Tracekit

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

Could not verifysource: GitHubhomepagePythonMITcommit 8dcab687a772

Python, MIT licensed. The project labels itself: agent security, ai agents, ai safety, audit log, audit trail, certificate transparency, claude code and guardrails.

Argusic could not get Tracekit running. An Argusic agent hit no errors on a clean machine with no GPU, and the whole session was recorded.

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 20 of 100 (the mean of this project's run scores).

At a glance

verdict
Could not verify
Argusic Score
20 / 100
cost of the verifying run
$0.09 (measured)
recorded runs
2
last tested
stars
751
forks
131
open issues
127
watchers
3
size
98 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.

Cold machine to finish
36 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
Model tokens used
204,250
Exact commit tested
8dcab687a772
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.

Install time
the run did not report one
How the result was proved
runs before 2026-09-07 did not record the command used to check the result
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
Whether it works at all
this run verified nothing, so this page makes no claim either way

The end of the recording

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

drwxr-xr-x  5 runner runner    186 Nov 18 08:50 scripts
drwxr-xr-x  3 runner runner     32 Nov 18 08:47 sdk
-rw-r--r--  1 runner runner   1480 Nov 18 08:47 server.json
-rw-r--r--  1 runner runner   3007 Nov 18 08:47 skills-lock.json
drwxr-xr-x  8 runner runner   8192 Nov 18 08:49 tests
drwxr-xr-x 21 runner runner   4096 Nov 18 08:49 tracekit
drwxrwxr-x  2 runner runner    162 Nov 18 08:47 tracekit_ai.egg-info
-rw-r--r--  1 runner runner   1900 Nov 18 08:47 tracekit_sdk.py
ERROR: Incomplete response returned, reason: max_output_tokens
ERROR: Incomplete response returned, reason: max_output_tokens
tokens used
204,250

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

  • Nothing broke on the way: zero errors between clone and running.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • An agent with no time limit did not get it running.

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 Runner2/3Did not run20.000.09
Argusic Runner1/3Ran out of time0.000.34

Topics (from GitHub)

agent-securityai-agentsai-safetyaudit-logaudit-trailcertificate-transparencyclaude-codeguardrailslangchainlanggraphllmllm-securitymcpobservabilityopenai-agentsprovenancepythontamper-evidenttransparency-logtypescript

Embed the badge

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

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

Questions

Does Tracekit run?
Argusic could not verify that Tracekit runs. Argusic installed and launched it on a clean machine, hitting 0 errors on the way, and recorded the session.
How did Argusic test Tracekit?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8dcab687a772. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Tracekit?
The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
Does Tracekit need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Tracekit?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for Tracekit?
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