feat(nanobot): add README and docker-compose configuration for multi-channel AI assistant

feat(openclaw): introduce OpenClaw personal AI assistant with multi-channel support and CLI

fix(mineru): update MinerU version to 2.7.6 in Dockerfile and documentation

README.md

@@ -1,5 +1,7 @@
 # Compose Anything
 
+[中文说明](README.zh.md) | [English](README.md)
+
 Compose Anything helps users quickly deploy various services by providing a set of high-quality Docker Compose configuration files. These configurations constrain resource usage, can be easily migrated to systems like K8S, and are easy to understand and modify.
 
 ## Build Services
@@ -12,7 +14,7 @@ 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)              | 2.7.2   |
+| [MinerU vLLM](./builds/mineru)              | 2.7.6   |
 
 ## Supported Services
 
@@ -89,6 +91,7 @@ These services require building custom Docker images from source.
 | [MongoDB Standalone](./src/mongodb-standalone)                 | 8.2.3                |
 | [MySQL](./src/mysql)                                           | 9.4.0                |
 | [n8n](./apps/n8n)                                              | 1.114.0              |
+| [Nanobot](./apps/nanobot)                                      | v0.1.3.post4         |
 | [Nacos](./src/nacos)                                           | v3.1.0               |
 | [NebulaGraph](./src/nebulagraph)                               | v3.8.0               |
 | [NexaSDK](./src/nexa-sdk)                                      | v0.2.62              |

README.zh.md

@@ -1,5 +1,7 @@
 # Compose Anything
 
+[中文说明](README.zh.md) | [English](README.md)
+
 Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，帮助用户快速部署各种服务。这些配置约束了资源使用，可快速迁移到 K8S 等系统，并且易于理解和修改。
 
 ## 构建服务
@@ -12,7 +14,7 @@ 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)              | 2.7.2  |
+| [MinerU vLLM](./builds/mineru)              | 2.7.6  |
 
 ## 已经支持的服务
 
@@ -89,6 +91,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件，
 | [MongoDB Standalone](./src/mongodb-standalone)                 | 8.2.3                 |
 | [MySQL](./src/mysql)                                           | 9.4.0                 |
 | [n8n](./apps/n8n)                                              | 1.114.0               |
+| [Nanobot](./apps/nanobot)                                      | v0.1.3.post4          |
 | [Nacos](./src/nacos)                                           | v3.1.0                |
 | [NebulaGraph](./src/nebulagraph)                               | v3.8.0                |
 | [NexaSDK](./src/nexa-sdk)                                      | v0.2.62               |

apps/nanobot/.env.example

@@ -0,0 +1,144 @@
+# Nanobot version
+NANOBOT_VERSION=v0.1.3.post4
+
+# Timezone
+TZ=UTC
+
+# Port override
+NANOBOT_PORT_OVERRIDE=18790
+
+# Command to run (gateway, onboard, status, agent, etc.)
+NANOBOT_COMMAND=gateway
+
+# ============================================================================
+# LLM Provider Configuration
+# ============================================================================
+
+# OpenRouter (recommended for global access to all models)
+# Get API key: https://openrouter.ai/keys
+OPENROUTER_API_KEY=
+
+# Anthropic (Claude direct access)
+# Get API key: https://console.anthropic.com
+ANTHROPIC_API_KEY=
+
+# OpenAI (GPT direct access)
+# Get API key: https://platform.openai.com
+OPENAI_API_KEY=
+
+# Google Gemini
+# Get API key: https://aistudio.google.com
+GEMINI_API_KEY=
+
+# DeepSeek
+# Get API key: https://platform.deepseek.com
+DEEPSEEK_API_KEY=
+
+# Groq (LLM + Voice transcription)
+# Get API key: https://console.groq.com
+GROQ_API_KEY=
+
+# Zhipu AI (智谱 AI)
+# Get API key: https://open.bigmodel.cn
+ZHIPU_API_KEY=
+
+# Alibaba Cloud DashScope (阿里云通义千问)
+# Get API key: https://dashscope.console.aliyun.com
+DASHSCOPE_API_KEY=
+
+# Moonshot (月之暗面 Kimi)
+# Get API key: https://platform.moonshot.cn
+MOONSHOT_API_KEY=
+
+# vLLM / Local LLM Server
+# For local models running on vLLM or OpenAI-compatible server
+VLLM_API_KEY=dummy
+VLLM_API_BASE=http://localhost:8000/v1
+
+# ============================================================================
+# Agent Configuration
+# ============================================================================
+
+# Model to use (examples: anthropic/claude-opus-4-5, gpt-4, deepseek/deepseek-chat)
+NANOBOT_MODEL=anthropic/claude-opus-4-5
+
+# Maximum tokens for model response
+NANOBOT_MAX_TOKENS=8192
+
+# Temperature for model (0.0-1.0, higher = more creative)
+NANOBOT_TEMPERATURE=0.7
+
+# Maximum tool iterations per turn
+NANOBOT_MAX_TOOL_ITERATIONS=20
+
+# ============================================================================
+# Channel Configuration
+# ============================================================================
+
+# Telegram
+# 1. Create bot via @BotFather on Telegram
+# 2. Get your user ID from @userinfobot
+TELEGRAM_ENABLED=false
+TELEGRAM_TOKEN=
+TELEGRAM_PROXY=
+
+# Discord
+# 1. Create bot at https://discord.com/developers/applications
+# 2. Enable MESSAGE CONTENT INTENT in bot settings
+DISCORD_ENABLED=false
+DISCORD_TOKEN=
+
+# WhatsApp (requires Node.js bridge)
+# 1. Run `nanobot channels login` to scan QR code
+# 2. Bridge URL points to the WhatsApp bridge server
+WHATSAPP_ENABLED=false
+WHATSAPP_BRIDGE_URL=ws://localhost:3001
+
+# Feishu (飞书/Lark)
+# 1. Create app at https://open.feishu.cn/app
+# 2. Enable Bot capability and add im:message permission
+FEISHU_ENABLED=false
+FEISHU_APP_ID=
+FEISHU_APP_SECRET=
+FEISHU_ENCRYPT_KEY=
+FEISHU_VERIFICATION_TOKEN=
+
+# ============================================================================
+# Tools Configuration
+# ============================================================================
+
+# Brave Search API (for web search tool)
+# Get API key: https://brave.com/search/api/
+BRAVE_API_KEY=
+
+# Web search max results
+WEB_SEARCH_MAX_RESULTS=5
+
+# Shell command execution timeout (seconds)
+EXEC_TIMEOUT=60
+
+# Restrict all tool access to workspace directory
+# Set to true for production/sandboxed environments
+RESTRICT_TO_WORKSPACE=false
+
+# ============================================================================
+# Gateway Configuration
+# ============================================================================
+
+# Gateway host (0.0.0.0 allows external connections)
+GATEWAY_HOST=0.0.0.0
+
+# Gateway port (internal port, mapped via NANOBOT_PORT_OVERRIDE)
+GATEWAY_PORT=18790
+
+# ============================================================================
+# Resource Limits
+# ============================================================================
+
+# CPU limits
+NANOBOT_CPU_LIMIT=1.0
+NANOBOT_CPU_RESERVATION=0.5
+
+# Memory limits
+NANOBOT_MEMORY_LIMIT=1G
+NANOBOT_MEMORY_RESERVATION=512M

