OpenManus FoundationAgents/OpenManus

Terminal-based general agent from the MetaGPT team that plans tasks, browses the web and runs tools with your own model keys or a local Ollama model.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

OpenManus at a glance

Checked 16 Oct 2026

OpenManus (58.7k stars, MIT) is a Python agent you run from the terminal: type a task and it plans, searches, browses (via a bundled Browser Use MCP server and your local Chrome) and runs code and file tools. There is an optional data-analysis agent and an "unstable" multi-agent mode. It needs an LLM API key (OpenAI, Anthropic, Gemini, Azure and others) or a local Ollama model. No web UI, no slides or site builder, no scheduler. Last tagged release is v0.3.0 (April 2025); commits continued into August 2026.

Cite this pageRepoQuarry. “OpenManus.” Checked 16 Oct 2026. https://repoquarry.dev/projects/openmanus

How much of Manus does it replace?

2 of 6 jobs. Terminal agent for browsing and code/file tasks; no hosted app, slides, websites, schedules or app connectors.

Autonomous web browsing Partial replacement

Deep research reports Not covered

File and code tasks in a sandbox Partial replacement

Slides generated from a prompt Not covered

Scheduled agent tasks Not covered

Connectors to your apps Not covered

For deep research reports, slides generated from a prompt, scheduled agent tasks, connectors to your apps, see other Manus alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, Python CLI on your own machine; Docker sandbox optional Then input your idea via terminal! github.com · OpenManus#quick-start ↗ today

Code licence MIT github.com · LICENSE ↗ today

Model weights licence No separate model weights; you bring your own model API key or a local Ollama model OpenManus requires configuration for the LLM APIs it uses. github.com · OpenManus#configuration ↗ today

Commercial use Yes, MIT code; model terms depend on the provider or local model you choose github.com · LICENSE ↗ today

Paid services needed? An LLM API key is needed unless you run a local model through Ollama; Browser Use Cloud and Daytona sandboxes are optional api_type = 'ollama' github.com · config.example.toml ↗ today

Hardware Not documented; needs Python 3.12 and Chrome or Chromium; a local model needs your own GPU Know the answer? —

Operating systems Windows, macOS and Linux (install steps cover each) # Or on Windows: github.com · OpenManus#installation ↗ today

Setup effort Medium; clone, install Python deps with uv or conda, edit config.toml with model keys Method 2 (using uv) is recommended for faster installation and better dependency management. github.com · OpenManus#installation ↗ today