OpenClaw is a free, open source ai interaction & interfaces project written in TypeScript and released under a custom open-source licence. It has 389,982 GitHub stars, 81,978 forks and 6,671 open issues, and was last pushed 3 hours ago. On this registry it ranks #1 of 76 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available. It gained 473 stars over the last 6 tracked days.

OpenClaw — An AI assistant that acts, not just answers

What is OpenClaw?

OpenClaw is an open-source, self-hosted AI assistant in the AI & Machine Learning / AI Interaction & Interfaces category that runs on hardware the user controls and meets them inside the messaging channels they already use, for individuals who want a personal assistant on a laptop and teams that want a shared deployment.

What it is

OpenClaw is an open-source AI assistant written in TypeScript and stewarded by the OpenClaw Foundation, an independent 501(c)(3). It runs on the operator's own computer and appears in channels already in use — Discord, iMessage, Slack, Teams, Telegram, WhatsApp, and more than twenty others — alongside native apps for macOS, iOS, Android, Windows, and Linux. One Gateway runs it as a personal assistant on a laptop or as a shared team deployment, with configuration the only difference between the two. State, memory, and credentials live on the operator's hardware, while models and agent harnesses such as Claude, Codex, and local models are plugins that can be swapped without changing anything else.

The problem it solves is ownership of a persistent assistant that acts rather than only answers. State, memory, and credentials stay on hardware the user controls rather than in a vendor account, and the project states it has no paid tier, no hosted service, and no token. Prompts go to the model providers and chat platforms the operator configures, plus any diagnostics export they enable; by default OpenClaw phones home for nothing but a daily version check, anonymous feature statistics are opt-in, and update.checkOnStart: false disables both. It also removes the separate assistant app, putting the assistant into WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, and other messaging services already in use.

Key capabilities

  • Channels spanning Discord, iMessage, Slack, Teams, Telegram, WhatsApp, and more than twenty other services, including Google Chat and Signal.
  • Native apps for macOS, iOS, Android, Windows, and Linux, with companion apps and nodes adding voice, Canvas, camera, screen, and device-local actions.
  • One Gateway as the local control plane for sessions, tools, events, and channel connections, reached through the Control UI, CLI, or TUI.
  • Swappable model providers, hosted or local, installed as plugins alongside agent harnesses such as Claude, Codex, and local models.
  • Tools, skills, and plugins that extend what an assistant can do.
  • Privacy and security defaults: a daily version check is the only default outbound contact, update.checkOnStart: false turns it off, and DM-capable channels pair unknown senders by default with approval via openclaw pairing approve.

Who uses it and how

  • An individual who runs the installer on a personal laptop and reaches the assistant through channels already open.
  • A small team running the same Gateway as a shared team deployment, where only configuration differs from a personal setup.
  • Operators who need one assistant across several operating systems, using the native macOS, iOS, Android, Windows, and Linux apps.
  • Privacy-conscious adopters who keep state, memory, and credentials on their own hardware while choosing hosted or local model providers.

Getting started

Install with the macOS, Linux, and Windows installer — curl -fsSL https://openclaw.ai/install.sh | bash, or iwr -useb https://openclaw.ai/install.ps1 | iex in PowerShell — or with npm install -g openclaw@latest --allow-scripts=openclaw on Node 24.16+ or 26.1+ (Node 26 recommended). Then run openclaw onboard --install-daemon, openclaw gateway status, and openclaw dashboard; Docker, Nix, and other deployment paths appear in the installation guide.

How it compares

The facts name no comparable assistant product, so no head-to-head comparison is offered here. On the evidence given, OpenClaw stands alone in this registry, distinguished by having no paid tier, no hosted service, and no token.

When to use it — and when not to

A self-hoster must operate the Gateway and its runtime, supply model-provider access, configure and approve channel pairings, and decide whether tools run on the host or under sandboxing. Anyone who wants a managed or hosted assistant with no operational responsibility should look elsewhere, since the project offers no hosted service. The entry also carries licence value NOASSERTION and shows 6,671 open issues, so licence terms should be confirmed from the repository and the backlog weighed before adoption.

project readme (upstream, from github) — read inline

OpenClaw 🦞 — Your assistant, on your devices, in your chats

OpenClaw — EXFOLIATE! EXFOLIATE! Your AI assistant, running on your own devices.