apps/nanobot/README.md

@@ -0,0 +1,269 @@
+# Nanobot
+
+[中文说明](README.zh.md) | [English](README.md)
+
+Nanobot is a lightweight, production-ready personal AI assistant with multi-channel support (Telegram, Discord, WhatsApp, Feishu), local model integration, and powerful tool capabilities.
+
+## Features
+
+- 🤖 **Multi-Provider LLM Support**: OpenRouter, Anthropic, OpenAI, DeepSeek, Groq, Gemini, and more
+- 🖥️ **Local Models**: Run your own models with vLLM or any OpenAI-compatible server
+- 💬 **Multi-Channel**: Telegram, Discord, WhatsApp, and Feishu (飞书) integration
+- 🛠️ **Powerful Tools**: File operations, shell execution, web search, and custom skills
+- 📅 **Scheduled Tasks**: Cron-like job scheduling with natural language
+- 🎯 **Memory & Skills**: Persistent memory and extensible skill system
+- 🔒 **Security**: Sandbox mode, access control, and safe command execution
+
+## Quick Start
+
+### Prerequisites
+
+- Docker and Docker Compose installed
+- At least one LLM provider API key (recommended: [OpenRouter](https://openrouter.ai/keys))
+
+### Setup
+
+1. **Copy the example environment file:**
+
+    ```bash
+    cp .env.example .env
+    ```
+
+2. **Edit `.env` and configure at least one LLM provider:**
+
+    ```bash
+    # For OpenRouter (recommended for global access)
+    OPENROUTER_API_KEY=sk-or-v1-xxxxx
+
+    # Or use any other provider
+    ANTHROPIC_API_KEY=sk-ant-xxxxx
+    OPENAI_API_KEY=sk-xxxxx
+    ```
+
+3. **Start the service:**
+
+    ```bash
+    docker compose up -d
+    ```
+
+4. **Initialize configuration (first time only):**
+
+    ```bash
+    docker compose exec nanobot nanobot onboard
+    ```
+
+5. **Check status:**
+
+    ```bash
+    docker compose exec nanobot nanobot status
+    ```
+
+## Usage
+
+### CLI Mode
+
+Chat directly with nanobot:
+
+```bash
+docker compose exec nanobot nanobot agent -m "What is 2+2?"
+```
+
+Interactive mode:
+
+```bash
+docker compose exec nanobot nanobot agent
+```
+
+### Gateway Mode (Default)
+
+The default `docker compose up` starts the gateway server which enables:
+
+- Telegram bot integration
+- Discord bot integration
+- WhatsApp messaging (requires additional setup)
+- Feishu/Lark integration
+- HTTP API access (port 18790)
+
+### Channel Setup
+
+#### Telegram
+
+1. Create a bot via [@BotFather](https://t.me/BotFather) on Telegram
+2. Get your user ID from [@userinfobot](https://t.me/userinfobot)
+3. Configure in `.env`:
+
+    ```bash
+    TELEGRAM_ENABLED=true
+    TELEGRAM_TOKEN=your_bot_token
+    ```
+
+4. Restart the service
+
+#### Discord
+
+1. Create a bot at [Discord Developer Portal](https://discord.com/developers/applications)
+2. Enable **MESSAGE CONTENT INTENT** in bot settings
+3. Configure in `.env`:
+
+    ```bash
+    DISCORD_ENABLED=true
+    DISCORD_TOKEN=your_bot_token
+    ```
+
+4. Restart the service
+
+#### WhatsApp
+
+Requires Node.js and additional setup. See [official documentation](https://github.com/HKUDS/nanobot#-chat-apps) for details.
+
+#### Feishu (飞书)
+
+1. Create an app at [Feishu Open Platform](https://open.feishu.cn/app)
+2. Enable Bot capability and add `im:message` permission
+3. Configure in `.env`:
+
+    ```bash
+    FEISHU_ENABLED=true
+    FEISHU_APP_ID=your_app_id
+    FEISHU_APP_SECRET=your_app_secret
+    ```
+
+4. Restart the service
+
+## Configuration
+
+### Environment Variables
+
+See [.env.example](.env.example) for all available configuration options.
+
+Key settings:
+
+| Variable                | Description                                | Default                     |
+| ----------------------- | ------------------------------------------ | --------------------------- |
+| `NANOBOT_MODEL`         | LLM model to use                           | `anthropic/claude-opus-4-5` |
+| `NANOBOT_COMMAND`       | Command to run (gateway, agent, status)    | `gateway`                   |
+| `RESTRICT_TO_WORKSPACE` | Sandbox mode - restrict tools to workspace | `false`                     |
+| `BRAVE_API_KEY`         | API key for web search tool                | (empty)                     |
+| `TELEGRAM_ENABLED`      | Enable Telegram channel                    | `false`                     |
+| `DISCORD_ENABLED`       | Enable Discord channel                     | `false`                     |
+
+### LLM Provider Priority
+
+When multiple providers are configured, nanobot will:
+
+1. Match provider based on model name (e.g., `gpt-4` → OpenAI)
+2. Fall back to first available API key
+
+### Security
+
+For production deployments:
+
+- Set `RESTRICT_TO_WORKSPACE=true` to sandbox all file and shell operations
+- Configure `allowFrom` lists in the config file for channel access control
+- Use dedicated user accounts for channel integrations
+- Monitor API usage and set spending limits
+- Keep credentials in environment variables, never in code
+
+## Scheduled Tasks
+
+Run tasks on a schedule:
+
+```bash
+# Add a daily reminder
+docker compose exec nanobot nanobot cron add \
+  --name "morning" \
+  --message "Good morning! What's on the agenda?" \
+  --cron "0 9 * * *"
+
+# List scheduled jobs
+docker compose exec nanobot nanobot cron list
+
+# Remove a job
+docker compose exec nanobot nanobot cron remove <job_id>
+```
+
+## Local Models (vLLM)
+
+Run nanobot with your own local models:
+
+1. **Start a vLLM server:**
+
+    ```bash
+    vllm serve meta-llama/Llama-3.1-8B-Instruct --port 8000
+    ```
+
+2. **Configure in `.env`:**
+
+    ```bash
+    VLLM_API_KEY=dummy
+    VLLM_API_BASE=http://host.docker.internal:8000/v1
+    NANOBOT_MODEL=meta-llama/Llama-3.1-8B-Instruct
+    ```
+
+3. **Restart the service**
+
+## Volumes
+
+- `nanobot_config`: Configuration files and credentials
+- `nanobot_workspace`: Agent workspace and files
+
+## Ports
+
+- `18790`: Gateway HTTP API (configurable via `NANOBOT_PORT_OVERRIDE`)
+
+## Resource Limits
+
+Default resource limits:
+
+- CPU: 1.0 cores (limit), 0.5 cores (reservation)
+- Memory: 1GB (limit), 512MB (reservation)
+
+Adjust via environment variables: `NANOBOT_CPU_LIMIT`, `NANOBOT_MEMORY_LIMIT`, etc.
+
+## Troubleshooting
+
+### Check logs
+
+```bash
+docker compose logs -f nanobot
+```
+
+### Verify configuration
+
+```bash
+docker compose exec nanobot nanobot status
+```
+
+### Test LLM connection
+
+```bash
+docker compose exec nanobot nanobot agent -m "Hello!"
+```
+
+### Common issues
+
+**No API key configured:**
+
+- Ensure at least one provider API key is set in `.env`
+- Restart the service after updating environment variables
+
+**Channel not responding:**
+
+- Check that the channel is enabled in `.env`
+- Verify bot tokens are correct
+- Check logs for connection errors
+
+**File permission errors:**
+
+- Ensure volumes have proper permissions
+- Try running with `RESTRICT_TO_WORKSPACE=false` for debugging
+
+## License
+
+Nanobot is an open-source project. See the [official repository](https://github.com/HKUDS/nanobot) for license details.
+
+## Links
+
+- Official Repository: <https://github.com/HKUDS/nanobot>
+- Documentation: <https://github.com/HKUDS/nanobot#readme>
+- Issues: <https://github.com/HKUDS/nanobot/issues>

