FoundationAgents /
OpenManus
Open-source general AI agent that runs tasks from your terminal with your own LLM key
- 58.8k stars
- Python
- Updated 23 days ago
- Some experience
- AI agents
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.
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.gituv pip install -r requirements.txtpython main.pyCommands are copied from the project's README. Read it on GitHub for the full setup.
More in AI agents
openclaw
Self-hosted AI assistant that answers in your chat apps and runs on your own machine
hermes-agent
Self-hosted AI agent that keeps skills and memory, and chats via terminal or Telegram
TradingAgents
A team of LLM agents that debate and decide on stock trades, for research
paperclip
A Node.js server and React dashboard for running a team of AI agents like a company
autoresearch
Let an AI agent edit a small LLM training script overnight and keep what improves it
ruflo
Agent harness adding swarms, memory and plugins around Claude Code and Codex
multica
A shared board where you assign issues to AI coding agents like teammates
openhuman
Rust agent harness with a desktop app, terminal client and embeddable library
buzz
Self-hostable team workspace where people and AI agents share channels on a Nostr relay
composio
SDK and CLI that connect AI agents to 1000+ apps with per-user auth