OpenClaw logo

OpenClaw

Your own personal AI assistant

AI Latest: 2026.3.28

Introduction

OpenClaw is a personal AI assistant you run on your own devices. It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, Microsoft Teams, WebChat), plus extension channels like BlueBubbles, Matrix, Zalo, and Zalo Personal. It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.

If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.

Highlights

  • Local-first Gateway — single control plane for sessions, channels, tools, and events.
  • Multi-channel inbox — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, Microsoft Teams, Matrix, Zalo, Zalo Personal, WebChat, macOS, iOS/Android.
  • Multi-agent routing — route inbound channels/accounts/peers to isolated agents (workspaces + 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 Discord/Slack actions.
  • Companion apps — macOS menu bar app + iOS/Android nodes.
  • Onboarding + skills — wizard-driven setup with bundled/managed/workspace skills.

Common Providers & Models

  • MiniMax: minimax/MiniMax-M2.1
  • DeepSeek: deepseek/deepseek-chat
  • Qwen: qwen/qwen2.5-coder-32b-instruct
  • Moonshot (Kimi): moonshot/kimi-k2.5
  • ZAI (GLM): zai/glm-4.7
  • OpenAI: openai/gpt-4o-mini
  • Anthropic: anthropic/claude-3-7-sonnet
  • Gemini: gemini/gemini-1.5-pro
  • Groq: groq/llama-3.1-70b-versatile
  • Mistral: mistral/large-latest
  • Cohere: cohere/command-r-plus

Local Ollama Model Setup

  1. Install Ollama from the 1Panel App Store, then open the AI - Models menu to add a model.
  2. It is recommended to use newer models, such as:
    • qwen3-coder:30b
    • glm-4.7
    • gpt-oss:20b
    • gpt-oss:120b

Older models are likely incompatible and may cause OpenClaw to not work properly.

2. Install OpenClaw

  1. API Key: Enter any English characters.
  2. Base URL: Use the container name or IP address, for example: http://<ollama-container-name-or-ip>:11434/v1
  3. Model configuration: Format as ollama/<model-name>, for example: ollama/qwen3:14b

Obtain the OpenClaw Token

Open the openclaw.json file and copy the value of "gateway.auth.token".
Use this token to access the OpenClaw application.

  "gateway": {
    "mode": "local",
    "auth": {
      "mode": "token",
      "token": "c9917c5a066beeb26266d09baed99495e7563b33c771e89a"
    },
    ***

Deploy OpenClaw with 1Panel

  1. Install 1Panel on your VPS (Linux server).

    # Copy and paste the following command into your terminal and press Enter
    bash -c "$(curl -sSL https://resource.1panel.pro/v2/quick_start.sh)"
  2. Open the 1Panel dashboard, go to App Store.

  3. Search for OpenClaw and click Install.

  4. Fill in the required parameters (ports, admin credentials, storage path), then confirm.

  5. After deployment, create a website/reverse proxy in 1Panel if you want a custom domain.

  6. Enable HTTPS (recommended) and keep the app updated from the App Store.