AI and models · Independent · 21 Oct 2026

FoundationAgents/OpenManus

No fortress, purely open ground. OpenManus is Coming.

← AI and models
OpenManus: open-source AI agent framework. Runs autonomous tasks from your terminal using LLMs.

In simple English

This program acts as an artificial intelligence assistant that can run tasks on its own. You tell it what you want to do through your terminal window. It plans steps, browses the web and runs code to finish the job. You need your own paid API key from a language model provider to make it work. It costs nothing to download, but you pay for the artificial intelligence queries it makes.

What it is

OpenManus is an open-source framework for building and running general AI agents that execute complex multi-step workflows. It provides a terminal interface and integrates with browser automation tools to complete web-based tasks.

What it is good for

Solo builders who want to experiment with autonomous artificial intelligence agents without paying for closed commercial services or waiting for an invite code.

Stars59k
LicenceMIT
Latestv0.3.0 (2025-04-10)checked 21 Oct 2026
Last code change2026-09-30
Written inPython
Setup effort
3 / 5
Payoff
4 / 5
Good
  • Runs locally on your own machine with full control over your data.
  • Includes built-in browser automation so the agent can interact with websites.
  • Supports custom configurations for different language models and specialized agents.
Watch for
  • Requires an active paid subscription or API balance for a large language model.
  • Autonomous agents can occasionally get stuck in loops or make costly API calls.
  • Setup requires configuring environment variables and text configuration files.
Replaces

Paid commercial autonomous assistant platforms and manual multi-step browser tasks.

Works well with

OpenAI API and Python 3.12.

Similar repositories
  • OpenHands/OpenHands91k stars

    An open-source platform for software development agents that write code and run tests.

  • SWE-agent/SWE-agent21k stars

    An agent framework that turns language models into software engineers to fix bugs in GitHub repositories.

Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
git clone https://github.com/FoundationAgents/OpenManus.git
cd OpenManus
uv venv --python 3.12
source .venv/bin/activate
uv pip install -r requirements.txt

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Assistants & Agents › Autonomous Agents.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.