apps/nanobot/README.zh.md

@@ -0,0 +1,269 @@
+# Nanobot
+
+[中文说明](README.zh.md) | [English](README.md)
+
+Nanobot 是一个轻量级、生产就绪的个人 AI 助手，支持多渠道（Telegram、Discord、WhatsApp、飞书），本地模型集成，以及强大的工具能力。
+
+## 特性
+
+- 🤖 **多 LLM 提供商支持**：OpenRouter、Anthropic、OpenAI、DeepSeek、Groq、Gemini 等
+- 🖥️ **本地模型**：使用 vLLM 或任何 OpenAI 兼容服务器运行您自己的模型
+- 💬 **多渠道**：集成 Telegram、Discord、WhatsApp 和飞书
+- 🛠️ **强大工具**：文件操作、Shell 执行、网络搜索和自定义技能
+- 📅 **定时任务**：支持自然语言的类 Cron 任务调度
+- 🎯 **记忆与技能**：持久化记忆和可扩展技能系统
+- 🔒 **安全性**：沙盒模式、访问控制和安全命令执行
+
+## 快速开始
+
+### 前置要求
+
+- 已安装 Docker 和 Docker Compose
+- 至少一个 LLM 提供商 API 密钥（推荐：[OpenRouter](https://openrouter.ai/keys)）
+
+### 配置步骤
+
+1. **复制环境变量示例文件：**
+
+    ```bash
+    cp .env.example .env
+    ```
+
+2. **编辑 `.env` 并至少配置一个 LLM 提供商：**
+
+    ```bash
+    # 使用 OpenRouter（推荐，可访问所有模型）
+    OPENROUTER_API_KEY=sk-or-v1-xxxxx
+
+    # 或使用其他提供商
+    ANTHROPIC_API_KEY=sk-ant-xxxxx
+    OPENAI_API_KEY=sk-xxxxx
+    ```
+
+3. **启动服务：**
+
+    ```bash
+    docker compose up -d
+    ```
+
+4. **初始化配置（仅首次需要）：**
+
+    ```bash
+    docker compose exec nanobot nanobot onboard
+    ```
+
+5. **检查状态：**
+
+    ```bash
+    docker compose exec nanobot nanobot status
+    ```
+
+## 使用方法
+
+### CLI 模式
+
+直接与 nanobot 对话：
+
+```bash
+docker compose exec nanobot nanobot agent -m "2+2 等于多少？"
+```
+
+交互模式：
+
+```bash
+docker compose exec nanobot nanobot agent
+```
+
+### 网关模式（默认）
+
+默认的 `docker compose up` 会启动网关服务器，支持：
+
+- Telegram 机器人集成
+- Discord 机器人集成
+- WhatsApp 消息（需要额外配置）
+- 飞书 / Lark 集成
+- HTTP API 访问（端口 18790）
+
+### 渠道配置
+
+#### Telegram
+
+1. 通过 Telegram 上的 [@BotFather](https://t.me/BotFather) 创建机器人
+2. 从 [@userinfobot](https://t.me/userinfobot) 获取您的用户 ID
+3. 在 `.env` 中配置：
+
+    ```bash
+    TELEGRAM_ENABLED=true
+    TELEGRAM_TOKEN=你的机器人令牌
+    ```
+
+4. 重启服务
+
+#### Discord
+
+1. 在 [Discord 开发者门户](https://discord.com/developers/applications) 创建机器人
+2. 在机器人设置中启用 **MESSAGE CONTENT INTENT**
+3. 在 `.env` 中配置：
+
+    ```bash
+    DISCORD_ENABLED=true
+    DISCORD_TOKEN=你的机器人令牌
+    ```
+
+4. 重启服务
+
+#### WhatsApp
+
+需要 Node.js 和额外配置。详见 [官方文档](https://github.com/HKUDS/nanobot#-chat-apps)。
+
+#### 飞书
+
+1. 在 [飞书开放平台](https://open.feishu.cn/app) 创建应用
+2. 启用机器人能力并添加 `im:message` 权限
+3. 在 `.env` 中配置：
+
+    ```bash
+    FEISHU_ENABLED=true
+    FEISHU_APP_ID=你的应用ID
+    FEISHU_APP_SECRET=你的应用密钥
+    ```
+
+4. 重启服务
+
+## 配置
+
+### 环境变量
+
+所有可用配置选项请参见 [.env.example](.env.example)。
+
+关键设置：
+
+| 变量                    | 描述                                   | 默认值                      |
