OpenClaw - Self-Hosted AI Assistant Platform

Project Introduction

OpenClaw is an open-source, self-hosted personal AI assistant platform that bridges messaging apps to AI agents running on your own hardware. Designed for developers and power users who want autonomous AI assistants without surrendering data control.

Official Website: https://openclaw.ai
Documentation: https://docs.openclaw.ai
GitHub: https://github.com/moltbot/moltbot

🌟 Core Features

Multi-Channel Integration

Full Platform Coverage: Supports Lark (Feishu), Discord, Slack, Microsoft Teams, and more
Single Gateway: Manage all channels through a single Gateway process
Voice Support: Voice interaction on macOS/iOS/Android
Canvas Interface: Render interactive Canvas interfaces

Self-Hosted & Data Security

Fully Self-Hosted: Runs on your own machine or server
Open Source: MIT licensed, fully transparent code
Local Data Storage: Context and skills stored on your local computer, not in the cloud

Intelligent Agent Capabilities

Always-On: Supports background persistent operation with persistent memory
Scheduled Tasks: Supports cron scheduled tasks
Session Isolation: Sessions isolated per agent/workspace/sender
Multi-Agent Routing: Supports multi-agent collaborative work
Tool Calling: Native support for tool calling and code execution

📦 Installation

Requirements

Node.js 22 or higher
An AI model API key

npm install -g openclaw@latest

After installation, run the onboarding wizard:

openclaw onboard

🚀 Configuration

Configuration File Location

The OpenClaw configuration file is located at ~/.openclaw/config.json. It can be auto-generated through the onboarding wizard or manually edited.

Configuration Example

Here is a complete configuration example using New API as the model provider:

{
  "meta": {
    "lastTouchedVersion": "2026.2.1",
    "lastTouchedAt": "2026-02-03T12:17:41.559Z"
  },
  "wizard": {
    "lastRunAt": "2026-02-02T21:17:16.011Z",
    "lastRunVersion": "2026.2.1",
    "lastRunCommand": "onboard",
    "lastRunMode": "local"
  },
  "auth": {
    "cooldowns": {
      "billingBackoffHoursByProvider": {}
    }
  },
  "models": {
    "providers": {
      "newapi": {
        "baseUrl": "https://your-newapi-domain.com/v1",
        "apiKey": "sk-your-api-key",
        "auth": "api-key",
        "api": "openai-completions",
        "models": [
          {
            "id": "gemini-3-flash-preview",
            "name": "gemini-3-flash-preview",
            "api": "openai-completions",
            "reasoning": true,
            "input": [
              "text",
              "image"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 64000
          },
          {
            "id": "kimi-k2.5",
            "name": "kimi-k2.5",
            "api": "openai-completions",
            "reasoning": true,
            "input": [
              "text",
              "image"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 64000
          }
        ]
      }
    },
    "bedrockDiscovery": {
      "providerFilter": []
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "newapi/gemini-3-flash-preview",
        "fallbacks": [
          "newapi/kimi-k2.5"
        ]
      },
      "models": {
        "newapi/gemini-3-flash-preview": {
          "alias": "gemini-3-flash-preview"
        },
        "newapi/kimi-k2.5": {
          "alias": "kimi-k2.5"
        }
      },
      "workspace": "/home/your-username/.openclaw/workspace",
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  },
  "messages": {
    "ackReactionScope": "group-mentions"
  },
  "commands": {
    "native": "auto",
    "nativeSkills": "auto"
  },
  "channels": {
    "lark": {
      "enabled": true,
      "dmPolicy": "pairing",
      "appId": "your-lark-app-id",
      "appSecret": "your-lark-app-secret",
      "groupPolicy": "allowlist",
      "streamMode": "partial"
    }
  },
  "gateway": {
    "port": 18789,
    "mode": "local",
    "bind": "loopback",
    "auth": {
      "mode": "token",
      "token": "your-secure-token"
    },
    "tailscale": {
      "mode": "off",
      "resetOnExit": false
    }
  },
  "skills": {
    "install": {
      "nodeManager": "npm"
    }
  }
}

Key Configuration Details

Configuration Item	Description
`models.providers.newapi.baseUrl`	New API deployment address, must include `/v1`
`models.providers.newapi.apiKey`	New API token key
`models.providers.newapi.models`	Model list, add multiple models as needed
`agents.defaults.model.primary`	Default primary model, format: `provider/model-id`
`agents.defaults.model.fallbacks`	Fallback model list, auto-switches when primary is unavailable
`channels.lark.appId`	Lark (Feishu) App ID, obtained from Lark Open Platform
`channels.lark.appSecret`	Lark (Feishu) App Secret
`gateway.port`	Gateway listening port
`gateway.auth.token`	Gateway access security token

Start the Service

After configuration is complete, start OpenClaw:

openclaw start

Once started, you can interact with the AI assistant through the configured channels.

OpenClaw - Self-Hosted AI Assistant Platform

On this page