (server, server-cuda, server-rocm, etc.) | `server`             |
+| `LLAMA_CPP_MODEL_PATH`           | Model file path inside container                              | `/models/model.gguf` |
+| `LLAMA_CPP_CONTEXT_SIZE`         | Context window size in tokens                                 | `512`                |
+| `LLAMA_CPP_GPU_LAYERS`           | Number of layers to offload to GPU (0=CPU only, 99=all)       | `0`                  |
+| `LLAMA_CPP_SERVER_PORT_OVERRIDE` | Server port on host                                           | `8080`               |
+| `LLAMA_CPP_SERVER_MEMORY_LIMIT`  | Memory limit for server                                       | `8G`                 |
+
+### Available Profiles
+
+- `server`: CPU-only server
+- `cuda`: NVIDIA GPU server (requires nvidia-container-toolkit)
+- `rocm`: AMD GPU server (requires ROCm)
+- `cli`: Command-line interface
+- `full`: Full toolkit with model conversion tools
+- `gpu`: Generic GPU profile (includes cuda and rocm)
+
+### Image Variants
+
+Each variant comes in multiple flavors:
+
+- **server**: Only `llama-server` executable (API server)
+- **light**: Only `llama-cli` and `llama-completion` executables
+- **full**: Complete toolkit including model conversion tools
+
+Backend options:
+
+- Base (CPU)
+- `-cuda` (NVIDIA GPU)
+- `-rocm` (AMD GPU)
+- `-musa` (Moore Threads GPU)
+- `-intel` (Intel GPU with SYCL)
+- `-vulkan` (Vulkan GPU)
+
+## Server API
+
+The server provides an OpenAI-compatible API:
+
+- `GET /health` - Health check
+- `GET /v1/models` - List available models
+- `POST /v1/chat/completions` - Chat completion
+- `POST /v1/completions` - Text completion
+- `POST /v1/embeddings` - Generate embeddings
+
+See the [llama.cpp server documentation](https://github.com/ggml-org/llama.cpp/blob/master/examples/server/README.md) for full API details.
+
+## Model Sources
+
+Download GGUF models from:
+
+- [Hugging Face GGUF Models](https://huggingface.co/models?library=gguf)
+- [TheBloke's GGUF Collection](https://huggingface.co/TheBloke)
+- Convert your own models using the full toolkit
+
+Popular quantization formats:
+
+- `Q4_K_M`: Good balance of quality and size (recommended)
+- `Q5_K_M`: Higher quality, larger size
+- `Q8_0`: Very high quality, large size
+- `Q2_K`: Smallest size, lower quality
+
+## Resource Requirements
+
+Minimum requirements by model size:
+
+| Model Size | RAM (CPU) | VRAM (GPU) | Context Size |
+| ---------- | --------- | ---------- | ------------ |
+| 7B Q4_K_M  | 6GB       | 4GB        | 2048         |
+| 13B Q4_K_M | 10GB      | 8GB        | 2048         |
+| 34B Q4_K_M | 24GB      | 20GB       | 2048         |
+| 70B Q4_K_M | 48GB      | 40GB       | 2048         |
+
+Larger context sizes require proportionally more memory.
+
+## Performance Tuning
+
+For CPU inference:
+
+- Increase `LLAMA_CPP_SERVER_CPU_LIMIT` for more cores
+- Optimize threads with `-t` flag (default: auto)
+
+For GPU inference:
+
+- Set `LLAMA_CPP_GPU_LAYERS=99` to offload all layers
+- Increase context size for longer conversations
+- Monitor GPU memory usage
+
+## Security Notes
+
+- The server binds to `0.0.0.0` by default - ensure proper network security
+- No authentication is enabled by default
+- Consider using a reverse proxy (nginx, Caddy) for production deployments
+- Limit resource usage to prevent system exhaustion
+
+## Troubleshooting
+
+### Out of Memory
+
+- Reduce `LLAMA_CPP_CONTEXT_SIZE`
+- Use a smaller quantized model (e.g., Q4 instead of Q8)
+- Reduce `LLAMA_CPP_GPU_LAYERS` if using GPU
+
+### GPU Not Detected
+
+**NVIDIA**: Verify nvidia-container-toolkit is installed:
+
+```bash
+docker run --rm --gpus all nvidia/cuda:12.4.0-base-ubuntu22.04 nvidia-smi
+```
+
+**AMD**: Ensure ROCm drivers and `/dev/kfd`, `/dev/dri` are accessible.
+
+### Slow Inference
+
+- Check CPU/GPU utilization
+- Increase resource limits in `.env`
+- For GPU: Verify all layers are offloaded (`LLAMA_CPP_GPU_LAYERS=99`)
+
+## Documentation
+
+- [llama.cpp GitHub](https://github.com/ggml-org/llama.cpp)
+- [Docker Documentation](https://github.com/ggml-org/llama.cpp/blob/master/docs/docker.md)
+- [Server API Docs](https://github.com/ggml-org/llama.cpp/blob/master/examples/server/README.md)
+
+## License
+
+llama.cpp is released under the MIT License. See the [LICENSE](https://github.com/ggml-org/llama.cpp/blob/master/LICENSE) file for details.
--- a/src/llama.cpp/README.zh.md
+++ b/src/llama.cpp/README.zh.md
@@ -0,0 +1,244 @@
+# llama.cpp
+
+[English Documentation](README.md)
+
+[llama.cpp](https://github.com/ggml-org/llama.cpp) 是一个高性能的 C/C++ 实现的大语言模型推理引擎，支持多种硬件加速器。
+
+## 功能特性
+
+- **高速推理**：优化的 C/C++ 实现，提供高效的 LLM 推理
+- **多种后端**：支持 CPU、CUDA（NVIDIA）、ROCm（AMD）、MUSA（摩尔线程）、Intel GPU、Vulkan
+- **OpenAI 兼容 API**：服务器模式提供 OpenAI 兼容的 REST API
+- **CLI 支持**：交互式命令行界面，方便快速测试
+- **模型转换**：完整工具包包含模型转换和量化工具
+- **GGUF 格式**：支持高效的 GGUF 模型格式
+- **跨平台**：支持 Linux（x86-64、ARM64、s390x）、Windows、macOS
+
+## 前置要求
+
+- 已安装 Docker 和 Docker Compose
+- 至少 4GB 内存（推荐 8GB 以上）
+- GPU 版本需要：
+  - **CUDA**：NVIDIA GPU 及 [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia-container-toolkit)
+  - **ROCm**：AMD GPU 及相应的 ROCm 驱动
+  - **MUSA**：摩尔线程 GPU 及 mt-container-toolkit
+- GGUF 格式的模型文件（例如从 [Hugging Face](https://huggingface.co/models?library=gguf) 下载）
+
+## 快速开始
+
+### 1. 服务器模式（CPU）
+
+```bash
+# 复制并配置环境变量
+cp .env.example .env
+
+# 编辑 .env 并设置模型路径
+# LLAMA_CPP_MODEL_PATH=/models/your-model.gguf
+
+# 将 GGUF 模型放在目录中，然后更新 docker-compose.yaml 挂载，例如：
+# volumes:
+#   - ./models:/models
+
+# 启动服务器
+docker compose --profile server up -d
+
+# 测试服务器（OpenAI 兼容 API）
+curl http://localhost:8080/v1/models
+
+# 聊天补全请求
+curl http://localhost:8080/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "messages": [
+      {"role": "user", "content": "你好！"}
+    ]
+  }'
+```
+
+### 2. 服务器模式（NVIDIA GPU）
+
+```bash
+# 编辑 .env
+# 设置 LLAMA_CPP_GPU_LAYERS=99 将所有层卸载到 GPU
+
+# 启动 GPU 加速服务器
+docker compose --profile cuda up -d
+
+# 服务器将自动使用 NVIDIA GPU
+```
+
+### 3. 服务器模式（AMD GPU）
+
+```bash
+# 编辑 .env
+# 设置 LLAMA_CPP_GPU_LAYERS=99 将所有层卸载到 GPU
+
+# 启动 GPU 加速服务器
+docker compose --profile rocm up -d
+
+# 服务器将自动使用 AMD GPU
+```
+
+### 4. CLI 模式
+
+```bash
+# 编辑 .env 并配置模型路径和提示词
+
+# 运行 CLI
+docker compose --profile cli up
+
+# 交互模式：
+docker compose run --rm llama-cpp-cli \
+  -m /models/your-model.gguf \
+  -p "你的提示词" \
+  -n 512
+```
+
+### 5. 完整工具包（模型转换）
+
+```bash
+# 启动完整容器
+docker compose --profile full up -d
+
+# 在容器内执行命令
+docker compose exec llama-cpp-full bash
+
+# 在容器内可以使用转换工具
+# 示例：转换 Hugging Face 模型
+# python3 convert_hf_to_gguf.py /models/source-model --outfile /models/output.gguf
+```
+
+## 配置说明
+
+### 环境变量
+
+主要环境变量（完整选项请查看 [.env.example](.env.example)）：
+
+| 变量                             | 说明                                                  | 默认值               |
+| -------------------------------- | ----------------------------------------------------- | -------------------- |
+| `LLAMA_CPP_SERVER_VARIANT`       | 服务器镜像变体（server、server-cuda、server-rocm 等） | `server`             |
