zot

Yet another coding agent harness, lightweight and written in go.

Runs with mockssource: GitHubhomepageGoMITcommit f2fef94e4d0f

Go, MIT licensed. The project labels itself: agent framework, agent harness, ai agent, cli, coding agent, coding assistant, continuous agents and developer tools.

zot runs, with stand-ins for the services it depends on. An Argusic agent installed it in 7 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

zot 0.0.0 builds from source under a toolchain I installed, prints its version, launches its TUI, and ran a complete streaming agent conversation against my local OpenAI-compatible mock with exit 0, writing a session file; the full test suite passes 16/16 under -race when the container's injected OPENROUTER_API_KEY is unset.

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
$0.69 (measured)
recorded runs
1
last tested
stars
371
forks
50
open issues
2
watchers
2
size
20 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 zot, 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.

  • make test failed: TestOpenRouterServerToolsLivePresetFlash hit real OpenRouter and got 404 preset "flash" not found for this user (container has injected OPENROUTER_API_KEY without that paid server-tools preset)8 minutes
  • make test failed: TestResolveEnvOnlyBedrockDiscoveredWithoutConfig resolved provider openrouter instead of amazon-bedrock (same injected OPENROUTER_API_KEY pre-empts the AWS env fallback in provider scan)6 minutes
  • Go toolchain missing in container (no root to apt-install)2 minutes
Install time
7 minutes
Cold machine to finish
22 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
ZOT_HOME=/tmp/zothome_clean2 ./bin/zot -p "end-to-end check 42" --provider ollama --model qwen3.5:4b --base-url http://127.0.0.1:18080/v1 ; exit 0 and final printed text contained the mock's streamed reply; ./bin/zot --version printed 'zot 0.0.0-20260926112130-f2fef94e4d0f'; OPENROUTER_API_KEY= make test -> 16/16 ok, 0 FAIL; go vet ./... exit 0
Model tokens used
541,279
Exact commit tested
f2fef94e4d0f
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.

Done. Summary of the mission:
**What I did**
- Read `README.md` and `docs/*`; installed a Go 1.25.0 toolchain (no Go was present; no root, so it…
- Build: `make build` → `bin/zot` produced successfully (18 MB); `go build ./...` and `go install .…
- Launched the app: `./bin/zot --version` returned `zot 0.0.0-20260926112130-f2fef94e4d0f`; the TUI…
- End-to-end behavior: stood up a schema-correct Argusic-compatible mock (Ollama wire format, SSE o…
- Tests: initially `make test` (race) failed in 2 tests because this container has a non-empty inje…
  - `TestArgusicServerToolsLivePresetFlash` hits the real Argusic API and got 404 `preset "flash" n…
  - `TestResolveEnvOnlyBedrockDiscoveredWithoutConfig` resolved provider `Argusic` instead of `amaz…
- With `OPENROUTER_API_KEY=` unset, the full race suite `make test` passed: 16/16 packages `ok`; al…
```
```

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

  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, 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.
  • Took 7 minutes to install, slower than the median of the 83 comparable projects Argusic has measured.
  • 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, zot was the 49th 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 mocks92.000.69

Topics (from GitHub)

agent-frameworkagent-harnessai-agentclicoding-agentcoding-assistantcontinuous-agentsdeveloper-toolsdurable-agentsgoterminaltui

Embed the badge

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

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

Questions

Does zot run?
zot runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 7 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test zot?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit f2fef94e4d0f. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test zot?
The run that produced this verdict cost $0.69: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does zot take to install?
7 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 zot need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing zot?
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.
How does zot compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, zot was the 49th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for zot?
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