+| ----------------------- | -------------------------------------- | --------------------------- |
+| `NANOBOT_MODEL`         | 要使用的 LLM 模型                      | `anthropic/claude-opus-4-5` |
+| `NANOBOT_COMMAND`       | 要运行的命令（gateway、agent、status） | `gateway`                   |
+| `RESTRICT_TO_WORKSPACE` | 沙盒模式 - 限制工具访问工作空间        | `false`                     |
+| `BRAVE_API_KEY`         | 网络搜索工具的 API 密钥                | （空）                      |
+| `TELEGRAM_ENABLED`      | 启用 Telegram 渠道                     | `false`                     |
+| `DISCORD_ENABLED`       | 启用 Discord 渠道                      | `false`                     |
+
+### LLM 提供商优先级
+
+当配置了多个提供商时，nanobot 将：
+
+1. 根据模型名称匹配提供商（例如 `gpt-4` → OpenAI）
+2. 回退到第一个可用的 API 密钥
+
+### 安全性
+
+对于生产部署：
+
+- 设置 `RESTRICT_TO_WORKSPACE=true` 以沙盒化所有文件和 Shell 操作
+- 在配置文件中为渠道访问控制配置 `allowFrom` 列表
+- 为渠道集成使用专用用户账户
+- 监控 API 使用并设置支出限制
+- 将凭证保存在环境变量中，绝不在代码中
+
+## 定时任务
+
+按计划运行任务：
+
+```bash
+# 添加每日提醒
+docker compose exec nanobot nanobot cron add \
+  --name "morning" \
+  --message "早上好！今天有什么安排？" \
+  --cron "0 9 * * *"
+
+# 列出计划任务
+docker compose exec nanobot nanobot cron list
+
+# 删除任务
+docker compose exec nanobot nanobot cron remove <job_id>
+```
+
+## 本地模型（vLLM）
+
+使用您自己的本地模型运行 nanobot：
+
+1. **启动 vLLM 服务器：**
+
+    ```bash
+    vllm serve meta-llama/Llama-3.1-8B-Instruct --port 8000
+    ```
+
+2. **在 `.env` 中配置：**
+
+    ```bash
+    VLLM_API_KEY=dummy
+    VLLM_API_BASE=http://host.docker.internal:8000/v1
+    NANOBOT_MODEL=meta-llama/Llama-3.1-8B-Instruct
+    ```
+
+3. **重启服务**
+
+## 数据卷
+
+- `nanobot_config`：配置文件和凭证
+- `nanobot_workspace`：代理工作空间和文件
+
+## 端口
+
+- `18790`：网关 HTTP API（可通过 `NANOBOT_PORT_OVERRIDE` 配置）
+
+## 资源限制
+
+默认资源限制：
+
+- CPU：1.0 核心（限制），0.5 核心（预留）
+- 内存：1GB（限制），512MB（预留）
+
+通过环境变量调整：`NANOBOT_CPU_LIMIT`、`NANOBOT_MEMORY_LIMIT` 等。
+
+## 故障排除
+
+### 查看日志
+
+```bash
+docker compose logs -f nanobot
+```
+
+### 验证配置
+
+```bash
+docker compose exec nanobot nanobot status
+```
+
+### 测试 LLM 连接
+
+```bash
+docker compose exec nanobot nanobot agent -m "你好！"
+```
+
+### 常见问题
+
+**未配置 API 密钥：**
+
+- 确保在 `.env` 中至少设置了一个提供商 API 密钥
+- 更新环境变量后重启服务
+
+**渠道无响应：**
+
+- 检查渠道是否在 `.env` 中启用
+- 验证机器人令牌是否正确
+- 检查日志中的连接错误
+
+**文件权限错误：**
+
+- 确保数据卷具有适当的权限
+- 调试时尝试使用 `RESTRICT_TO_WORKSPACE=false` 运行
+
+## 许可证
+
+Nanobot 是一个开源项目。许可证详情请参见 [官方仓库](https://github.com/HKUDS/nanobot)。
+
+## 链接
+
+- 官方仓库：<https://github.com/HKUDS/nanobot>
+- 文档：<https://github.com/HKUDS/nanobot#readme>
+- 问题反馈：<https://github.com/HKUDS/nanobot/issues>

