OpenManus
An open-source AI agent framework runs locally, connects to LLM APIs, and automates Chrome or Chromium through Browser Use.
Alternative to:
OpenManus is a Python framework for developers who want to run and extend a general AI agent on their own machine. You give it tasks through a terminal, and it connects a language model to tools that can act on those tasks.
- Browser automation: The agent uses Browser Use to interact with web pages and capture screenshots in Chrome or Chromium.
- MCP tools: MCP support lets the agent work with tools exposed through the Model Context Protocol.
- Model connections: You can choose the LLM API endpoint and model, with separate settings for vision tasks; the supplied example uses OpenAI's GPT-4o.
The framework runs locally on macOS, Windows and Unix systems and uses the MIT license. Local execution doesn't mean offline AI: it requires credentials for the LLM APIs it uses, and requests go to the selected provider.
Browser Use can control a local browser without a Browser Use API key. Its optional Cloud browser runs remotely and requires Browser Use authentication.
Logotyper
