OpenClaw - Self-Hosted AI Assistant

OpenClaw Tutorial — Install OpenClaw, connect to New API, and quickly build a self-hosted AI assistant. An open-source project with support for multi-channel integrations such as Lark, Discord, and Slack.

Project Overview

OpenClaw is an open-source, self-hosted personal AI assistant platform that connects messaging apps to AI agents running on your own hardware. Designed for developers and advanced users, it lets you have an autonomous AI assistant without giving up control of your data.

Official website: https://openclaw.ai
Project documentation: https://docs.openclaw.ai
GitHub: https://github.com/moltbot/moltbot

OpenClaw (open claw) is fully open source. You can browse the source code, submit Issues, or contribute in the OpenClaw GitHub repository. This tutorial covers the complete process for installing, configuring, and connecting OpenClaw to New API.

🌟 Core Features

Multi-Channel Integration

Cross-platform coverage: Supports multiple mainstream messaging platforms including Lark, Discord, Slack, and Microsoft Teams
Single gateway: Manage all channels through a single Gateway process
Voice support: Supports voice interaction on macOS/iOS/Android
Canvas UI: Can render interactive Canvas interfaces

Self-Hosting and Data Security

Fully self-hosted: Runs on your own machine or server
Open-source transparency: MIT license with fully transparent code
Local data storage: Context and skills are stored on your local computer rather than in the cloud

Intelligent Agent Capabilities

Continuous operation: Supports always-on background execution with persistent memory
Scheduled tasks: Supports cron scheduled tasks
Session isolation: Isolates sessions by agent/workspace/sender
Multi-agent routing: Supports collaborative work across multiple agents
Tool calling: Native support for tool calling and code execution

📦 Installation

Requirements

Node.js 22 or later
An AI model API key

npm install -g openclaw@latest

After installation, run the onboarding wizard:

openclaw onboard

{
  "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://api.moleapi.com/v1",
        "apiKey": "sk-your-api-key-from-moleapi",
        "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 Items

Configuration Item	Description
`models.providers.newapi.baseUrl`	New API deployment URL. Must include `/v1`
`models.providers.newapi.apiKey`	New API key
`models.providers.newapi.models`	Model list. You can add multiple models as needed
`agents.defaults.model.primary`	Default primary model, in the format `provider/model-id`
`agents.defaults.model.fallbacks`	Fallback model list. Automatically switches when the primary model is unavailable
`channels.lark.appId`	Lark app App ID, obtained from the Lark Open Platform
`channels.lark.appSecret`	Lark app App Secret
`gateway.port`	Gateway listening port
`gateway.auth.token`	Gateway access security token

Start the Service

After completing the configuration, start OpenClaw:

openclaw start

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

OpenClaw - Self-Hosted AI Assistant

🌟 Core Features

Multi-Channel Integration

Self-Hosting and Data Security

Intelligent Agent Capabilities

📦 Installation

🚀 Configuration

Configuration File Location

Configuration Example

Key Configuration Items

Start the Service

On this page