agav

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Runs with mockssource: GitHubTypeScriptApache-2.0commit 989687b1ac50

TypeScript, Apache-2.0 licensed. The project labels itself: ai agent, ai coding assistant, anthropic, claude code, cli, codex, coding agent and command line.

agav runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Agav v0.2.8 builds and runs successfully: CLI displays full help with all subcommands (run, agents, skills, sessions, mcp, workflows, job), version command returns '0.2.8', non-interactive mode processes prompts correctly using its built-in tools (read_file, list_directory, etc.), and 6615/6776 tests pass with all 55 failures caused by test-timeout sensitivity rather than code defects.

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

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.13 (measured)
recorded runs
1
last tested
stars
201
forks
0
open issues
0
watchers
0
created
-
last push
-

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.

Time lost to each failure while testing agav, 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.

  • Test suite: 55 tests failed out of 6776 (0.8%) in full parallel run — all are timeout/race-condition failures from resource contention10 minutes
  • Background-jobs coordinator tests 2/2 fail individually due to beforeEach hook timeout (10s) on linux — createCoordinator hangs5 minutes
  • Node.js v18.19.1 present but project requires >=22.13.00.5 minutes
  • pnpm not available with stock Node 22 (corepack key verification failed)0.3 minutes
Install time
under a minute
Cold machine to finish
11 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
node build/cli.js --version returned '0.2.8'; node build/cli.js -P 'What files are in the current directory?' answered correctly with interactive agent; pnpm test ran 6776 tests with 6615 passed, 106 skipped, 55 failed (all timeout-related, pass in isolation)
Model tokens used
223,365
Exact commit tested
989687b1ac50
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
Behaviour against real services
this run was verified against stand-in services only

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.

        }),
      ]);
      expect(result).toBeNull();
      await vi.waitFor(() => expect(() => process.kill(pid!, 0)).toThrow(), { timeout: 1000 });
    } finally {
      controller.abort();
I can see one of the timeout issues: `vi.waitFor` with a 2000ms timeout to read a file that needs t…
Here's my summary of findings. Let me compose the result.
tokens used
223,365
I can see one of the timeout issues: `vi.waitFor` with a 2000ms timeout to read a file that needs t…
Here's my summary of findings. Let me compose the 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

  • Installed in 0.5 minutes, faster than the median of the 83 comparable projects Argusic has measured.
  • Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 84 ai-agent projects Argusic has installed and timed, agav was the 10th fastest to reach a running state, and 58 of 84 reached one at all.

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 Runner1/3Runs with mocks92.000.13

Topics (from GitHub)

ai-agentai-coding-assistantanthropicclaude-codeclicodexcoding-agentcommand-linedevtoolsharnesshermesllmmcpollamaopenaiproductivityshellterminaltuitypescript

Embed the badge

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

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

Questions

Does agav run?
agav runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test agav?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 989687b1ac50. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test agav?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agav take to install?
0.5 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 agav need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agav?
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 agav compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, agav was the 10th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for agav?
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.

Discussion