A self-hosted, OpenAI-compatible AI engine that runs LLMs, vision, voice, image and video models on any hardware, including CPU-only machines.
openclaw/openclaw
A self-hosted personal AI assistant that runs on your own devices and answers you through messaging apps like WhatsApp, Telegram, Slack and Discord.
- Stars
- 392,439
- Forks
- 82,492
- Open issues
- 9,458
- Last commit
- 5 hours ago
What is it?
OpenClaw is an open-source AI assistant that runs on your own computer and connects to the chat services you already use, including Discord, iMessage, Slack, Teams, Telegram, WhatsApp and many more. A single local Gateway acts as the control plane for sessions, tools, events and channel connections, and the Control UI, CLI and TUI all connect to it. Native companion apps exist for macOS, iOS, Android, Windows and Linux.
State, memory and credentials are stored on your own hardware. Model providers and agent harnesses such as Claude, Codex or local models are pluggable, so they can be swapped without changing the rest of the setup. Tools, skills and plugins extend what the assistant can do, and the project provides a plugin SDK for building new ones.
Inbound messages are treated as untrusted input, and direct-message channels pair unknown senders by default. Tools run on the host unless sandboxing is configured, so the project documents security and sandboxing guides before exposing the Gateway to other users or remote networks.
Key features
- 01Connects to WhatsApp, Telegram, Slack, Discord, iMessage, Teams and 20+ other chat channels.
- 02Runs a local Gateway that manages sessions, tools and channel connections.
- 03Supports hosted and local model providers, including Claude, Codex and local models.
- 04Extends with tools, skills and a plugin SDK, with ClawHub for sharing plugins.
- 05Provides native companion apps for macOS, iOS, Android, Windows and Linux.
- 06Stores state, memory and credentials on your own hardware.
Use cases
- Running a personal assistant on your laptop that you message from your usual chat apps.
- Deploying a shared assistant for a small team, with configuration as the only difference from a personal setup.
- Keeping conversation history and credentials on your own machines instead of a hosted service.
Quick start
- 1
Install with the installer script (macOS, Linux, WSL2)
curl -fsSL https://openclaw.ai/install.sh | bash - 2
Run onboarding (if installed via npm, pnpm, or Bun)
openclaw onboard --install-daemon - 3
Open the Control UI dashboard
openclaw dashboard
Things to know
- Onboarding requires configuring a model provider, which may need a paid or hosted API account.
- Tools run on the host by default unless sandboxing is configured, so security setup matters before exposing it to others.
- The README warns to treat inbound messages as untrusted input and to read the security guide before exposing the Gateway remotely.
Topics
FAQ
- What is openclaw?
- A self-hosted personal AI assistant that runs on your own devices and answers you through messaging apps like WhatsApp, Telegram, Slack and Discord. OpenClaw is an open-source AI assistant that runs on your own computer and connects to the chat services you already use, including Discord, iMessage, Slack, Teams, Telegram, WhatsApp and many more. A single local Gateway acts as the control plane for sessions, tools, events and channel connections, and the Control UI, CLI and TUI all connect to it. Native companion apps exist for macOS, iOS, Android, Windows and Linux.
- Is openclaw free to use? What license does it have?
- openclaw is open source under the MIT license. Check the license terms before using it in commercial products.
- Is openclaw still maintained?
- Actively maintained. The last commit to openclaw was on Oct 19, 2026.
- What can I use openclaw for?
- Running a personal assistant on your laptop that you message from your usual chat apps. Deploying a shared assistant for a small team, with configuration as the only difference from a personal setup. Keeping conversation history and credentials on your own machines instead of a hosted service.
- How do I install openclaw?
- Install with the installer script (macOS, Linux, WSL2): curl -fsSL https://openclaw.ai/install.sh | bash Run onboarding (if installed via npm, pnpm, or Bun): openclaw onboard --install-daemon Open the Control UI dashboard: openclaw dashboard
- Where can I get openclaw?
- The source code and installation instructions are on GitHub: https://github.com/openclaw/openclaw
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Self-hosted ChatGPT-style chat platform that unifies many AI providers, with Agents, MCP support, Artifacts, and multi-user auth.
An MCP server that lets AI assistants like Claude and Cursor run web searches through a SearXNG instance you operate or trust.
AutoGPT is an open-source platform for building, running, and scheduling AI agents that carry out multi-step workflows from plain-English descriptions or a visual builder.
A Python framework and runtime for building, serving, and managing AI agent platforms, with a web UI for administration.
An open agent framework where the AI agent gets its own Dockerized Linux desktop, browser, and document tools to carry out real work.