OpenManus
No fortress, purely open ground. OpenManus is Coming.
Runssource: GitHubPythonMITcommit 3309bf4e416f
Python, MIT licensed.
OpenManus runs. An Argusic agent installed it in 3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
OpenManus installs with pip in a venv, all 19 core modules import without errors, 4 pytest tests pass, MCP server registers 3 tools and starts in stdio mode, config loads correctly from toml
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- DaytonaSettings.daytona_api_key had no default, causing ValidationError when [daytona] section missing1 minute
- Install time
- 3 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- python -m pytest tests/tools/test_browser_use_mcp.py -v: 4 passed, 0 failed; MCP server started and registered tools via stdio; python -c 'import app.config, app.llm, app.schema, app.agent.manus, app.mcp.server, ...' verified 19 modules import cleanly
- Model tokens used
- 45,983
- Exact commit tested
- 3309bf4e416f
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
All 19 modules import cleanly. Let me assemble the final ARGUSIC_RESULT. Here's the complete report: **Errors encountered and fixed:** 1. **`DaytonaSettings` missing default** - `config.py` line 109 had `daytona_api_key: str` with no … **Verification:** - All 4 tests in `tests/tools/test_browser_use_mcp.py` pass (4 passed, 0 failed) - All 19 core app modules import successfully - MCP server creates, registers all 3 tools (bash, str_replace_editor, terminate), and runs in stdi… - The Docker-based sandbox tests fail because Docker daemon is not running in this container — this… **What's untested:** - Docker-based sandbox (`tests/sandbox/`) requires a running Docker daemon - Real LLM API calls require valid API keys (ollama mock is configured but no ollama server is runn…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 3 minutes, faster than the median of the 33 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 34 Python projects Argusic has installed and timed, OpenManus was the 14th fastest to reach a running state, and 19 of 34 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 3 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openmanus)Questions
- Does OpenManus run?
- Yes. OpenManus runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test OpenManus?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3309bf4e416f. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test OpenManus?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does OpenManus take to install?
- 3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does OpenManus need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenManus?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does OpenManus compare with the alternatives?
- Of the 34 Python projects Argusic has installed and timed, OpenManus was the 14th fastest to reach a running state, and 19 of 34 reached one at all.
- Where is the evidence for OpenManus?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.