+| `LLAMA_CPP_MODEL_PATH`           | 容器内模型文件路径                                    | `/models/model.gguf` |
+| `LLAMA_CPP_CONTEXT_SIZE`         | 上下文窗口大小（token 数）                            | `512`                |
+| `LLAMA_CPP_GPU_LAYERS`           | 卸载到 GPU 的层数（0=仅 CPU，99=全部）                | `0`                  |
+| `LLAMA_CPP_SERVER_PORT_OVERRIDE` | 主机端口                                              | `8080`               |
+| `LLAMA_CPP_SERVER_MEMORY_LIMIT`  | 服务器内存限制                                        | `8G`                 |
+
+### 可用配置文件
+
+- `server`：仅 CPU 服务器
+- `cuda`：NVIDIA GPU 服务器（需要 nvidia-container-toolkit）
+- `rocm`：AMD GPU 服务器（需要 ROCm）
+- `cli`：命令行界面
+- `full`：包含模型转换工具的完整工具包
+- `gpu`：通用 GPU 配置（包括 cuda 和 rocm）
+
+### 镜像变体
+
+每个变体都有多种类型：
+
+- **server**：仅包含 `llama-server` 可执行文件（API 服务器）
+- **light**：仅包含 `llama-cli` 和 `llama-completion` 可执行文件
+- **full**：完整工具包，包括模型转换工具
+
+后端选项：
+
+- 基础版（CPU）
+- `-cuda`（NVIDIA GPU）
+- `-rocm`（AMD GPU）
+- `-musa`（摩尔线程 GPU）
+- `-intel`（Intel GPU，支持 SYCL）
+- `-vulkan`（Vulkan GPU）
+
+## 服务器 API
+
+服务器提供 OpenAI 兼容的 API：
+
+- `GET /health` - 健康检查
+- `GET /v1/models` - 列出可用模型
+- `POST /v1/chat/completions` - 聊天补全
+- `POST /v1/completions` - 文本补全
+- `POST /v1/embeddings` - 生成嵌入向量
+
+完整 API 详情请参阅 [llama.cpp 服务器文档](https://github.com/ggml-org/llama.cpp/blob/master/examples/server/README.md)。
+
+## 模型来源
+
+下载 GGUF 模型：
+
+- [Hugging Face GGUF 模型](https://huggingface.co/models?library=gguf)
+- [TheBloke 的 GGUF 合集](https://huggingface.co/TheBloke)
+- 使用完整工具包转换您自己的模型
+
+常用量化格式：
+
+- `Q4_K_M`：质量和大小的良好平衡（推荐）
+- `Q5_K_M`：更高质量，更大体积
+- `Q8_0`：非常高的质量，大体积
+- `Q2_K`：最小体积，较低质量
+
+## 资源需求
+
+按模型大小的最低要求：
+
+| 模型大小   | 内存（CPU） | 显存（GPU） | 上下文大小 |
+| ---------- | ----------- | ----------- | ---------- |
+| 7B Q4_K_M  | 6GB         | 4GB         | 2048       |
+| 13B Q4_K_M | 10GB        | 8GB         | 2048       |
+| 34B Q4_K_M | 24GB        | 20GB        | 2048       |
+| 70B Q4_K_M | 48GB        | 40GB        | 2048       |
+
+更大的上下文大小需要成比例的更多内存。
+
+## 性能调优
+
+CPU 推理：
+
+- 增加 `LLAMA_CPP_SERVER_CPU_LIMIT` 以使用更多核心
+- 使用 `-t` 参数优化线程数（默认：自动）
+
+GPU 推理：
+
+- 设置 `LLAMA_CPP_GPU_LAYERS=99` 卸载所有层
+- 增加上下文大小以支持更长对话
+- 监控 GPU 内存使用
+
+## 安全注意事项
+
+- 服务器默认绑定到 `0.0.0.0` - 请确保网络安全
+- 默认未启用身份验证
+- 生产环境建议使用反向代理（nginx、Caddy）
+- 限制资源使用以防止系统资源耗尽
+
+## 故障排除
+
+### 内存不足
+
+- 减小 `LLAMA_CPP_CONTEXT_SIZE`
+- 使用更小的量化模型（例如 Q4 而不是 Q8）
+- 减少 `LLAMA_CPP_GPU_LAYERS`（如果使用 GPU）
+
+### GPU 未检测到
+
+**NVIDIA**：验证 nvidia-container-toolkit 是否已安装：
+
+```bash
+docker run --rm --gpus all nvidia/cuda:12.4.0-base-ubuntu22.04 nvidia-smi
+```
+
+**AMD**：确保 ROCm 驱动已安装且 `/dev/kfd`、`/dev/dri` 可访问。
+
+### 推理速度慢
+
+- 检查 CPU/GPU 利用率
+- 增加 `.env` 中的资源限制
+- GPU：验证所有层都已卸载（`LLAMA_CPP_GPU_LAYERS=99`）
+
+## 文档
+
+- [llama.cpp GitHub](https://github.com/ggml-org/llama.cpp)
+- [Docker 文档](https://github.com/ggml-org/llama.cpp/blob/master/docs/docker.md)
+- [服务器 API 文档](https://github.com/ggml-org/llama.cpp/blob/master/examples/server/README.md)
+
+## 许可证
+
+llama.cpp 使用 MIT 许可证发布。详情请参阅 [LICENSE](https://github.com/ggml-org/llama.cpp/blob/master/LICENSE) 文件。
--- a/src/llama.cpp/docker-compose.yaml
+++ b/src/llama.cpp/docker-compose.yaml
@@ -0,0 +1,210 @@
+# Docker Compose configuration for llama.cpp
+# https://github.com/ggml-org/llama.cpp
+# LLM inference in C/C++ with support for various hardware accelerators
+
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  # llama.cpp server - OpenAI-compatible API server
+  # Variant: server (CPU), server-cuda (NVIDIA GPU), server-rocm (AMD GPU)
+  llama-cpp-server:
+    <<: *defaults
+    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_SERVER_VARIANT:-server}
+    ports:
+      - "${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080"
+    volumes:
+      - llama_cpp_models:/models
+    command:
+      - "-m"
+      - "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
+      - "--port"
+      - "8080"
+      - "--host"
+      - "0.0.0.0"
+      - "-n"
+      - "${LLAMA_CPP_CONTEXT_SIZE:-512}"
+      - "--n-gpu-layers"
+      - "${LLAMA_CPP_GPU_LAYERS:-0}"
+    environment:
+      - TZ=${TZ:-UTC}
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "wget",
+          "--quiet",
+          "--tries=1",
+          "--spider",
+          "http://localhost:8080/health",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          cpus: ${LLAMA_CPP_SERVER_CPU_LIMIT:-4.0}
+          memory: ${LLAMA_CPP_SERVER_MEMORY_LIMIT:-8G}
+        reservations:
+          cpus: ${LLAMA_CPP_SERVER_CPU_RESERVATION:-2.0}
+          memory: ${LLAMA_CPP_SERVER_MEMORY_RESERVATION:-4G}
+    profiles:
+      - server
+
+  # llama.cpp server with NVIDIA GPU support
+  llama-cpp-server-cuda:
+    <<: *defaults
+    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:server-cuda
+    ports:
+      - "${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080"
+    volumes:
+      - llama_cpp_models:/models
+    command:
+      - "-m"
+      - "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
+      - "--port"
+      - "8080"
+      - "--host"
+      - "0.0.0.0"
+      - "-n"
+      - "${LLAMA_CPP_CONTEXT_SIZE:-512}"
+      - "--n-gpu-layers"
+      - "${LLAMA_CPP_GPU_LAYERS:-99}"
+    environment:
+      - TZ=${TZ:-UTC}
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "wget",
+          "--quiet",
+          "--tries=1",
+          "--spider",
+          "http://localhost:8080/health",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          cpus: ${LLAMA_CPP_SERVER_CPU_LIMIT:-4.0}
+          memory: ${LLAMA_CPP_SERVER_MEMORY_LIMIT:-8G}
+        reservations:
+          cpus: ${LLAMA_CPP_SERVER_CPU_RESERVATION:-2.0}
+          memory: ${LLAMA_CPP_SERVER_MEMORY_RESERVATION:-4G}
+          devices:
+            - driver: nvidia
+              count: ${LLAMA_CPP_GPU_COUNT:-1}
+              capabilities: [gpu]
+    profiles:
+      - gpu
+      - cuda
+
+  # llama.cpp server with AMD ROCm GPU support
+  llama-cpp-server-rocm:
+    <<: *defaults
+    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:server-rocm
+    ports:
+      - "${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080"
+    volumes:
+      - llama_cpp_models:/models
+    devices:
+      - /dev/kfd
+      - /dev/dri
+    command:
+      - "-m"
+      - "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
+      - "--port"
+      - "8080"
+      - "--host"
+      - "0.0.0.0"
+      - "-n"
+      - "${LLAMA_CPP_CONTEXT_SIZE:-512}"
+      - "--n-gpu-layers"
+      - "${LLAMA_CPP_GPU_LAYERS:-99}"
+    environment:
+      - TZ=${TZ:-UTC}
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "wget",
+          "--quiet",
+          "--tries=1",
+          "--spider",
+          "http://localhost:8080/health",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          cpus: ${LLAMA_CPP_SERVER_CPU_LIMIT:-4.0}
+          memory: ${LLAMA_CPP_SERVER_MEMORY_LIMIT:-8G}
+        reservations:
+          cpus: ${LLAMA_CPP_SERVER_CPU_RESERVATION:-2.0}
+          memory: ${LLAMA_CPP_SERVER_MEMORY_RESERVATION:-4G}