apps/nanobot/docker-compose.yaml

@@ -0,0 +1,76 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  nanobot:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-ghcr.io/}hkuds/nanobot:${NANOBOT_VERSION:-v0.1.3.post4}
+    ports:
+      - "${NANOBOT_PORT_OVERRIDE:-18790}:18790"
+    volumes:
+      - nanobot_config:/root/.nanobot
+      - nanobot_workspace:/root/.nanobot/workspace
+    environment:
+      - TZ=${TZ:-UTC}
+      # LLM Provider Configuration
+      - NANOBOT_PROVIDERS__OPENROUTER__API_KEY=${OPENROUTER_API_KEY:-}
+      - NANOBOT_PROVIDERS__ANTHROPIC__API_KEY=${ANTHROPIC_API_KEY:-}
+      - NANOBOT_PROVIDERS__OPENAI__API_KEY=${OPENAI_API_KEY:-}
+      - NANOBOT_PROVIDERS__GEMINI__API_KEY=${GEMINI_API_KEY:-}
+      - NANOBOT_PROVIDERS__DEEPSEEK__API_KEY=${DEEPSEEK_API_KEY:-}
+      - NANOBOT_PROVIDERS__GROQ__API_KEY=${GROQ_API_KEY:-}
+      - NANOBOT_PROVIDERS__ZHIPU__API_KEY=${ZHIPU_API_KEY:-}
+      - NANOBOT_PROVIDERS__DASHSCOPE__API_KEY=${DASHSCOPE_API_KEY:-}
+      - NANOBOT_PROVIDERS__MOONSHOT__API_KEY=${MOONSHOT_API_KEY:-}
+      - NANOBOT_PROVIDERS__VLLM__API_KEY=${VLLM_API_KEY:-}
+      - NANOBOT_PROVIDERS__VLLM__API_BASE=${VLLM_API_BASE:-}
+      # Agent Configuration
+      - NANOBOT_AGENTS__DEFAULTS__MODEL=${NANOBOT_MODEL:-anthropic/claude-opus-4-5}
+      - NANOBOT_AGENTS__DEFAULTS__MAX_TOKENS=${NANOBOT_MAX_TOKENS:-8192}
+      - NANOBOT_AGENTS__DEFAULTS__TEMPERATURE=${NANOBOT_TEMPERATURE:-0.7}
+      - NANOBOT_AGENTS__DEFAULTS__MAX_TOOL_ITERATIONS=${NANOBOT_MAX_TOOL_ITERATIONS:-20}
+      # Channel Configuration
+      - NANOBOT_CHANNELS__TELEGRAM__ENABLED=${TELEGRAM_ENABLED:-false}
+      - NANOBOT_CHANNELS__TELEGRAM__TOKEN=${TELEGRAM_TOKEN:-}
+      - NANOBOT_CHANNELS__TELEGRAM__PROXY=${TELEGRAM_PROXY:-}
+      - NANOBOT_CHANNELS__DISCORD__ENABLED=${DISCORD_ENABLED:-false}
+      - NANOBOT_CHANNELS__DISCORD__TOKEN=${DISCORD_TOKEN:-}
+      - NANOBOT_CHANNELS__WHATSAPP__ENABLED=${WHATSAPP_ENABLED:-false}
+      - NANOBOT_CHANNELS__WHATSAPP__BRIDGE_URL=${WHATSAPP_BRIDGE_URL:-ws://localhost:3001}
+      - NANOBOT_CHANNELS__FEISHU__ENABLED=${FEISHU_ENABLED:-false}
+      - NANOBOT_CHANNELS__FEISHU__APP_ID=${FEISHU_APP_ID:-}
+      - NANOBOT_CHANNELS__FEISHU__APP_SECRET=${FEISHU_APP_SECRET:-}
+      - NANOBOT_CHANNELS__FEISHU__ENCRYPT_KEY=${FEISHU_ENCRYPT_KEY:-}
+      - NANOBOT_CHANNELS__FEISHU__VERIFICATION_TOKEN=${FEISHU_VERIFICATION_TOKEN:-}
+      # Tools Configuration
+      - NANOBOT_TOOLS__WEB__SEARCH__API_KEY=${BRAVE_API_KEY:-}
+      - NANOBOT_TOOLS__WEB__SEARCH__MAX_RESULTS=${WEB_SEARCH_MAX_RESULTS:-5}
+      - NANOBOT_TOOLS__EXEC__TIMEOUT=${EXEC_TIMEOUT:-60}
+      - NANOBOT_TOOLS__RESTRICT_TO_WORKSPACE=${RESTRICT_TO_WORKSPACE:-false}
+      # Gateway Configuration
+      - NANOBOT_GATEWAY__HOST=${GATEWAY_HOST:-0.0.0.0}
+      - NANOBOT_GATEWAY__PORT=${GATEWAY_PORT:-18790}
+    command: ${NANOBOT_COMMAND:-gateway}
+    healthcheck:
+      test: ["CMD", "python", "-c", "import sys; sys.exit(0)"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 10s
+    deploy:
+      resources:
+        limits:
+          cpus: ${NANOBOT_CPU_LIMIT:-1.0}
+          memory: ${NANOBOT_MEMORY_LIMIT:-1G}
+        reservations:
+          cpus: ${NANOBOT_CPU_RESERVATION:-0.5}
+          memory: ${NANOBOT_MEMORY_RESERVATION:-512M}
+
+volumes:
+  nanobot_config:
+  nanobot_workspace:

apps/openclaw/.env.example

@@ -1,4 +1,4 @@
-# MoltBot Environment Configuration
+# OpenClaw Environment Configuration
 # Copy this file to .env and configure the values
 
 # Timezone (default: UTC)
@@ -8,27 +8,27 @@ TZ=UTC
 # Examples: docker.io/, ghcr.io/, your-registry.com/
 GLOBAL_REGISTRY=
 
-# MoltBot Version
+# OpenClaw Version
-# Use 'main' for latest, or specific version tag like 'v2026.1.27'
+# Use 'main' for latest, or specific version tag like 'v2026.2.3'
-MOLTBOT_VERSION=main
+OPENCLAW_VERSION=2026.2.3
 
 # === Gateway Configuration ===
 # Gateway access token (REQUIRED - generate a secure random token)
 # Example: openssl rand -hex 32
-MOLTBOT_GATEWAY_TOKEN=your-secure-token-here
+OPENCLAW_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
+OPENCLAW_GATEWAY_BIND=lan
 
