# OpenClaw

Open-source agent platform for browser, tool, and workflow automation that actually takes actions.

## Summary
OpenClaw is an open-source agent platform for running action-oriented AI workflows across browser automation, tools, skills, local execution, and connected services.


## Guide
OpenClaw is an open-source agent platform for running action-oriented AI workflows across browser automation, tools, skills, local execution, and connected services.

### What it is
OpenClaw is an open AI agents resource tracked by OpenAgent.bot because it gives builders a concrete implementation path rather than just a product claim.

### Why it matters
OpenClaw matters because it represents the shift from chat assistants to agents that operate software. It gives builders a concrete runtime to study browser control, tool execution, skills, safety boundaries, and workflow automation in one place.

### How it works
Start from the official repository or documentation, verify the license and runtime requirements, then test it on a narrow workflow before expanding it into production use.


## Use Cases
- Browser-based automation: Use OpenClaw as a candidate when an agent must navigate websites, fill forms, or inspect pages.
- Reusable agent workflows: Turn repeated tasks into skills, scripts, or controlled workflows that agents can run again.
- Agent safety research: Study the risks that appear when agents can execute code, access accounts, and use authenticated browser sessions.

## Alternatives
- OpenClaw is for doing, not just chatting vs chatbot UIs: A chatbot interface is useful for conversation; OpenClaw is relevant when the agent needs tool access and workflow execution.

### Getting Started
- Review the GitHub repository: https://github.com/openclaw/openclaw
- Official source: https://openclawdoc.com/

### FAQ
- Is OpenClaw open source?
  - OpenClaw is listed with MIT based on its official source links. Always re-check the repository or model card before production use.
- Who should evaluate OpenClaw?
  - Builders experimenting with browser and tool-using agents
## Why It Matters
OpenClaw matters because it represents the shift from chat assistants to agents that operate software. It gives builders a concrete runtime to study browser control, tool execution, skills, safety boundaries, and workflow automation in one place.


## Best For
- Builders experimenting with browser and tool-using agents
- Teams that want a self-hosted runtime for repeatable automation workflows
- Researchers studying agent safety, permissions, and real-world action boundaries

## Not For
- Users who only want a passive chatbot
- Teams unwilling to review sandboxing, credentials, and safety controls before giving an agent tool access

## What It Actually Does
- Action-oriented runtime: OpenClaw is designed for agents that can use tools and automate tasks, not just answer questions.
  - Why it matters: That makes it a useful reference point for the whole action-agent category.
- Browser and workflow surface: Its ecosystem emphasizes browser control, tools, channels, and reusable skills.
  - Why it matters: Real agent work often happens across websites, APIs, files, and messaging systems.
- Open-source inspection path: The public repository lets builders inspect how the runtime handles execution and boundaries.
  - Why it matters: Action agents require trust, and trust starts with inspectable implementation details.

## Typical Use Cases
- Browser-based automation: Use OpenClaw as a candidate when an agent must navigate websites, fill forms, or inspect pages.
- Reusable agent workflows: Turn repeated tasks into skills, scripts, or controlled workflows that agents can run again.
- Agent safety research: Study the risks that appear when agents can execute code, access accounts, and use authenticated browser sessions.

## How It Compares
- OpenClaw is for doing, not just chatting vs chatbot UIs: A chatbot interface is useful for conversation; OpenClaw is relevant when the agent needs tool access and workflow execution.

## Command Line
### Clone the OpenClaw repository
Start from the official repository and docs before installing daemons, browser access, or connected services.

```bash
git clone https://github.com/openclaw/openclaw.git
```

## Facts
- Category: agents
- Resource type: agent
- Open source: yes
- License: MIT
- Last verified: 2026-04-19
- GitHub repo: openclaw/openclaw

## Capabilities
- browser-automation
- workflow-orchestration
- tool-calling
- mcp
- browser

## Structured Use Case Tags
- browser-agent
- self-hosted-ai
- developer-workflow

## Getting Started
- Review the GitHub repository: https://github.com/openclaw/openclaw
- Official source: https://openclawdoc.com/

## Links
- GitHub: https://github.com/openclaw/openclaw
- Homepage: https://openclawdoc.com/

## Structured Outputs
- JSON: https://www.openagent.bot/agents/openclaw.json
- Markdown: https://www.openagent.bot/agents/openclaw.md
- Canonical: https://www.openagent.bot/agents/openclaw