FoundationAgents/OpenManus

No fortress, purely open ground. OpenManus is Coming.

What it solves

OpenManus is an open-source framework designed to build general AI agents that can execute complex ideas and tasks without requiring invite codes or proprietary access. It provides a way for users to deploy their own autonomous agents capable of browser automation and data analysis.

How it works

The system leverages Large Language Models (LLMs) and a set of integrated tools to perform tasks. It uses the Browser Use CLI as a default Model Context Protocol (MCP) server to enable the agent to interact with the and take screenshots. It also supports a specialized DataAnalysis Agent for visualization and data tasks. The framework allows for different execution modes, including a standard single-agent setup, an MCP tool version, and a multi-agent flow version.

Who it’s for

Developers and AI enthusiasts who want to build and run autonomous general-purpose agents locally or via cloud browsers, and those looking for an open-source alternative to proprietary agent platforms.

Highlights

  • Browser Automation: Integrated with Browser Use and Playwright for native web interaction and screenshots.
  • Multi-Agent Support: Includes an unstable multi-agent version and a specialized DataAnalysis Agent for visualization.
  • MCP Integration: Uses the Model Context Protocol to manage tools and browser capabilities.
  • Flexible Configuration: Supports various LLM APIs via a simple configuration file.

Written about in

Related

  • Project
    browser-use/browser-use

    A library and framework that enables AI agents to control a web browser like a human to automate tasks such as filling forms and extracting data.

  • Project
    webbrain-one/webbrain

    An open-source AI browser agent extension that automates web tasks, extracts data, and runs multi-step workflows using local or cloud LLMs.

  • Project
    MaxGfeller/open-harness

    A framework based on Vercel's AI SDK for building general-purpose AI agents with built-in support for tool use, session management, and composable middleware.

  • Project
    the-open-agent/openagent

    An open-source personal AI assistant platform that combines LLMs, RAG, and autonomous agent loops into a single, self-hostable binary.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents from different runtimes can share context, files, and a browser.