# OpenManus

> Open-source general AI agent that runs tasks from your terminal with your own LLM key

- Repository: https://github.com/FoundationAgents/OpenManus
- Category: AI agents
- Stars: 58,759 · Forks: 10,184 · Language: Python · License: MIT
- Experience: Some experience
- Page: https://ir.adyog.com/repos/foundationagents/openmanus/

Manus is an AI agent product that was available by invite only. OpenManus is a community project from contributors in the MetaGPT group that lets you run a similar kind of agent yourself. The README calls it a simple implementation and says the first prototype was built in about three hours.

You install it with Python, put an LLM API key in a config file, and run python main.py. Then you type your idea in the terminal and the agent works on it. For web tasks it starts Browser Use as a default MCP server, so the agent gets browser tools for running commands and taking screenshots.

Besides the main agent, there is an MCP tool version and an experimental multi-agent flow. The flow can add a DataAnalysis agent for data analysis and charts. The README says it builds on anthropic-computer-use, browser-use and crawl4ai. A sibling project, OpenManus-RL, covers reinforcement-learning tuning of LLM agents.

## What it does

- **Terminal-driven agent**: Run python main.py and type a task. The agent uses whichever LLM you set in config/config.toml.
- **Browser automation built in**: Browser Use CLI starts as a default MCP server through uvx. It can attach to local Chrome or Chromium without an API key, or use a Browser Use Cloud browser. An environment variable turns it off.
- **MCP tool version**: python run_mcp.py runs a version of the agent that uses MCP tools.
- **Experimental multi-agent flow**: python run_flow.py runs several agents together. The README labels it unstable. You can enable a DataAnalysis agent for analysis and visualization tasks in config.toml.
- **Configurable LLMs**: The config file sets model, base URL, API key, max tokens and temperature. You can add a separate vision model.

## What you could build

- Try a general-purpose agent on your own ideas without waiting for an invite to a hosted product.
- Study how a small agent framework wires an LLM to browser tools and MCP.
- Run data analysis and chart-making tasks through the optional DataAnalysis agent.
- Point an agent at the web to do browsing tasks using your local Chrome.
- Extend the codebase with your own agents or tools and contribute changes back.

## Who it's for

Developers comfortable with Python and the command line who have an LLM API key and want to experiment with or study an open agent framework.

## Get started

Clone the repo, create a Python 3.12 environment (the README recommends uv) and install requirements.txt. Copy config/config.example.toml to config/config.toml, add your API key, then run python main.py and type your task.

```
git clone https://github.com/FoundationAgents/OpenManus.git
```
```
uv pip install -r requirements.txt
```
```
python main.py
```

Tags: ai-agent, llm, mcp, browser-automation, python