+    profiles:
+      - gpu
+      - rocm
+
+  # llama.cpp CLI (light) - Interactive command-line interface
+  llama-cpp-cli:
+    <<: *defaults
+    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_CLI_VARIANT:-light}
+    volumes:
+      - llama_cpp_models:/models
+    entrypoint: /app/llama-cli
+    command:
+      - "-m"
+      - "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
+      - "-p"
+      - "${LLAMA_CPP_PROMPT:-Hello, how are you?}"
+      - "-n"
+      - "${LLAMA_CPP_CONTEXT_SIZE:-512}"
+    environment:
+      - TZ=${TZ:-UTC}
+    deploy:
+      resources:
+        limits:
+          cpus: ${LLAMA_CPP_CLI_CPU_LIMIT:-2.0}
+          memory: ${LLAMA_CPP_CLI_MEMORY_LIMIT:-4G}
+        reservations:
+          cpus: ${LLAMA_CPP_CLI_CPU_RESERVATION:-1.0}
+          memory: ${LLAMA_CPP_CLI_MEMORY_RESERVATION:-2G}
+    profiles:
+      - cli
+
+  # llama.cpp full - Complete toolkit including model conversion tools
+  llama-cpp-full:
+    <<: *defaults
+    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_FULL_VARIANT:-full}
+    volumes:
+      - llama_cpp_models:/models
+    command: ["sleep", "infinity"]
+    environment:
+      - TZ=${TZ:-UTC}
+    deploy:
+      resources:
+        limits:
+          cpus: ${LLAMA_CPP_FULL_CPU_LIMIT:-2.0}
+          memory: ${LLAMA_CPP_FULL_MEMORY_LIMIT:-4G}
+        reservations:
+          cpus: ${LLAMA_CPP_FULL_CPU_RESERVATION:-1.0}
+          memory: ${LLAMA_CPP_FULL_MEMORY_RESERVATION:-2G}
+    profiles:
+      - full
+
+volumes:
+  llama_cpp_models:
--- a/src/lmdeploy/.env.example
+++ b/src/lmdeploy/.env.example
@@ -0,0 +1,27 @@
+# LMDeploy Version
+# Find more tags at: https://hub.docker.com/r/openmmlab/lmdeploy/tags
+LMDEPLOY_VERSION=v0.11.1-cu12.8
+
+# Host port override
+LMDEPLOY_PORT_OVERRIDE=23333
+
+# Model path or HuggingFace model ID
+# Examples: 
+# - internlm/internlm2-chat-1_8b
+# - Qwen/Qwen2.5-7B-Instruct
+LMDEPLOY_MODEL=internlm/internlm2-chat-1_8b
+
+# HuggingFace token for private models
+HF_TOKEN=
+
+# Resource limits
+LMDEPLOY_CPU_LIMIT=4.0
+LMDEPLOY_MEMORY_LIMIT=8G
+LMDEPLOY_CPU_RESERVATION=2.0
+LMDEPLOY_MEMORY_RESERVATION=4G
+
+# Shared memory size (required for some models)
+LMDEPLOY_SHM_SIZE=4g
+
+# Timezone
+TZ=UTC
--- a/src/lmdeploy/README.md
+++ b/src/lmdeploy/README.md
@@ -0,0 +1,31 @@
+# LMDeploy Docker Compose
+
+[LMDeploy](https://github.com/InternLM/lmdeploy) is a toolkit for compressing, deploying, and serving LLMs.
+
+## Quick Start
+
+1. (Optional) Configure the model and port in `.env`.
+2. Start the service:
+
+   ```bash
+   docker compose up -d
+   ```
+
+3. Access the OpenAI compatible API at `http://localhost:23333/v1`.
+
+## Configuration
+
+| Environment Variable     | Default                        | Description                          |
+| ------------------------ | ------------------------------ | ------------------------------------ |
+| `LMDEPLOY_VERSION`       | `v0.11.1-cu12.8`               | LMDeploy image version               |
+| `LMDEPLOY_PORT_OVERRIDE` | `23333`                        | Host port for the API server         |
+| `LMDEPLOY_MODEL`         | `internlm/internlm2-chat-1_8b` | HuggingFace model ID or local path   |
+| `HF_TOKEN`               |                                | HuggingFace token for private models |
+
+## Monitoring Health
+
+The service includes a health check that verifies if the OpenAI `/v1/models` endpoint is responsive.
+
+## GPU Support
+
+By default, this configuration reserves 1 NVIDIA GPU. Ensure you have the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) installed on your host.
--- a/src/lmdeploy/README.zh.md
+++ b/src/lmdeploy/README.zh.md
@@ -0,0 +1,31 @@
+# LMDeploy Docker Compose
+
+[LMDeploy](https://github.com/InternLM/lmdeploy) 是一个用于压缩、部署和服务大语言模型（LLM）的工具包。
+
+## 快速开始
+
+1. （可选）在 `.env` 中配置模型和端口。
+2. 启动服务：
+
+   ```bash
+   docker compose up -d
+   ```
+
+3. 通过 `http://localhost:23333/v1` 访问与 OpenAI 兼容的 API。
+
+## 配置项
+
+| 环境变量                 | 默认值                         | 说明                                 |
+| ------------------------ | ------------------------------ | ------------------------------------ |
+| `LMDEPLOY_VERSION`       | `v0.11.1-cu12.8`               | LMDeploy 镜像版本                    |
+| `LMDEPLOY_PORT_OVERRIDE` | `23333`                        | API 服务器的主机端口                 |
+| `LMDEPLOY_MODEL`         | `internlm/internlm2-chat-1_8b` | HuggingFace 模型 ID 或本地路径       |
+| `HF_TOKEN`               |                                | 用于访问私有模型的 HuggingFace Token |
+
+## 健康检查
+
+该配置包含健康检查，用于验证 OpenAI `/v1/models` 接口是否响应。
+
+## GPU 支持
+
+默认情况下，此配置会预留 1 个 NVIDIA GPU。请确保您的主机已安装 [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html)。
--- a/src/lmdeploy/docker-compose.yaml
+++ b/src/lmdeploy/docker-compose.yaml
@@ -0,0 +1,50 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  lmdeploy:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}openmmlab/lmdeploy:${LMDEPLOY_VERSION:-v0.11.1-cu12.8}
+    ports:
+      - "${LMDEPLOY_PORT_OVERRIDE:-23333}:23333"
+    volumes:
+      - lmdeploy_data:/root/.cache
+    environment:
+      - TZ=${TZ:-UTC}
+      - HF_TOKEN=${HF_TOKEN:-}
+    command:
+      - lmdeploy
+      - serve
+      - api_server
+      - ${LMDEPLOY_MODEL:-internlm/internlm2-chat-1_8b}
+      - --server-name
+      - "0.0.0.0"
+      - --server-port
+      - "23333"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:23333/v1/models"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    deploy:
+      resources:
+        limits:
+          cpus: ${LMDEPLOY_CPU_LIMIT:-4.0}
+          memory: ${LMDEPLOY_MEMORY_LIMIT:-8G}
+        reservations:
+          cpus: ${LMDEPLOY_CPU_RESERVATION:-2.0}
+          memory: ${LMDEPLOY_MEMORY_RESERVATION:-4G}
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    shm_size: ${LMDEPLOY_SHM_SIZE:-4g}
+
+volumes:
+  lmdeploy_data:
--- a/src/opencode/.env.example
+++ b/src/opencode/.env.example
@@ -0,0 +1,31 @@
+# OpenCode Version
+OPENCODE_VERSION=1.1.27
+
+# Host Port Override
+OPENCODE_PORT_OVERRIDE=4096
+
+# Project Directory to mount (absolute or relative path)
+# This is where OpenCode will perform coding tasks
+OPENCODE_PROJECT_DIR=./project
+
+# Timezone
+TZ=UTC
+
+# LLM Provider API Keys
+# You need at least one of these to use OpenCode
+ANTHROPIC_API_KEY=
+OPENAI_API_KEY=
+GEMINI_API_KEY=
+DEEPSEEK_API_KEY=
+GROQ_API_KEY=
+TOGETHER_API_KEY=
+MISTRAL_API_KEY=
+
+# Optional: Inline JSON config content
+# OPENCODE_CONFIG_CONTENT={"theme": "opencode", "autoupdate": false}
+
+# Resource Limits
+OPENCODE_CPU_LIMIT=1.0
+OPENCODE_MEMORY_LIMIT=2G
+OPENCODE_CPU_RESERVATION=0.25
+OPENCODE_MEMORY_RESERVATION=512M
--- a/src/opencode/README.md
+++ b/src/opencode/README.md
@@ -0,0 +1,42 @@
+# OpenCode
+
+[English](./README.md) | [中文](./README.zh.md)
+
+[OpenCode](https://github.com/anomalyco/opencode) is the open source AI coding agent built for the terminal and web. It allows you to use various LLM providers to automate coding tasks in your local or remote projects.
