openfang
Open-source Agent Operating System
Runssource: GitHubhomepageRustApache-2.0commit acf2587e46be
Rust, Apache-2.0 licensed. The project labels itself: agent framework, ai agents, llm, mcp, open source, openclaw, operating system and rust.
openfang runs. An Argusic agent installed it in 12.5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
OpenFang 0.6.9 compiles, passes 2699 tests, and the daemon starts successfully, booting 30 agents and serving the API on port 4200 with a health endpoint returning HTTP 200.
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, refreshed . 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.
- Missing glib-2.0.pc (libglib2.0-dev) for gtk-sys/glib-sys system deps5 minutes
- openfang-desktop requires full GTK/WebKit stack which is not installable without root2 minutes
- Rust toolchain missing1.5 minutes
- 2 kernel tests fail when OPENROUTER_API_KEY is set in environment (env-poisoning, not code bugs)1 minute
- Install time
- 13 minutes
- Cold machine to finish
- 28 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:4200/api/health returned 200, body '{"status":"ok","version":"0.6.9"}'; cargo test --workspace --exclude openfang-desktop --exclude xtask exited 0 with 2699 passed 0 failed; openfang --version returned 'openfang 0.6.9'
- Model tokens used
- 108,579
- Exact commit tested
- acf2587e46be
- 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.
f = int(pp[i-1])
total_f += f
if f > 0:
print('FAIL:', line.strip())
print(f'Total passed: {total_p}, failed: {total_f}')
\"" in /work/repo
succeeded in 0ms:
Total passed: 2699, failed: 0
All 2699 tests pass with a clean environment, 0 failures. Now let me compose the final JSON result.
tokens used
108,579
All 2699 tests pass with a clean environment, 0 failures. Now let me compose the final JSON result.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.
- Recovered from all 4 errors 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 12.5 minutes to install, slower than the median of the 62 comparable projects Argusic has measured.
Of the 63 agent-framework projects Argusic has installed and timed, openfang was the 48th fastest to reach a running state, and 50 of 63 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.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-frameworkai-agentsllmmcpopen-sourceopenclawoperating-systemrust
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openfang)Questions
- Does openfang run?
- Yes. openfang runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test openfang?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit acf2587e46be. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test openfang?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does openfang take to install?
- 12.5 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 openfang need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing openfang?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does openfang compare with the alternatives?
- Of the 63 agent-framework projects Argusic has installed and timed, openfang was the 48th fastest to reach a running state, and 50 of 63 reached one at all.
- Where is the evidence for openfang?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.