CodeAF

Open-Source Software factory for Open Models

Runssource: GitHubGoApache-2.0commit 794b49a57894

Go, Apache-2.0 licensed. The project labels itself: agent fleet, agent harness, agentfield, agentic coding, ai, ai coding, ai coding agents and cli agent.

CodeAF runs. An Argusic agent installed it in 26.8 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

codeaf v0.8.0 release binary installed, builds from source with SHELL=/bin/bash, all 31 law/test-quick packages pass, real model call to DeepSeek returns correct output

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 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.23 (measured)
recorded runs
2
last tested
stars
825
forks
96
open issues
331
watchers
3
size
413 MB
created
last push

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.

Time lost to each failure while testing CodeAF, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • go toolchain not installed: Go 1.26.5+ required but no go binary on PATH1.5 minutes
  • make build fails with '/bin/sh: 1: Bad substitution' on plandb CGO link step1 minute
  • make size and test targets print '/bin/sh: 1: Bad substitution' at end even after SHELL fix (from CGO subprocess invoking /bin/sh directly)
Install time
27 minutes
Cold machine to finish
31 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
codeaf --version returned 'codeaf v0.8.0 built 2026-10-14 14:18'; codeaf doctor showed key set and store; codeaf exec 'say hello' on deepseek-chat returned 'Hello! I'm here and ready...'; codeaf chat --once 'Say hello in one word only.' returned 'hello'; make test-quick passed all 31 packages; make test-laws passed all 30 law packages; make build with SHELL=/bin/bash produced working bin/codeaf (64MB) and bin/plandb (6.6MB); codeaf manual listed 100+ pages
Model tokens used
174,332
Exact commit tested
794b49a57894
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

---restored---
---final git state---
?? plandb
2026-10-20T04:56:18.962692Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce…
exec
/bin/sh -lc 'cd /work/repo && mv plandb /tmp/ 2>/dev/null; echo "cleaned"' in /work/repo
 succeeded in 0ms:
cleaned
Here is the comprehensive test report.
tokens used
174,332
Here is the comprehensive test report.

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 26.8 minutes.
  • Recovered from all 3 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 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.05
Argusic Runner1/3Runs100.000.23

Topics (from GitHub)

agent-fleetagent-harnessagentfieldagentic-codingaiai-codingai-coding-agentscli-agentcoding-agentcoding-agentscoding-assistantcoding-harnessdeveloper-toolsharness-engineeringllmopen-modelsopen-source-modelsopenai-compatiblesoftware-factoryterminal-agent

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/CodeAF.svg)](https://argusic.com/subject/codeaf)

Questions

Does CodeAF run?
Yes. CodeAF runs. Argusic installed and launched it on a clean machine in 27 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test CodeAF?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 794b49a57894. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test CodeAF?
The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does CodeAF take to install?
26.8 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 CodeAF need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing CodeAF?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for CodeAF?
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.

Discussion