CI status npm version Node.js version License: MIT Discord

OpenClaw is an open-source AI assistant that runs on your own computer and meets you in the channels you already use: Discord, iMessage, Slack, Teams, Telegram, WhatsApp, and 20+ more, plus native apps for macOS, iOS, Android, Windows, and Linux. One Gateway runs it as a personal assistant on a laptop or as a shared team deployment; configuration is the only difference.

Yours, with no catch. State, memory, and credentials live on your hardware. Models and agent harnesses (Claude, Codex, local models) are plugins you can swap without changing anything else. Your prompts go to the model provider and chat platforms you configure, plus any diagnostics export you enable yourself; by default OpenClaw itself phones home for nothing but a daily version check, anonymous feature statistics are opt-in, and update.checkOnStart: false disables both (what OpenClaw sends). OpenClaw is stewarded by the OpenClaw Foundation, an independent 501(c)(3), and has no paid tier, hosted service, or token. The architecture case — trusted gateway, untrusted execution, deterministic policy — is in Why OpenClaw.

Website · Docs · Getting started · Why OpenClaw · Showcase · FAQ · Vision · DeepWiki

Install

The installer supports macOS, Linux, and Windows. It provisions a supported Node.js runtime when needed.

# macOS / Linux / WSL2
curl -fsSL https://openclaw.ai/install.sh | bash
# Windows PowerShell
iwr -useb https://openclaw.ai/install.ps1 | iex

Already manage Node.js? Install the published package instead (Node 24.16+ or 26.1+; Node 26 recommended):

npm install -g openclaw@latest --allow-scripts=openclaw

That command is for npm 12 or npm 11.16+. On npm 11.15 and earlier, omit --allow-scripts=openclaw. See the installation guide for the lifecycle script contract, Docker, Nix, and other deployment paths.

Quick start

On a fresh install, the installer scripts start onboarding automatically. Complete the wizard they open. If you installed the package directly with npm, pnpm, or Bun, run:

openclaw onboard --install-daemon

After onboarding:

openclaw gateway status
openclaw dashboard

Onboarding verifies model access, creates the workspace, and configures the Gateway. The last command opens the Control UI; send a message there to confirm the assistant is working. See the getting started guide for channel setup and troubleshooting.

How it fits together

  • The Gateway is the local control plane for sessions, tools, events, and channel connections.
  • The Control UI, CLI, and TUI connect to the Gateway.
  • Channels bring the assistant to WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, and other messaging services.
  • Companion apps and nodes add voice, Canvas, camera, screen, and device-local actions on supported platforms.

OpenClaw works with hosted and local model providers. Its tools, skills, and plugins extend what an assistant can do.

Security

Treat inbound messages as untrusted input. DM-capable channels pair unknown senders by default; approve a pairing request with openclaw pairing approve <code>.

Tools run on the host for the main session unless you configure sandboxing. Read the security guide, exposure runbook, and sandboxing guide before connecting other users or exposing the Gateway remotely.

Documentation

Goal Start here
Configure models and auth Models · Model providers
Connect a messaging service Channels
Add tools, skills, and plugins Tools · Skills · Plugins · ClawHub
Run apps and device nodes Platforms · Nodes
Use the CLI and chat commands CLI reference · Slash commands
Configure or operate the Gateway Configuration · Architecture · Updating · Release channels

Development

The repository is a pnpm workspace. Plain npm install at the repository root is not supported.

git clone https://github.com/openclaw/openclaw.git
cd openclaw
pnpm install
pnpm build
pnpm ui:build

See CONTRIBUTING.md for the contribution workflow and the source setup guide for the development loop.

Governance

OpenClaw is developed in the open by the OpenClaw Foundation, an independent 501(c)(3). The Foundation employs the core team and signs releases. Donors and infrastructure sponsors support the Foundation; none of them own or direct the project. OpenAI is a donor, not an owner.

Community

See CONTRIBUTING.md for maintainers and contribution guidelines; AI-assisted PRs are welcome.

Use the [issue chooser](https://github.com/opencl

readme truncated — read the full docs on github

Frequently asked questions

Is OpenClaw free to use?

OpenClaw is open source. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does OpenClaw do?

An AI assistant that acts, not just answers

What is OpenClaw written in?

OpenClaw is primarily written in TypeScript. Its source is publicly available at https://github.com/openclaw/openclaw, and it has 389,982 GitHub stars.