 # Gateway internal port (default: 18789)
-MOLTBOT_GATEWAY_PORT=18789
+OPENCLAW_GATEWAY_PORT=18789
 
 # Gateway host port override (default: 18789)
-MOLTBOT_GATEWAY_PORT_OVERRIDE=18789
+OPENCLAW_GATEWAY_PORT_OVERRIDE=18789
 
 # Bridge port override (default: 18790)
-MOLTBOT_BRIDGE_PORT_OVERRIDE=18790
+OPENCLAW_BRIDGE_PORT_OVERRIDE=18790
 
 # === Model API Keys (Optional - if not using OAuth) ===
 # Anthropic Claude API Key
@@ -44,11 +44,11 @@ CLAUDE_WEB_COOKIE=
 
 # === Resource Limits ===
 # Gateway service resource limits
-MOLTBOT_CPU_LIMIT=2.0
+OPENCLAW_CPU_LIMIT=2.0
-MOLTBOT_MEMORY_LIMIT=2G
+OPENCLAW_MEMORY_LIMIT=2G
-MOLTBOT_CPU_RESERVATION=1.0
+OPENCLAW_CPU_RESERVATION=1.0
-MOLTBOT_MEMORY_RESERVATION=1G
+OPENCLAW_MEMORY_RESERVATION=1G
 
 # CLI service resource limits
-MOLTBOT_CLI_CPU_LIMIT=1.0
+OPENCLAW_CLI_CPU_LIMIT=1.0
-MOLTBOT_CLI_MEMORY_LIMIT=512M
+OPENCLAW_CLI_MEMORY_LIMIT=512M

apps/openclaw/README.md

@@ -1,6 +1,6 @@
-# MoltBot
+# OpenClaw
 
-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.
+OpenClaw 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
 
@@ -32,7 +32,7 @@ MoltBot is a personal AI assistant that runs on your own devices. It integrates
    ```
 
 3. Edit `.env` and set at least:
-   - `MOLTBOT_GATEWAY_TOKEN` - Your generated token
+   - `OPENCLAW_GATEWAY_TOKEN` - Your generated token
    - `ANTHROPIC_API_KEY` or `OPENAI_API_KEY` - If using API key auth
 
 4. Start the gateway:
@@ -51,8 +51,8 @@ MoltBot is a personal AI assistant that runs on your own devices. It integrates
 
 The gateway can be accessed in two ways:
 
-- **Loopback** (`MOLTBOT_GATEWAY_BIND=loopback`): Only accessible from the host machine (127.0.0.1)
+- **Loopback** (`OPENCLAW_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)
+- **LAN** (`OPENCLAW_GATEWAY_BIND=lan`): Accessible from your local network (0.0.0.0)
 
 For production deployments, consider:
 
@@ -62,7 +62,7 @@ For production deployments, consider:
 
 ### Model Configuration
 
-MoltBot supports multiple AI model providers:
+OpenClaw supports multiple AI model providers:
 
 - **Anthropic Claude** (Recommended): Claude Pro/Max with OAuth or API key
 - **OpenAI**: ChatGPT/Codex with OAuth or API key
@@ -86,7 +86,7 @@ To connect messaging platforms:
 
 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.
+See the [official documentation](https://docs.openclaw.bot/channels) for detailed setup instructions.
 
 ## Using the CLI
 
@@ -94,23 +94,23 @@ The CLI service is available via the `cli` profile:
 
 ```bash
 # Run onboarding wizard
-docker compose run --rm --service-ports moltbot-cli onboard
+docker compose run --rm --service-ports openclaw-cli onboard
 
 # List providers
-docker compose run --rm moltbot-cli providers list
+docker compose run --rm openclaw-cli providers list
 
 # Send a message
-docker compose run --rm moltbot-cli message send --to +1234567890 --message "Hello"
+docker compose run --rm openclaw-cli message send --to +1234567890 --message "Hello"
 
 # Check health
-docker compose run --rm moltbot-cli health --port 18789
+docker compose run --rm openclaw-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.
+2. **DM Access**: By default, OpenClaw 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
@@ -128,29 +128,29 @@ docker compose run --rm moltbot-cli health --port 18789
 Adjust CPU and memory limits in `.env`:
 
 ```env
-MOLTBOT_CPU_LIMIT=2.0
+OPENCLAW_CPU_LIMIT=2.0
-MOLTBOT_MEMORY_LIMIT=2G
+OPENCLAW_MEMORY_LIMIT=2G
-MOLTBOT_CPU_RESERVATION=1.0
+OPENCLAW_CPU_RESERVATION=1.0
-MOLTBOT_MEMORY_RESERVATION=1G
+OPENCLAW_MEMORY_RESERVATION=1G
 ```
 
 ### Persistent Data
 
 Data is stored in two Docker volumes:
 
-- `moltbot_config`: Configuration files and credentials (~/.clawdbot)
+- `openclaw_config`: Configuration files and credentials (~/.openclaw)
-- `moltbot_workspace`: Agent workspace and skills (~/clawd)
+- `openclaw_workspace`: Agent workspace and skills (~/openclaw-workspace)
 
 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 openclaw_config:/data -v $(pwd):/backup alpine tar czf /backup/openclaw-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
+docker run --rm -v openclaw_workspace:/data -v $(pwd):/backup alpine tar czf /backup/openclaw-workspace-backup.tar.gz /data
 ```
 
 ### Custom Configuration File
 
-Create a custom config file at `~/.clawdbot/moltbot.json` (inside the container):
+Create a custom config file at `~/.openclaw/openclaw.json` (inside the container):
 
 ```json
 {
@@ -169,7 +169,7 @@ Create a custom config file at `~/.clawdbot/moltbot.json` (inside the container)
 
 ### Gateway Won't Start
 
-1. Check logs: `docker compose logs moltbot-gateway`
+1. Check logs: `docker compose logs openclaw-gateway`
 2. Verify gateway token is set in `.env`
 3. Ensure port 18789 is not already in use
 
@@ -190,25 +190,25 @@ Create a custom config file at `~/.clawdbot/moltbot.json` (inside the container)
 The doctor command helps diagnose common issues:
 