+
+## Usage
+
+1. Copy `.env.example` to `.env`.
+2. Set your preferred LLM provider API key in `.env` (e.g., `ANTHROPIC_API_KEY`).
+3. Set `OPENCODE_PROJECT_DIR` to the path of the project you want the agent to work on.
+4. Run the service:
+
+    ```bash
+    docker compose up -d
+    ```
+
+5. Access the web interface at `http://localhost:4096`.
+
+## Configuration
+
+- `OPENCODE_VERSION`: The version of the OpenCode image (default: `1.1.27`).
+- `OPENCODE_PORT_OVERRIDE`: The host port to expose the web interface (default: `4096`).
+- `OPENCODE_PROJECT_DIR`: Path to the project codebase you want the agent to have access to.
+- `ANTHROPIC_API_KEY`: API key for Anthropic Claude models.
+- `OPENAI_API_KEY`: API key for OpenAI models.
+- `GEMINI_API_KEY`: API key for Google Gemini models.
+- `DEEPSEEK_API_KEY`: API key for DeepSeek models.
+
+## Volumes
+
+- `opencode_data`: Stores configuration, session data, and cache.
+- Mounts the target project directory to `/app`.
+
+## Resources
+
+Default limits:
+
+- CPU: 1.0
+- Memory: 2G
+
+You can override these in your `.env` file using `OPENCODE_CPU_LIMIT` and `OPENCODE_MEMORY_LIMIT`.
--- a/src/opencode/README.zh.md
+++ b/src/opencode/README.zh.md
@@ -0,0 +1,42 @@
+# OpenCode
+
+[English](./README.md) | [中文](./README.zh.md)
+
+[OpenCode](https://github.com/anomalyco/opencode) 是一个为终端和 Web 构建的开源 AI 编程助手。它允许你使用多种大语言模型（LLM）提供商来自动执行本地或远程项目中的编码任务。
+
+## 使用方法
+
+1. 将 `.env.example` 复制为 `.env`。
+2. 在 `.env` 中设置你偏好的 LLM 提供商 API 密钥（例如 `ANTHROPIC_API_KEY`）。
+3. 将 `OPENCODE_PROJECT_DIR` 设置为你希望助手工作的项目路径。
+4. 启动服务：
+
+    ```bash
+    docker compose up -d
+    ```
+
+5. 在浏览器中访问 `http://localhost:4096` 进入 Web 界面。
+
+## 配置项
+
+- `OPENCODE_VERSION`：OpenCode 镜像版本（默认为 `1.1.27`）。
+- `OPENCODE_PORT_OVERRIDE`：映射到宿主机的 Web 端口（默认为 `4096`）。
+- `OPENCODE_PROJECT_DIR`：助手有权访问的项目代码库路径。
+- `ANTHROPIC_API_KEY`：Anthropic Claude 模型的 API 密钥。
+- `OPENAI_API_KEY`：OpenAI 模型的 API 密钥。
+- `GEMINI_API_KEY`：Google Gemini 模型的 API 密钥。
+- `DEEPSEEK_API_KEY`：DeepSeek 模型的 API 密钥。
+
+## 数据卷
+
+- `opencode_data`：用于存储配置、会话数据和缓存。
+- 将目标项目目录挂载到容器内的 `/app` 路径。
+
+## 资源限制
+
+默认限制：
+
+- CPU：1.0
+- 内存：2G
+
+你可以通过 `.env` 文件中的 `OPENCODE_CPU_LIMIT` 和 `OPENCODE_MEMORY_LIMIT` 来覆盖这些默认值。
--- a/src/opencode/docker-compose.yaml
+++ b/src/opencode/docker-compose.yaml
@@ -0,0 +1,54 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  opencode:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}ghcr.io/anomalyco/opencode:${OPENCODE_VERSION:-1.1.27}
+    command: web --hostname 0.0.0.0 --port 4096
+    ports:
+      - "${OPENCODE_PORT_OVERRIDE:-4096}:4096"
+    volumes:
+      - opencode_data:/root/.opencode
+      - ${OPENCODE_PROJECT_DIR:-./project}:/app
+    environment:
+      - TZ=${TZ:-UTC}
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - GEMINI_API_KEY=${GEMINI_API_KEY:-}
+      - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
+      - GROQ_API_KEY=${GROQ_API_KEY:-}
+      - TOGETHER_API_KEY=${TOGETHER_API_KEY:-}
+      - MISTRAL_API_KEY=${MISTRAL_API_KEY:-}
+      - OPENCODE_CONFIG_CONTENT=${OPENCODE_CONFIG_CONTENT:-}
+    working_dir: /app
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "wget",
+          "--quiet",
+          "--tries=1",
+          "--spider",
+          "http://localhost:4096/",
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          cpus: ${OPENCODE_CPU_LIMIT:-1.0}
+          memory: ${OPENCODE_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${OPENCODE_CPU_RESERVATION:-0.25}
+          memory: ${OPENCODE_MEMORY_RESERVATION:-512M}
+
+volumes:
+  opencode_data:
--- a/src/openlist/docker-compose.yaml
+++ b/src/openlist/docker-compose.yaml
@@ -28,7 +28,15 @@ services:
          cpus: ${OPENLIST_CPU_RESERVATION:-0.25}
          memory: ${OPENLIST_MEMORY_RESERVATION:-256M}
    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:5244/"]
+      test:
+        [
+          "CMD",
+          "wget",
+          "--no-verbose",
+          "--tries=1",
+          "--spider",
+          "http://localhost:5244/",
+        ]
      interval: 30s
      timeout: 10s
      retries: 3
--- a/src/opensearch/docker-compose.yaml
+++ b/src/opensearch/docker-compose.yaml
@@ -40,7 +40,8 @@ services:
          cpus: ${OPENSEARCH_CPU_RESERVATION:-1.0}
          memory: ${OPENSEARCH_MEMORY_RESERVATION:-1G}
    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://localhost:9200/_cluster/health || exit 1"]
+      test:
+        ["CMD-SHELL", "curl -f http://localhost:9200/_cluster/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
@@ -67,7 +68,15 @@ services:
          cpus: ${OPENSEARCH_DASHBOARDS_CPU_RESERVATION:-0.5}
          memory: ${OPENSEARCH_DASHBOARDS_MEMORY_RESERVATION:-512M}
    healthcheck:
-      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:5601/api/status"]
+      test:
+        [
+          "CMD",
+          "wget",
+          "--no-verbose",
+          "--tries=1",
+          "--spider",
+          "http://localhost:5601/api/status",
+        ]
      interval: 30s
      timeout: 10s
      retries: 3
--- a/src/phoenix/.env.example
+++ b/src/phoenix/.env.example
@@ -3,7 +3,7 @@
 COMPOSE_PROFILES=sqlite

 # Phoenix version
-PHOENIX_VERSION=12.28.1-nonroot
+PHOENIX_VERSION=12.31.2-nonroot

 # Timezone
 TZ=UTC
--- a/src/phoenix/README.md
+++ b/src/phoenix/README.md
@@ -32,7 +32,7 @@ This project supports two modes of operation via Docker Compose profiles:
