Yes. Tracely-ai runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.

How did Argusic test Tracely-ai?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit f332bc865d60. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test Tracely-ai?

The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does Tracely-ai take to install?

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 Tracely-ai need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing Tracely-ai?

2 things broke in the recorded run. Each one, and the time it cost, is listed on this page.

Where is the evidence for Tracely-ai?

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.

Tracely-ai

Trace-native CI/CD for AI agents, production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.

Runssource: GitHub homepagePythonMITcommit f332bc865d60

Python, MIT licensed. The project labels itself: agent, agent observability, ai agents, ci cd, clickhouse, evals, evaluation and llm.

Tracely-ai runs. An Argusic agent installed it in 5 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.

Python backend and SDK install, import, and all 1174 pytest tests pass on Python 3.12.3. Frontend installs via pnpm with no errors and next build compiles successfully but OOMs during static page generation (container memory limit). vitest tests require Node 22+ ([email protected] and [email protected]) while this container has Node 18.19.1 - CI uses Node 22. CLI tool tracely --help works.
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 80 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 80 / 100
cost of the verifying run: $0.24 (measured)
recorded runs: 1
last tested: 2026-10-07
stars: 1,501
forks: 170
open issues: 13
watchers: 6
size: 24 MB
created: 2026-06-03
last push: 2026-10-06

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-07. 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 Tracely-ai, 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.

frontend vitest tests fail on Node 18 - jsdom@30 depends on [email protected] (engines: ^22.14.0) and [email protected] (engines: >=22.19.0), container has Node 18.19.115 minutes
pnpm build (next build) OOM killed during static page generation after successful compilation5 minutes

Install time: 5 minutes
Cold machine to finish: 43 minutes
Errors hit and fixed: 2 hit, 0 fixed with no human help
How the result was proved: pytest backend/tests sdk/tests: 1174 passed, 34 skipped, 0 failed; tracely --help returned usage; uv run uvicorn --help succeeded; next build compiled successfully before OOM
Model tokens used: 667,905
Exact commit tested: f332bc865d60
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.

 succeeded in 0ms:
Restored @exodus/bytes package.json to original-like state
Removed encoding-lite.cjs
Removed encoding.cjs
Removed whatwg.cjs
Removed utf16.cjs
Removed utf8.cjs
Restored encoding-lite.js from .esm backup
Now let me do my final report. All patches are reverted and the repo is back to its original state.
tokens used
667,905
Now let me do my final report. All patches are reverted and the repo is back to its original state.

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 5 minutes, faster than the median of the 75 comparable projects Argusic has measured.
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

Hit 2 errors during setup, 2 of which were not solved.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 76 agent projects Argusic has installed and timed, Tracely-ai was the 29th fastest to reach a running state, and 52 of 76 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 5 minutes after the clone.

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 by	attempt	outcome	score	cost USD	when
Argusic Runner	1/3	Runs	80.00	0.24	2026-10-07 15:39 UTC

Topics (from GitHub)

agent agent-observability ai-agents ci-cd clickhouse evals evaluation llm llm-as-judge llm-evaluation llm-observability llm-ops llmops mcp monitoring opentelemetry python self-hosted tracing

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/Tracely-ai.svg)](https://argusic.com/subject/tracely-ai)

Questions

Does Tracely-ai run?: Yes. Tracely-ai runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test Tracely-ai?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit f332bc865d60. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test Tracely-ai?: The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Tracely-ai take to install?: 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 Tracely-ai need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Tracely-ai?: 2 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
How does Tracely-ai compare with the alternatives?: Of the 76 agent projects Argusic has installed and timed, Tracely-ai was the 29th fastest to reach a running state, and 52 of 76 reached one at all.
Where is the evidence for Tracely-ai?: 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.