 ```bash
-docker compose run --rm moltbot-cli doctor
+docker compose run --rm openclaw-cli doctor
 ```
 
 ## Documentation
 
-- [Official Website](https://molt.bot)
+- [Official Website](https://openclaw.bot)
-- [Full Documentation](https://docs.molt.bot)
+- [Full Documentation](https://docs.openclaw.bot)
-- [Getting Started Guide](https://docs.molt.bot/start/getting-started)
+- [Getting Started Guide](https://docs.openclaw.bot/start/getting-started)
-- [Configuration Reference](https://docs.molt.bot/gateway/configuration)
+- [Configuration Reference](https://docs.openclaw.bot/gateway/configuration)
-- [Security Guide](https://docs.molt.bot/gateway/security)
+- [Security Guide](https://docs.openclaw.bot/gateway/security)
-- [Docker Installation](https://docs.molt.bot/install/docker)
+- [Docker Installation](https://docs.openclaw.bot/install/docker)
-- [GitHub Repository](https://github.com/moltbot/moltbot)
+- [GitHub Repository](https://github.com/openclaw/openclaw)
 
 ## License
 
-MoltBot is released under the MIT License. See the [LICENSE](https://github.com/moltbot/moltbot/blob/main/LICENSE) file for details.
+OpenClaw is released under the MIT License. See the [LICENSE](https://github.com/openclaw/openclaw/blob/main/LICENSE) file for details.
 
 ## Community
 
 - [Discord](https://discord.gg/clawd)
-- [GitHub Discussions](https://github.com/moltbot/moltbot/discussions)
+- [GitHub Discussions](https://github.com/openclaw/openclaw/discussions)
-- [Issues](https://github.com/moltbot/moltbot/issues)
+- [Issues](https://github.com/openclaw/openclaw/issues)

apps/openclaw/README.zh.md

@@ -1,6 +1,6 @@
-# MoltBot
+# OpenClaw
 
-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。
+OpenClaw 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
 
@@ -32,7 +32,7 @@ MoltBot 是一个运行在你自己设备上的个人 AI 助手。它集成了
    ```
 
 3. 编辑 `.env` 文件，至少设置：
-   - `MOLTBOT_GATEWAY_TOKEN` - 你生成的令牌
+   - `OPENCLAW_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：
@@ -51,8 +51,8 @@ MoltBot 是一个运行在你自己设备上的个人 AI 助手。它集成了
 
 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）
+- **回环地址**（`OPENCLAW_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）
+- **局域网**（`OPENCLAW_GATEWAY_BIND=lan`）：从本地网络访问（0.0.0.0）
 
 对于生产部署，建议：
 
@@ -62,7 +62,7 @@ MoltBot 是一个运行在你自己设备上的个人 AI 助手。它集成了
 
 ### 模型配置
 
-MoltBot 支持多个 AI 模型提供商：
+OpenClaw 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
@@ -86,7 +86,7 @@ MoltBot 支持多个 AI 模型提供商：
 
 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)。
+详细设置说明请参阅[官方文档](https://docs.openclaw.bot/channels)。
 
 ## 使用命令行界面
 
@@ -94,23 +94,23 @@ 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
+docker compose run --rm --service-ports openclaw-cli onboard
 
 # 列出提供商
-docker compose run --rm moltbot-cli providers list
+docker compose run --rm openclaw-cli providers list
 
 # 发送消息
-docker compose run --rm moltbot-cli message send --to +1234567890 --message "你好"
+docker compose run --rm openclaw-cli message send --to +1234567890 --message "你好"
 
 # 检查健康状态
-docker compose run --rm moltbot-cli health --port 18789
+docker compose run --rm openclaw-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。
+2. **私信访问**：默认情况下，OpenClaw 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
@@ -128,29 +128,29 @@ docker compose run --rm moltbot-cli health --port 18789
 在 `.env` 文件中调整 CPU 和内存限制：
 
 ```env
-MOLTBOT_CPU_LIMIT=2.0
+OPENCLAW_CPU_LIMIT=2.0
-MOLTBOT_MEMORY_LIMIT=2G
+OPENCLAW_MEMORY_LIMIT=2G
-MOLTBOT_CPU_RESERVATION=1.0
+OPENCLAW_CPU_RESERVATION=1.0
-MOLTBOT_MEMORY_RESERVATION=1G
+OPENCLAW_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）
+- `openclaw_config`：配置文件和凭据（~/.openclaw）
-- `moltbot_workspace`：代理工作区和技能（~/clawd）
+- `openclaw_workspace`：代理工作区和技能（~/openclaw-workspace）
 
 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 openclaw_config:/data -v $(pwd):/backup alpine tar czf /backup/openclaw-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
+docker run --rm -v openclaw_workspace:/data -v $(pwd):/backup alpine tar czf /backup/openclaw-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：
+在 `~/.openclaw/openclaw.json`（容器内）创建自定义配置文件：
 
 ```json
 {
@@ -169,7 +169,7 @@ docker run --rm -v moltbot_workspace:/data -v $(pwd):/backup alpine tar czf /bac
 
 ### 网关无法启动
 
-1. 检查日志：`docker compose logs moltbot-gateway`
+1. 检查日志：`docker compose logs openclaw-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
 
@@ -190,25 +190,25 @@ docker run --rm -v moltbot_workspace:/data -v $(pwd):/backup alpine tar czf /bac
 诊断命令可帮助诊断常见问题：
 