 | Variable Name                    | Description                              | Default Value     |
 | -------------------------------- | ---------------------------------------- | ----------------- |
 | COMPOSE_PROFILES                 | Active profiles (`sqlite` or `postgres`) | `sqlite`          |
-| PHOENIX_VERSION                  | Phoenix image version                    | `12.28.1-nonroot` |
+| PHOENIX_VERSION                  | Phoenix image version                    | `12.31.2-nonroot` |
 | PHOENIX_PORT_OVERRIDE            | Host port for Phoenix UI and HTTP API    | `6006`            |
 | PHOENIX_GRPC_PORT_OVERRIDE       | Host port for OTLP gRPC collector        | `4317`            |
 | PHOENIX_PROMETHEUS_PORT_OVERRIDE | Host port for Prometheus metrics         | `9090`            |
--- a/src/phoenix/README.zh.md
+++ b/src/phoenix/README.zh.md
@@ -32,7 +32,7 @@ Arize Phoenix 是一个开源的 AI 可观测性平台，专为 LLM 应用设计
 | 变量名                           | 描述                                     | 默认值            |
 | -------------------------------- | ---------------------------------------- | ----------------- |
 | COMPOSE_PROFILES                 | 激活的配置文件（`sqlite` 或 `postgres`） | `sqlite`          |
-| PHOENIX_VERSION                  | Phoenix 镜像版本                         | `12.28.1-nonroot` |
+| PHOENIX_VERSION                  | Phoenix 镜像版本                         | `12.31.2-nonroot` |
 | PHOENIX_PORT_OVERRIDE            | Phoenix UI 和 HTTP API 的主机端口        | `6006`            |
 | PHOENIX_GRPC_PORT_OVERRIDE       | OTLP gRPC 采集器的主机端口               | `4317`            |
 | PHOENIX_PROMETHEUS_PORT_OVERRIDE | Prometheus 指标的主机端口                | `9090`            |
--- a/src/phoenix/docker-compose.yaml
+++ b/src/phoenix/docker-compose.yaml
@@ -11,7 +11,7 @@ x-defaults: &defaults

 x-phoenix-common: &phoenix-common
  <<: *defaults
-  image: ${GLOBAL_REGISTRY:-}arizephoenix/phoenix:${PHOENIX_VERSION:-12.28.1-nonroot}
+  image: ${GLOBAL_REGISTRY:-}arizephoenix/phoenix:${PHOENIX_VERSION:-12.31.2-nonroot}
  ports:
    - "${PHOENIX_PORT_OVERRIDE:-6006}:6006" # UI and OTLP HTTP collector
    - "${PHOENIX_GRPC_PORT_OVERRIDE:-4317}:4317" # OTLP gRPC collector
--- a/src/pogocache/.env.example
+++ b/src/pogocache/.env.example
@@ -0,0 +1,15 @@
+# Pogocache Version
+POGOCACHE_VERSION=1.3.1
+
+# Host port override
+POGOCACHE_PORT_OVERRIDE=9401
+
+# Resource limits
+POGOCACHE_CPU_LIMIT=0.50
+POGOCACHE_MEMORY_LIMIT=512M
+POGOCACHE_CPU_RESERVATION=0.10
+POGOCACHE_MEMORY_RESERVATION=128M
+
+# Extra arguments for pogocache
+# Example: --auth mypassword --threads 4
+POGOCACHE_EXTRA_ARGS=
--- a/src/pogocache/README.md
+++ b/src/pogocache/README.md
@@ -0,0 +1,35 @@
+# Pogocache
+
+[Pogocache](https://github.com/tidwall/pogocache) is fast caching software built from scratch with a focus on low latency and cpu efficiency. It is a high-performance, multi-protocol Redis alternative.
+
+## Features
+
+- **Fast**: Faster than Memcached, Valkey, Redis, Dragonfly, and Garnet.
+- **Multi-protocol**: Supports Redis RESP, Memcached, PostgreSQL wire protocol, and HTTP.
+- **Persistence**: Supports AOF-style persistence.
+- **Resource Efficient**: Low CPU and memory overhead.
+
+## Deployment
+
+```bash
+docker compose up -d
+```
+
+## Configuration
+
+| Variable                  | Default | Description                                   |
+| ------------------------- | ------- | --------------------------------------------- |
+| `POGOCACHE_VERSION`       | `1.3.1` | Pogocache image version                       |
+| `POGOCACHE_PORT_OVERRIDE` | `9401`  | Host port for Pogocache                       |
+| `POGOCACHE_EXTRA_ARGS`    |         | Additional CLI arguments (e.g. `--auth pass`) |
+
+## Accessing Pogocache
+
+- **Redis**: `redis-cli -p 9401`
+- **Postgres**: `psql -h localhost -p 9401`
+- **HTTP**: `curl http://localhost:9401/key`
+- **Memcached**: `telnet localhost 9401`
+
+## Persistence
+
+By default, the data is persisted to a named volume `pogocache_data` at `/data/pogocache.db`.
--- a/src/pogocache/README.zh.md
+++ b/src/pogocache/README.zh.md
@@ -0,0 +1,35 @@
+# Pogocache
+
+[Pogocache](https://github.com/tidwall/pogocache) 是一款从零开始构建的高速缓存软件，专注于低延迟和 CPU 效率。它是一个高性能、多协议的 Redis 替代方案。
+
+## 特性
+
+- **极速**：比 Memcached、Valkey、Redis、Dragonfly 和 Garnet 更快。
+- **多协议支持**：支持 Redis RESP、Memcached、PostgreSQL 线缆协议和 HTTP。
+- **持久化**：支持 AOF 风格的持久化。
+- **资源高效**：极低的 CPU 和内存开销。
+
+## 部署
+
+```bash
+docker compose up -d
+```
+
+## 配置说明
+
+| 变量名                    | 默认值  | 描述                                   |
+| ------------------------- | ------- | -------------------------------------- |
+| `POGOCACHE_VERSION`       | `1.3.1` | Pogocache 镜像版本                     |
+| `POGOCACHE_PORT_OVERRIDE` | `9401`  | 主机端口                               |
+| `POGOCACHE_EXTRA_ARGS`    |         | 额外的命令行参数（例如 `--auth pass`） |
+
+## 访问方式
+
+- **Redis**：`redis-cli -p 9401`
+- **Postgres**：`psql -h localhost -p 9401`
+- **HTTP**：`curl http://localhost:9401/key`
+- **Memcached**：`telnet localhost 9401`
+
+## 持久化
+
+默认情况下，数据持久化到命名卷 `pogocache_data` 中的 `/data/pogocache.db`。
--- a/src/pogocache/docker-compose.yaml
+++ b/src/pogocache/docker-compose.yaml
@@ -0,0 +1,42 @@
+# Docker Compose for Pogocache
+# Pogocache is fast caching software built from scratch with a focus on low latency and cpu efficiency.
