Openclaw is an open-source AI automation framework designed for developers who want full control over their AI workflows. It runs on your infrastructure with complete source code access and customization through TypeScript plugins.

Who should use Openclaw?

Openclaw is built for developers and technical teams who need programmable AI automation with full source code access, custom plugin development, and zero vendor lock-in.

How is Openclaw different from ChatGPT or Claude?

ChatGPT and Claude are hosted AI services. Openclaw is a framework you deploy yourself—you control the infrastructure, data never leaves your environment, and you can swap underlying models without changing application code.

How do I install Openclaw?

Quick start with: curl -fsSL https://openclaw.im/install.sh | bash. For production, use Docker or deploy to Kubernetes with provided Helm charts.

Can I use Openclaw with local models?

Yes. Openclaw supports Ollama out of the box for fully offline operation with Llama, Mistral, or any compatible model. No API keys required.

Open Source|MIT Licensed|Built by Developers, for Developers

Your Code, Your AI, Your Rules

Openclaw is an open-source framework that lets developers build AI-powered automations. Route messages, execute workflows, and extend with plugins—all running on your own infrastructure.

View Source on GitHub Get Started

What It Does

Runs on Your Machine

Mac, Windows, or Linux. Anthropic, OpenAI, or local models. Private by default—your data stays yours.

Any Chat App

Talk to it on WhatsApp, Telegram, Discord, Slack, Signal, or iMessage. Works in DMs and group chats.

Persistent Memory

Remembers you and becomes uniquely yours. Your preferences, your context, your AI.

Browser Control

It can browse the web, fill forms, and extract data from any site.

Full System Access

Read and write files, run shell commands, execute scripts. Full access or sandboxed—your choice.

Skills & Plugins

Extend with community skills or build your own. It can even write its own.

60k+

GitHub Stars

50+

Integrations

Chat Platforms

MIT

Open Source

“Openclaw is running my company. I just tell it what I need and it handles everything from scheduling to email responses.”

Alex Chen

@alexchen

“Finally an AI assistant that actually DOES things instead of just telling me how to do them. This is the future.”

Sarah Miller

@sarahmiller

“The self-hosted aspect is huge. My data never leaves my machine. Openclaw with Ollama is a game changer for privacy.”

Marcus Johnson

@marcusj

Why Developers Choose Openclaw

Openclaw isn't just another chatbot wrapper—it's a programmable AI framework with transparent source code and a plugin architecture built for extensibility.

Programmable Workflow Engine

Define AI workflows in TypeScript or YAML. Full programmatic control over triggers, conditions, and actions. Build automation logic that fits your exact requirements.

Universal Message Router

Route messages across WhatsApp, Telegram, Discord, Slack, and iMessage through a unified API gateway. Treat messaging platforms as middleware, not lock-in.

Transparent & Auditable

100% open-source under MIT license. Every line of code is auditable. No telemetry, no hidden behaviors. Deploy on your infrastructure with full visibility.

Stateful Context Manager

Built-in session and context management for multi-turn conversations. Persistent state storage with pluggable backends—SQLite, PostgreSQL, or Redis.

Plugin Architecture

Extensible plugin system with 50+ built-in integrations. Write custom plugins in TypeScript. Hot-reload during development. Community plugin registry.

Bring Your Own Model (BYOM)

Zero vendor lock-in. Connect to OpenAI, Anthropic, or run fully local with Ollama. Swap models with a single config change. Your keys, your costs, your control.

Extensible Plugin Ecosystem

Openclaw ships with 50+ built-in integrations. Build custom plugins in TypeScript or leverage community extensions to connect any service.

messaging

WhatsAppTelegramDiscordSlackiMessage

productivity

GmailGoogle CalendarNotionLinearJiraTodoistTrello

developer

GitHub

media

Spotify

ai

OpenAIClaudeOllama

smart home

HomeAssistantPhilips Hue

automation

Zapier

Universal Message Router

Route messages through a unified API gateway

Discord

Slack

iMessage

Openclaw vs Cloud AI Services

Cloud AI services are convenient, but they come with trade-offs. Openclaw gives developers full control without sacrificing capability.

Capability	Cloud AI Services	Openclaw
Source Code Access	Closed source	100% Open Source (MIT)
Data Location	Vendor servers	Your infrastructure
Customization	Limited to API options	Full code-level control
Pricing Model	Per-token fees	Your compute costs only
Model Choice	Vendor-locked	BYOM - Any provider
Audit & Compliance	Trust vendor	Full auditability

Built for developers who want transparency and control

Frequently Asked Questions

Everything you need to know about Openclaw. Can't find an answer? Ask in our Discord community.

Openclaw is an open-source AI automation framework designed for developers who want full control over their AI workflows. Unlike hosted AI services, Openclaw runs on your infrastructure, gives you complete source code access, and lets you customize every aspect of the system through TypeScript plugins and configuration.

Openclaw is built for developers and technical teams who need programmable AI automation. If you want to inspect and modify the source code, write custom plugins, integrate with internal systems, or avoid vendor lock-in, Openclaw is for you. It's not a no-code chatbot builder—it's a developer toolkit.

ChatGPT and Claude are hosted AI services—you send data to their servers and get responses. Openclaw is a framework you deploy yourself. You control the infrastructure, the data never leaves your environment, and you can swap underlying models (GPT-4, Claude, Ollama) without changing your application code.

Openclaw supports multiple deployment methods. Quick start with: curl -fsSL https://openclaw.im/install.sh | bash. For production, use Docker (docker run openclaw/openclaw) or deploy to Kubernetes. Check the GitHub repo for Terraform modules and Helm charts.

Yes. Openclaw's BYOM (Bring Your Own Model) architecture supports Ollama out of the box. Run Llama, Mistral, or any Ollama-compatible model for fully offline operation. No API keys required, no data sent externally. Perfect for air-gapped environments or cost-sensitive deployments.

Openclaw is free and open-source under the MIT license—use it commercially, modify it, redistribute it. No license fees, no usage limits, no vendor lock-in. You only pay for compute (your own servers) and AI model API costs if you choose to use external providers instead of local models.

Write plugins in TypeScript using the Openclaw Plugin SDK. Plugins can add new integrations, custom workflow actions, or modify core behavior. Hot-reload in development, publish to the community registry, or keep them private. See the plugin development guide in the docs.

Start Building with Openclaw

Fork the repo, deploy in minutes, and build AI automations your way. Open source, MIT licensed, and backed by an active developer community.

View Source on GitHub Join Developer Discord

Releases|Documentation|Plugin SDK