Suits people comfortable with a terminal and Node.js who want a self-hosted assistant; read the security guide first, since tools run on the host unless you set up sandboxing.

What can you build with openclaw?

Chat with a personal AI assistant from WhatsApp, Telegram or iMessage while it runs on your own computer. Run a shared assistant for a team in Slack or Teams from a single Gateway. Switch between Claude, Codex or a local model without changing your chat setup. Write a plugin or skill that gives the assistant a new ability and share it on ClawHub. Use voice or camera features through the companion apps on your phone or desktop.

openclaw /

openclaw

Self-hosted AI assistant that answers in your chat apps and runs on your own machine

392.8k stars
1.6k stars since 3 Oct
TypeScript
Updated today
Some experience
AI agents

Open on GitHub (opens in a new tab) Website (opens in a new tab)

OpenClaw is an AI assistant you run yourself. Instead of opening a separate website, you talk to it in the messaging apps you already use, such as Discord, Telegram, Slack, WhatsApp and iMessage, or through native apps for macOS, iOS, Android, Windows and Linux.

A program called the Gateway sits at the centre. It runs locally and manages sessions, tools, events and the connections to each chat channel. The command line, a web Control UI and a terminal UI all connect to it. The same Gateway can serve one person on a laptop or a whole team; the README says configuration is the only difference.

Models are plugins. You can use Claude, Codex or local models and change them without touching the rest of the setup. State, memory and credentials stay on your hardware, though your prompts still go to whichever model provider and chat platforms you configure. The project is stewarded by an independent non-profit foundation and says it has no paid tier or hosted service.

What it does

Many chat channels
Connects to Discord, iMessage, Slack, Teams, Telegram, WhatsApp, Signal, Google Chat and 20+ more. Unknown senders in direct messages are paired and must be approved by default.
Local Gateway
One local control plane handles sessions, tools, events and channel connections. The CLI, Control UI and terminal UI all talk to it.
Swappable models
Hosted and local model providers plug in, so you can change models without reworking the rest of the setup.
Tools, skills and plugins
The assistant can be extended with tools, skills and plugins. New capabilities are meant to be built with the plugin SDK and shared through ClawHub.
Companion apps
Apps and device nodes add voice, Canvas, camera, screen and device-local actions on supported platforms.

What you could build

Chat with a personal AI assistant from WhatsApp, Telegram or iMessage while it runs on your own computer.
Run a shared assistant for a team in Slack or Teams from a single Gateway.
Switch between Claude, Codex or a local model without changing your chat setup.
Write a plugin or skill that gives the assistant a new ability and share it on ClawHub.
Use voice or camera features through the companion apps on your phone or desktop.

Get started

Run the installer for your system (a PowerShell version exists for Windows), then complete the onboarding wizard it opens. If you installed through a package manager, run the onboard command yourself. Afterwards open the dashboard and send a message to check the assistant works.

curl -fsSL https://openclaw.ai/install.sh | bash

openclaw onboard --install-daemon

openclaw dashboard

Commands are copied from the project's README. Read it on GitHub for the full setup.

Anything better than openclaw?

OpenClaw is the strongest pick for a personal assistant living in your chat apps on your own hardware, with by far the most stars and activity. Look elsewhere only for multi-user setups, tighter sandboxing, or a web chat UI instead of messaging apps.