+# See: https://github.com/tidwall/pogocache
+
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 10m
+      max-file: "3"
+
+services:
+  pogocache:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}pogocache/pogocache:${POGOCACHE_VERSION:-1.3.1}
+    ports:
+      - "${POGOCACHE_PORT_OVERRIDE:-9401}:9401"
+    environment:
+      - TZ=${TZ:-UTC}
+    volumes:
+      - pogocache_data:/data
+    command: >
+      ${POGOCACHE_EXTRA_ARGS:-}
+      --persist /data/pogocache.db
+    healthcheck:
+      test: ["CMD-SHELL", "nc -z localhost 9401 || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 5s
+    deploy:
+      resources:
+        limits:
+          cpus: ${POGOCACHE_CPU_LIMIT:-0.50}
+          memory: ${POGOCACHE_MEMORY_LIMIT:-512M}
+        reservations:
+          cpus: ${POGOCACHE_CPU_RESERVATION:-0.10}
+          memory: ${POGOCACHE_MEMORY_RESERVATION:-128M}
+
+volumes:
+  pogocache_data:
--- a/src/renovate/.env.example
+++ b/src/renovate/.env.example
@@ -1,7 +1,7 @@
 # Renovate Configuration

 # Image version
-RENOVATE_VERSION=42.52.5-full
+RENOVATE_VERSION=42.85.4-full

 # Global registry prefix (optional, e.g., your.registry.com/)
 GLOBAL_REGISTRY=
--- a/src/renovate/README.md
+++ b/src/renovate/README.md
@@ -53,7 +53,7 @@ Key environment variables in `.env`:

 | Variable                | Description             | Default        |
 | ----------------------- | ----------------------- | -------------- |
-| `RENOVATE_VERSION`      | Renovate image version  | `42.52.5-full` |
+| `RENOVATE_VERSION`      | Renovate image version  | `42.85.4-full` |
 | `RENOVATE_PLATFORM`     | Platform type           | `github`       |
 | `RENOVATE_TOKEN`        | Authentication token    | **(required)** |
 | `RENOVATE_REPOSITORIES` | Repositories to process | `''`           |
--- a/src/renovate/README.zh.md
+++ b/src/renovate/README.zh.md
@@ -53,7 +53,7 @@ Renovate 是一个自动化依赖更新工具，当有新版本可用时，它

 | 变量                    | 描述              | 默认值         |
 | ----------------------- | ----------------- | -------------- |
-| `RENOVATE_VERSION`      | Renovate 镜像版本 | `42.52.5-full` |
+| `RENOVATE_VERSION`      | Renovate 镜像版本 | `42.85.4-full` |
 | `RENOVATE_PLATFORM`     | 平台类型          | `github`       |
 | `RENOVATE_TOKEN`        | 身份验证令牌      | **（必需）**   |
 | `RENOVATE_REPOSITORIES` | 要处理的仓库      | `''`           |
--- a/src/renovate/docker-compose.yaml
+++ b/src/renovate/docker-compose.yaml
@@ -12,7 +12,7 @@ x-defaults: &defaults
 services:
  renovate:
    <<: *defaults
-    image: ${GLOBAL_REGISTRY:-}renovate/renovate:${RENOVATE_VERSION:-42.52.5-full}
+    image: ${GLOBAL_REGISTRY:-}renovate/renovate:${RENOVATE_VERSION:-42.85.4-full}

    # Renovate runs as a scheduled job, not a continuous service
    # Use 'docker compose run --rm renovate' to execute manually
--- a/src/selenium/.env.example
+++ b/src/selenium/.env.example
@@ -0,0 +1,48 @@
+# Selenium Standalone Configuration
+
+# Image Registry (optional)
+# GLOBAL_REGISTRY=
+
+# Selenium Version (stable version tag recommended)
+# Visit https://hub.docker.com/r/selenium/standalone-chrome/tags for available versions
+# Format: <browser-version>-<date> or <browser-version>-chromedriver-<driver-version>-grid-<grid-version>-<date>
+SELENIUM_VERSION=144.0-20260120
+
+# Shared Memory Size (required for browser stability)
+# Chrome and Firefox need sufficient shared memory to prevent crashes
+SELENIUM_SHM_SIZE=2g
+
+# Port Configuration
+# Selenium Grid HTTP port
+SELENIUM_GRID_PORT_OVERRIDE=4444
+# VNC port for viewing browser sessions (browser debugger)
+SELENIUM_VNC_PORT_OVERRIDE=7900
+
+# Timezone
+TZ=UTC
+
+# Screen Resolution Settings
+SE_SCREEN_WIDTH=1920
+SE_SCREEN_HEIGHT=1080
+SE_SCREEN_DEPTH=24
+SE_SCREEN_DPI=96
+
+# VNC Configuration
+# Password for VNC access (default: secret)
+SE_VNC_PASSWORD=secret
+
+# Session Configuration
+# Maximum concurrent sessions per container
+SE_NODE_MAX_SESSIONS=1
+# Session timeout in seconds (default: 300)
+SE_NODE_SESSION_TIMEOUT=300
+
+# Xvfb Configuration
+# Start virtual display server (required for headless mode in Chrome/Chromium v127+)
+SE_START_XVFB=true
+
+# Resource Limits
+SELENIUM_CPU_LIMIT=2.0
+SELENIUM_MEMORY_LIMIT=2G
+SELENIUM_CPU_RESERVATION=1.0
+SELENIUM_MEMORY_RESERVATION=1G
--- a/src/selenium/README.md
+++ b/src/selenium/README.md
@@ -0,0 +1,281 @@
+# Selenium Standalone with Chrome
+
+[![Docker Image](https://img.shields.io/docker/v/selenium/standalone-chrome?sort=semver)](https://hub.docker.com/r/selenium/standalone-chrome)
+[![Docker Pulls](https://img.shields.io/docker/pulls/selenium/standalone-chrome)](https://hub.docker.com/r/selenium/standalone-chrome)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/SeleniumHQ/docker-selenium/blob/trunk/LICENSE.md)
+
+Selenium Grid in Standalone mode with Chrome browser for browser automation at scale.
+
+## Quick Start
+
+```bash
+# Start the service
+docker compose up -d
+
+# Verify the service is running
+docker compose ps
+
+# View logs
+docker compose logs -f
+
+# Stop the service
+docker compose down
+```
+
+## Service Information
+
+### Ports
+
+| Port | Service       | Description                                  |
+| ---- | ------------- | -------------------------------------------- |
+| 4444 | Selenium Grid | HTTP endpoint for WebDriver                  |
+| 7900 | noVNC         | Browser viewing interface (password: secret) |
+
+### Default Credentials
+
+- VNC Password: `secret` (configurable via `SE_VNC_PASSWORD`)
+
+### Volumes
+
+- `selenium_downloads`: Browser downloads directory (`/home/seluser/Downloads`)
+
+## Configuration
+
+### Environment Variables
+
+All configuration can be customized via the `.env` file:
+
+```bash
+# Copy the example configuration
+cp .env.example .env
+
+# Edit the configuration
+nano .env
+```
+
+Key configurations:
+
+| Variable                      | Default          | Description                                         |
+| ----------------------------- | ---------------- | --------------------------------------------------- |
+| `SELENIUM_VERSION`            | `144.0-20260120` | Docker image tag (Chrome version + date)            |
+| `SELENIUM_SHM_SIZE`           | `2g`             | Shared memory size (required for browser stability) |
+| `SELENIUM_GRID_PORT_OVERRIDE` | `4444`           | Grid HTTP endpoint port                             |
+| `SELENIUM_VNC_PORT_OVERRIDE`  | `7900`           | noVNC viewer port                                   |
+| `SE_SCREEN_WIDTH`             | `1920`           | Browser screen width                                |
+| `SE_SCREEN_HEIGHT`            | `1080`           | Browser screen height                               |
+| `SE_NODE_MAX_SESSIONS`        | `1`              | Max concurrent sessions per container               |
+| `SE_NODE_SESSION_TIMEOUT`     | `300`            | Session timeout in seconds                          |
+
+For a complete list of environment variables, see the [Selenium Docker documentation](https://github.com/SeleniumHQ/docker-selenium/blob/trunk/ENV_VARIABLES.md).
+
+## Usage
+
+### Basic WebDriver Test (Python)
+
+```python
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+
+# Configure Chrome options
+options = Options()
+
+# Connect to Selenium Grid
+driver = webdriver.Remote(
+    command_executor='http://localhost:4444',
+    options=options
+)
+
+# Run your test
+driver.get('https://www.selenium.dev/')
+print(driver.title)
+
+# Clean up
+driver.quit()
+```
+
+### Basic WebDriver Test (Node.js)
+
+```javascript
+const { Builder } = require('selenium-webdriver');
+const chrome = require('selenium-webdriver/chrome');
+
+(async function example() {
+    let driver = await new Builder()
+        .forBrowser('chrome')
+        .usingServer('http://localhost:4444')
+        .build();
+    
+    try {
+        await driver.get('https://www.selenium.dev/');
+        console.log(await driver.getTitle());
+    } finally {
+        await driver.quit();
+    }
+})();
+```
+
+### Viewing Browser Sessions
+
+You can watch tests execute in real-time using noVNC:
+
+1. Open your browser to `http://localhost:7900/?autoconnect=1&resize=scale&password=secret`
+2. The default VNC password is `secret`
+3. You'll see the browser session in real-time
+
+Alternatively, use a VNC client to connect to `localhost:5900` (if exposed).
+
+## Advanced Configuration
+
+### Changing Browser Version
+
+To use a specific Chrome version, update the `SELENIUM_VERSION` in your `.env` file:
+
+```bash
+# Use Chrome 143.0
+SELENIUM_VERSION=143.0-20260120
+
+# Or use a specific Selenium Grid version
+SELENIUM_VERSION=144.0-chromedriver-144.0-grid-4.40.0-20260120
+```
+
+Visit [Docker Hub](https://hub.docker.com/r/selenium/standalone-chrome/tags) for available versions.