 ```bash
-docker compose run --rm moltbot-cli doctor
+docker compose run --rm openclaw-cli doctor
 ```
 
 ## 文档
 
-- [官方网站](https://molt.bot)
+- [官方网站](https://openclaw.bot)
-- [完整文档](https://docs.molt.bot)
+- [完整文档](https://docs.openclaw.bot)
-- [入门指南](https://docs.molt.bot/start/getting-started)
+- [入门指南](https://docs.openclaw.bot/start/getting-started)
-- [配置参考](https://docs.molt.bot/gateway/configuration)
+- [配置参考](https://docs.openclaw.bot/gateway/configuration)
-- [安全指南](https://docs.molt.bot/gateway/security)
+- [安全指南](https://docs.openclaw.bot/gateway/security)
-- [Docker 安装](https://docs.molt.bot/install/docker)
+- [Docker 安装](https://docs.openclaw.bot/install/docker)
-- [GitHub 仓库](https://github.com/moltbot/moltbot)
+- [GitHub 仓库](https://github.com/openclaw/openclaw)
 
 ## 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。
+OpenClaw 使用 MIT 许可证发布。详情请参阅 [LICENSE](https://github.com/openclaw/openclaw/blob/main/LICENSE) 文件。
 
 ## 社区
 
 - [Discord](https://discord.gg/clawd)
-- [GitHub 讨论](https://github.com/moltbot/moltbot/discussions)
+- [GitHub 讨论](https://github.com/openclaw/openclaw/discussions)
-- [问题跟踪](https://github.com/moltbot/moltbot/issues)
+- [问题跟踪](https://github.com/openclaw/openclaw/issues)

apps/openclaw/docker-compose.yaml

@@ -1,6 +1,6 @@
-# MoltBot - Personal AI Assistant Docker Compose Configuration
+# OpenClaw - Personal AI Assistant Docker Compose Configuration
-# Official Repository: https://github.com/moltbot/moltbot
+# Official Repository: https://github.com/openclaw/openclaw
-# Documentation: https://docs.molt.bot
+# Documentation: https://docs.openclaw.bot
 
 x-defaults: &defaults
   restart: unless-stopped
@@ -11,18 +11,18 @@ x-defaults: &defaults
       max-file: "3"
 
 services:
-  moltbot-gateway:
+  openclaw-gateway:
     <<: *defaults
-    image: ${GLOBAL_REGISTRY:-ghcr.io}/moltbot/moltbot:${MOLTBOT_VERSION:-main}
+    image: ${GLOBAL_REGISTRY:-ghcr.io}/openclaw/openclaw:${OPENCLAW_VERSION:-2026.2.3}
     environment:
       - TZ=${TZ:-UTC}
       - HOME=/home/node
       - NODE_ENV=production
       - TERM=xterm-256color
       # Gateway configuration
-      - CLAWDBOT_GATEWAY_TOKEN=${MOLTBOT_GATEWAY_TOKEN}
+      - OPENCLAW_GATEWAY_TOKEN=${OPENCLAW_GATEWAY_TOKEN}
-      - CLAWDBOT_GATEWAY_BIND=${MOLTBOT_GATEWAY_BIND:-lan}
+      - OPENCLAW_GATEWAY_BIND=${OPENCLAW_GATEWAY_BIND:-lan}
-      - CLAWDBOT_GATEWAY_PORT=${MOLTBOT_GATEWAY_PORT:-18789}
+      - OPENCLAW_GATEWAY_PORT=${OPENCLAW_GATEWAY_PORT:-18789}
       # Optional: Model API keys (if not using OAuth)
       - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
       - OPENAI_API_KEY=${OPENAI_API_KEY:-}
@@ -30,17 +30,17 @@ services:
       - CLAUDE_WEB_SESSION_KEY=${CLAUDE_WEB_SESSION_KEY:-}
       - CLAUDE_WEB_COOKIE=${CLAUDE_WEB_COOKIE:-}
     volumes:
-      - moltbot_config:/home/node/.clawdbot
+      - openclaw_config:/home/node/.openclaw
-      - moltbot_workspace:/home/node/clawd
+      - openclaw_workspace:/home/node/openclaw-workspace
     ports:
-      - "${MOLTBOT_GATEWAY_PORT_OVERRIDE:-18789}:18789"
+      - "${OPENCLAW_GATEWAY_PORT_OVERRIDE:-18789}:18789"
-      - "${MOLTBOT_BRIDGE_PORT_OVERRIDE:-18790}:18790"
+      - "${OPENCLAW_BRIDGE_PORT_OVERRIDE:-18790}:18790"
     command:
       - node
       - dist/index.js
       - gateway
       - --bind
-      - "${MOLTBOT_GATEWAY_BIND:-lan}"
+      - "${OPENCLAW_GATEWAY_BIND:-lan}"
       - --port
       - "18789"
     healthcheck:
@@ -52,15 +52,15 @@ services:
     deploy:
       resources:
         limits:
-          cpus: ${MOLTBOT_CPU_LIMIT:-2.0}
+          cpus: ${OPENCLAW_CPU_LIMIT:-2.0}
-          memory: ${MOLTBOT_MEMORY_LIMIT:-2G}
+          memory: ${OPENCLAW_MEMORY_LIMIT:-2G}
         reservations:
-          cpus: ${MOLTBOT_CPU_RESERVATION:-1.0}
+          cpus: ${OPENCLAW_CPU_RESERVATION:-1.0}
-          memory: ${MOLTBOT_MEMORY_RESERVATION:-1G}
+          memory: ${OPENCLAW_MEMORY_RESERVATION:-1G}
 
-  moltbot-cli:
+  openclaw-cli:
     <<: *defaults
-    image: ${GLOBAL_REGISTRY:-ghcr.io}/moltbot/moltbot:${MOLTBOT_VERSION:-main}
+    image: ${GLOBAL_REGISTRY:-ghcr.io}/openclaw/openclaw:${OPENCLAW_VERSION:-2026.2.3}
     environment:
       - TZ=${TZ:-UTC}
       - HOME=/home/node
@@ -80,9 +80,9 @@ services:
     deploy:
       resources:
         limits:
-          cpus: ${MOLTBOT_CLI_CPU_LIMIT:-1.0}
+          cpus: ${OPENCLAW_CLI_CPU_LIMIT:-1.0}
-          memory: ${MOLTBOT_CLI_MEMORY_LIMIT:-512M}
+          memory: ${OPENCLAW_CLI_MEMORY_LIMIT:-512M}
 
 volumes:
-  moltbot_config:
+  openclaw_config:
-  moltbot_workspace:
+  openclaw_workspace:

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]>=2.7.3' --break-system-packages && \
+RUN python3 -m pip install -U 'mineru[core]>=2.7.6' --break-system-packages && \
     python3 -m pip cache purge
 
 # Download models and update the configuration file

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 `2.7.3`.
+- `MINERU_VERSION`: The version for MinerU, default is `2.7.6`.
 - `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`.

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 `2.7.3`。
+- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.7.6`。
 - `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`。

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:-2.7.3}
+  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.7.6}
   build:
     context: .
     dockerfile: Dockerfile