+
+### Increasing Concurrent Sessions
+
+To run multiple concurrent sessions in one container (not recommended for production):
+
+```bash
+SE_NODE_MAX_SESSIONS=5
+```
+
+**Note:** For better stability, scale containers instead:
+
+```bash
+docker compose up -d --scale selenium-chrome=3
+```
+
+### Retrieving Downloaded Files
+
+To access files downloaded during tests, mount the downloads directory:
+
+```yaml
+volumes:
+  - ./downloads:/home/seluser/Downloads
+```
+
+**Linux users:** Set proper permissions before mounting:
+
+```bash
+mkdir -p ./downloads
+sudo chown 1200:1201 ./downloads
+```
+
+### Running in Headless Mode
+
+For newer Chrome versions (127+), headless mode requires Xvfb:
+
+```bash
+SE_START_XVFB=true
+```
+
+Then configure headless in your test:
+
+```python
+options = Options()
+options.add_argument('--headless=new')
+```
+
+### Custom Screen Resolution
+
+Adjust screen resolution for your test needs:
+
+```bash
+SE_SCREEN_WIDTH=1366
+SE_SCREEN_HEIGHT=768
+SE_SCREEN_DEPTH=24
+SE_SCREEN_DPI=74
+```
+
+## Health Check
+
+The container includes a built-in health check that polls the Grid status endpoint every 30 seconds:
+
+```bash
+# Check container health
+docker compose ps
+
+# Or inspect the health status
+docker inspect --format='{{json .State.Health.Status}}' <container-id>
+```
+
+## Troubleshooting
+
+### Browser Crashes
+
+If you see errors like "Chrome failed to start" or "invalid argument: can't kill an exited process":
+
+1. **Ensure sufficient shared memory:** The default `2g` should work for most cases
+
+   ```bash
+   SELENIUM_SHM_SIZE=2g
+   ```
+
+2. **Check headless mode configuration:** Make sure `SE_START_XVFB=true` if using headless mode with Chrome 127+
+
+### Permission Issues (Linux)
+
+When mounting volumes on Linux, ensure correct permissions:
+
+```bash
+# For downloads directory
+mkdir -p ./downloads
+sudo chown 1200:1201 ./downloads
+
+# Check user/group IDs in container
+docker compose exec selenium-chrome id
+```
+
+### Resource Constraints
+
+If tests are slow or containers are being OOM killed:
+
+```bash
+# Increase resource limits
+SELENIUM_CPU_LIMIT=4.0
+SELENIUM_MEMORY_LIMIT=4G
+```
+
+### VNC Connection Issues
+
+If you can't connect to VNC:
+
+1. Check that port 7900 is not in use
+2. Verify the VNC password is correct (default: `secret`)
+3. Try disabling VNC authentication: `SE_VNC_NO_PASSWORD=true`
+
+## Multi-Browser Support
+
+For running multiple browser types (Chrome, Firefox, Edge), consider using:
+
+- **Hub & Nodes architecture:** See `docker-compose-grid.yaml` example
+- **Dynamic Grid:** Automatically spawns containers on demand
+- **Selenium Grid 4:** Full distributed mode with Router, Distributor, etc.
+
+## Additional Resources
+
+- [Selenium Documentation](https://www.selenium.dev/documentation/)
+- [Docker Selenium GitHub](https://github.com/SeleniumHQ/docker-selenium)
+- [Selenium Grid Configuration](https://www.selenium.dev/documentation/grid/)
+- [Environment Variables Reference](https://github.com/SeleniumHQ/docker-selenium/blob/trunk/ENV_VARIABLES.md)
+
+## Security Notes
+
+- **VNC Password:** Change the default `secret` password in production
+- **Network Exposure:** Do not expose Selenium Grid directly to the internet
+- **Resource Limits:** Always set CPU and memory limits to prevent resource exhaustion
+- **User Permissions:** Selenium runs as non-root user `seluser` (UID 1200, GID 1201)
+
+## License
+
+This configuration is provided under the Apache License 2.0, following the Selenium project's licensing.
+The Selenium Docker images are maintained by the SeleniumHQ team and community contributors.
--- a/src/selenium/README.zh.md
+++ b/src/selenium/README.zh.md
@@ -0,0 +1,281 @@
+# Selenium Standalone Chrome
+
+[![Docker Image](https://img.shields.io/docker/v/selenium/standalone-chrome?sort=semver)](https://hub.docker.com/r/selenium/standalone-chrome)
+[![Docker Pulls](https://img.shields.io/docker/pulls/selenium/standalone-chrome)](https://hub.docker.com/r/selenium/standalone-chrome)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/SeleniumHQ/docker-selenium/blob/trunk/LICENSE.md)
+
+Selenium Grid 独立模式，配备 Chrome 浏览器，用于大规模浏览器自动化。
+
+## 快速开始
+
+```bash
+# 启动服务
+docker compose up -d
+
+# 验证服务运行状态
+docker compose ps
+
+# 查看日志
+docker compose logs -f
+
+# 停止服务
+docker compose down
+```
+
+## 服务信息
+
+### 端口
+
+| 端口 | 服务          | 说明                           |
+| ---- | ------------- | ------------------------------ |
+| 4444 | Selenium Grid | WebDriver HTTP 端点            |
+| 7900 | noVNC         | 浏览器查看界面（密码：secret） |
+
+### 默认凭据
+
+- VNC 密码：`secret`（可通过 `SE_VNC_PASSWORD` 配置）
+
+### 数据卷
+
+- `selenium_downloads`：浏览器下载目录（`/home/seluser/Downloads`）
+
+## 配置说明
+
+### 环境变量
+
+所有配置都可以通过 `.env` 文件自定义：
+
+```bash
+# 复制示例配置文件
+cp .env.example .env
+
+# 编辑配置
+nano .env
+```
+
+主要配置：
+
+| 变量                          | 默认值           | 说明                                  |
+| ----------------------------- | ---------------- | ------------------------------------- |
+| `SELENIUM_VERSION`            | `144.0-20260120` | Docker 镜像标签（Chrome 版本 + 日期） |
+| `SELENIUM_SHM_SIZE`           | `2g`             | 共享内存大小（浏览器稳定性所需）      |
+| `SELENIUM_GRID_PORT_OVERRIDE` | `4444`           | Grid HTTP 端点端口                    |
+| `SELENIUM_VNC_PORT_OVERRIDE`  | `7900`           | noVNC 查看器端口                      |
+| `SE_SCREEN_WIDTH`             | `1920`           | 浏览器屏幕宽度                        |
+| `SE_SCREEN_HEIGHT`            | `1080`           | 浏览器屏幕高度                        |
+| `SE_NODE_MAX_SESSIONS`        | `1`              | 每个容器最大并发会话数                |
+| `SE_NODE_SESSION_TIMEOUT`     | `300`            | 会话超时时间（秒）                    |
+
+完整的环境变量列表请参考 [Selenium Docker 文档](https://github.com/SeleniumHQ/docker-selenium/blob/trunk/ENV_VARIABLES.md)。
+
+## 使用方法
+
+### 基础 WebDriver 测试（Python）
+
+```python
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+
+# 配置 Chrome 选项
+options = Options()
+
+# 连接到 Selenium Grid
+driver = webdriver.Remote(
+    command_executor='http://localhost:4444',
+    options=options
+)
+
+# 运行测试
+driver.get('https://www.selenium.dev/')
+print(driver.title)
+
+# 清理资源
+driver.quit()
+```
+
+### 基础 WebDriver 测试（Node.js）
+
+```javascript
+const { Builder } = require('selenium-webdriver');
+const chrome = require('selenium-webdriver/chrome');
+
+(async function example() {
+    let driver = await new Builder()
+        .forBrowser('chrome')
+        .usingServer('http://localhost:4444')
+        .build();
+    
+    try {
+        await driver.get('https://www.selenium.dev/');
+        console.log(await driver.getTitle());
+    } finally {
+        await driver.quit();
+    }
+})();
+```
+
+### 查看浏览器会话
+
+您可以使用 noVNC 实时查看测试执行过程：
+
+1. 在浏览器中打开 `http://localhost:7900/?autoconnect=1&resize=scale&password=secret`
+2. 默认 VNC 密码是 `secret`
+3. 您将实时看到浏览器会话
+
+或者，使用 VNC 客户端连接到 `localhost:5900`（如果已暴露）。
+
+## 高级配置
+
+### 更改浏览器版本
+
+要使用特定的 Chrome 版本，请在 `.env` 文件中更新 `SELENIUM_VERSION`：
+
+```bash
+# 使用 Chrome 143.0
+SELENIUM_VERSION=143.0-20260120
+
+# 或使用特定的 Selenium Grid 版本
+SELENIUM_VERSION=144.0-chromedriver-144.0-grid-4.40.0-20260120
+```
+
+访问 [Docker Hub](https://hub.docker.com/r/selenium/standalone-chrome/tags) 查看可用版本。
+
+### 增加并发会话数
+
+在单个容器中运行多个并发会话（生产环境不推荐）：
+
+```bash
+SE_NODE_MAX_SESSIONS=5
+```
+
+**注意：** 为了更好的稳定性，建议通过扩展容器来实现：
+
+```bash
+docker compose up -d --scale selenium-chrome=3
+```
+
+### 获取下载的文件
+
+要访问测试期间下载的文件，挂载下载目录：
+
+```yaml
+volumes:
+  - ./downloads:/home/seluser/Downloads
+```
+
+**Linux 用户：** 挂载前设置正确的权限：
+
+```bash
+mkdir -p ./downloads
+sudo chown 1200:1201 ./downloads
+```
+
+### 无头模式运行
+
+对于新版 Chrome（127+），无头模式需要 Xvfb：
+
+```bash
+SE_START_XVFB=true
+```
+
+然后在测试中配置无头模式：
+
+```python
+options = Options()
+options.add_argument('--headless=new')
+```
+
+### 自定义屏幕分辨率
+
+根据测试需求调整屏幕分辨率：
+
+```bash
+SE_SCREEN_WIDTH=1366
+SE_SCREEN_HEIGHT=768
+SE_SCREEN_DEPTH=24
+SE_SCREEN_DPI=74
+```
+
+## 健康检查
+
+容器包含内置的健康检查，每 30 秒轮询 Grid 状态端点：
+
+```bash
+# 检查容器健康状态
+docker compose ps
+
+# 或检查健康状态详情
+docker inspect --format='{{json .State.Health.Status}}' <container-id>
+```
+
+## 故障排除
+
+### 浏览器崩溃
+
+如果看到 "Chrome failed to start" 或 "invalid argument: can't kill an exited process" 等错误：
+
+1. **确保足够的共享内存：** 默认的 `2g` 应该适用于大多数情况
+
+   ```bash
+   SELENIUM_SHM_SIZE=2g
+   ```
+
+2. **检查无头模式配置：** 如果在 Chrome 127+ 中使用无头模式，请确保 `SE_START_XVFB=true`
+
+### 权限问题（Linux）
+
+在 Linux 上挂载卷时，确保正确的权限：
+
+```bash
+# 对于下载目录
+mkdir -p ./downloads
+sudo chown 1200:1201 ./downloads
+
+# 检查容器中的用户/组 ID
+docker compose exec selenium-chrome id
+```
+
+### 资源限制
+
+如果测试缓慢或容器被 OOM 终止：
+
+```bash
+# 增加资源限制
+SELENIUM_CPU_LIMIT=4.0
+SELENIUM_MEMORY_LIMIT=4G
+```
+
+### VNC 连接问题
+
+如果无法连接到 VNC：
+
+1. 检查端口 7900 是否被占用
+2. 验证 VNC 密码是否正确（默认：`secret`）
+3. 尝试禁用 VNC 认证：`SE_VNC_NO_PASSWORD=true`
+
+## 多浏览器支持
+
+要运行多种浏览器类型（Chrome、Firefox、Edge），请考虑使用：
+
+- **Hub & Nodes 架构：** 参见 `docker-compose-grid.yaml` 示例
+- **动态 Grid：** 按需自动生成容器
+- **Selenium Grid 4：** 完整的分布式模式，包含 Router、Distributor 等
+
+## 其他资源
+
+- [Selenium 文档](https://www.selenium.dev/documentation/)
+- [Docker Selenium GitHub](https://github.com/SeleniumHQ/docker-selenium)
+- [Selenium Grid 配置](https://www.selenium.dev/documentation/grid/)
+- [环境变量参考](https://github.com/SeleniumHQ/docker-selenium/blob/trunk/ENV_VARIABLES.md)
+
+## 安全注意事项
+
+- **VNC 密码：** 生产环境中更改默认的 `secret` 密码
+- **网络暴露：** 不要将 Selenium Grid 直接暴露到互联网
+- **资源限制：** 始终设置 CPU 和内存限制以防止资源耗尽
+- **用户权限：** Selenium 以非 root 用户 `seluser` 运行（UID 1200，GID 1201）
+
+## 许可证
+
+本配置遵循 Apache License 2.0 提供，与 Selenium 项目的许可保持一致。
+Selenium Docker 镜像由 SeleniumHQ 团队和社区贡献者维护。
--- a/src/selenium/docker-compose.yaml
+++ b/src/selenium/docker-compose.yaml
@@ -0,0 +1,50 @@
+# Selenium Standalone with Chrome
+# This configuration runs Selenium Grid in Standalone mode with Chrome browser
+# Suitable for single-browser automation needs
+
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  selenium-chrome:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}selenium/standalone-chrome:${SELENIUM_VERSION:-144.0-20260120}
+    shm_size: ${SELENIUM_SHM_SIZE:-2g}
+    ports:
+      - "${SELENIUM_GRID_PORT_OVERRIDE:-4444}:4444"
+      - "${SELENIUM_VNC_PORT_OVERRIDE:-7900}:7900"
+    volumes:
+      - selenium_downloads:/home/seluser/Downloads
+    environment:
+      - TZ=${TZ:-UTC}
+      - SE_SCREEN_WIDTH=${SE_SCREEN_WIDTH:-1920}
+      - SE_SCREEN_HEIGHT=${SE_SCREEN_HEIGHT:-1080}
+      - SE_SCREEN_DEPTH=${SE_SCREEN_DEPTH:-24}
+      - SE_SCREEN_DPI=${SE_SCREEN_DPI:-96}
+      - SE_VNC_PASSWORD=${SE_VNC_PASSWORD:-secret}
+      - SE_NODE_MAX_SESSIONS=${SE_NODE_MAX_SESSIONS:-1}
+      - SE_NODE_SESSION_TIMEOUT=${SE_NODE_SESSION_TIMEOUT:-300}
+      - SE_START_XVFB=${SE_START_XVFB:-true}
+    healthcheck:
+      test:
+        ["CMD", "/opt/bin/check-grid.sh", "--host", "0.0.0.0", "--port", "4444"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    deploy:
+      resources:
+        limits:
+          cpus: ${SELENIUM_CPU_LIMIT:-2.0}
+          memory: ${SELENIUM_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${SELENIUM_CPU_RESERVATION:-1.0}
+          memory: ${SELENIUM_MEMORY_RESERVATION:-1G}
+
+volumes:
+  selenium_downloads:
Author	SHA1	Message	Date
Sun-ZhenXing	28ed2462af	feat: Add Chinese documentation and Docker Compose configurations for DeepTutor and llama.cpp - Created README.zh.md for DeepTutor with comprehensive features, installation steps, and usage instructions in Chinese. - Added docker-compose.yaml for DeepTutor to define services, environment variables, and resource limits. - Introduced .env.example for llama.cpp with configuration options for server settings and resource management. - Added README.md and README.zh.md for llama.cpp detailing features, prerequisites, quick start guides, and API documentation. - Implemented docker-compose.yaml for llama.cpp to support various server configurations (CPU, CUDA, ROCm) and CLI usage.	2026-02-01 16:08:44 +08:00
Sun-ZhenXing	e2ac465417	feat: add MoltBot service with configuration files and documentation	2026-01-30 10:12:03 +08:00
Sun-ZhenXing	31bcf0c435	chore: update mineru	2026-01-29 17:37:44 +08:00
Sun-ZhenXing	aeddac52bf	Update MinerU, Gitea, InfluxDB, Phoenix, and Selenium configurations - Bump MinerU version from 2.7.1 to 2.7.2 in .env.example, Dockerfile, README files, and docker-compose.yaml. - Update Gitea version from 1.25.2-rootless to 1.25.4-rootless in .env.example and docker-compose.yaml. - Add InfluxDB configuration files including .env.example, README.md, README.zh.md, and docker-compose.yaml with version 2.8.0. - Bump Phoenix version from 12.28.1-nonroot to 12.31.2-nonroot in .env.example and docker-compose.yaml, and update README files. - Introduce Selenium standalone configuration with version 144.0-20260120, including .env.example, README.md, README.zh.md, and docker-compose.yaml.	2026-01-25 22:59:55 +08:00
Sun-ZhenXing	32742dc535	feat: add opencode	2026-01-22 10:48:31 +08:00
Sun-ZhenXing	2a010843d1	feat: add FalkorDB, LMDeploy, and Pogocache with configuration files and documentation	2026-01-20 14:18:28 +08:00
Sun-ZhenXing	1c528c0e64	feat: add flowise	2026-01-20 13:10:28 +08:00