experiential

Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.

Runssource: GitHubhomepagePythonApache-2.0commit 1253c82fe479

Python, Apache-2.0 licensed.

experiential runs. An Argusic agent installed it in 45 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The experiential project installs cleanly under uv on Python 3.13 with the native Rust gateway extension built from source; all quality gates pass, 8396 of 8397 container-runnable tests pass, and the initialized loopback gateway serves health, models, non-stream and stream chat completions, and usage accounting against a local mock OpenAI-compatible upstream.

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

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.47 (measured)
recorded runs
2
last tested
stars
17,232
forks
311
open issues
169
watchers
20
size
107 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 experiential, 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.

  • uv sync on system Python 3.12 left venv incomplete; repo gates need 3.1315 minutes
  • TERM unset made ~77 rich picker PTY tests fail (non-interactive fallback)10 minutes
  • rustc/cargo not installed; native gateway crate requires them6 minutes
  • test_prepared_snapshot_rejects_path_and_content_races[rewrite] fails on overlayfs ctime semantics in this container5 minutes
  • macOS-only capture lock test fails on Linux because pwd exists and ~/Library 0755 trips fail-closed ancestor check3 minutes
  • uv not installed in container2 minutes
Install time
45 minutes
Cold machine to finish
74 minutes
Errors hit and fixed
7 hit, 7 fixed with no human help
How the result was proved
uv sync --extra dev exited 0; ruff check/format --check and ty check all reported All checks passed; .venv/bin/pytest -q = 8396 passed, 1 env-expected failure, 60 skipped; curl -s http://127.0.0.1:8000/health/ready returned 200 with body {"status":"ready"}; curl POST /v1/chat/completions with exp_vk_ key returned HTTP 200 with id chatcmpl_9feeeb47b3a8e4b60f01741637ca166a and content "Hello" via mock upstream; SSE stream returned chunks ending data: [DONE]
Model tokens used
1,697,702
Exact commit tested
1253c82fe479
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.

- Full pytest: **8396 passed, 1 failed (capture-lock env test), 1 error (flaky terminal-tasks test …
- Live gateway on loopback:
  - `exp config gateway init/provider add openai-compatible/alias create opus-5/identity create/gra…
  - `exp --root /tmp/exp-root-test --non-interactive --json --check` -> `{"status":"ready",...}` ex…
  - `exp --root ... --port 8000` launched; process stayed up (PID constant across probes).
  - `GET /health/ready` → 200 `{"status":"ready"}`.
  - `GET /v1/models` with issued `exp_vk_…` key → 200 listing the granted `opus-5` alias.
  - `POST /v1/chat/completions` (Bearer key, `{"model":"opus-5",...}`) → 200 real completion `"id":…
  - Streaming → 200 SSE `data:` chunks ending `data: [DONE]`.
  - `GET /usage` → 200 HTML accounting page (per-identity request/attempt/token tables); SQLite `ga…
  - 502s observed only when the background mock upstream had died between exec sessions (proven by …
**Honest scoping:** I did not run `exp build`/`exp optimize`/SFT (require real hosted provider keys…

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.
  • Recovered from all 7 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 did not, or is not known

  • Took 45 minutes to install, slower than the median of the 46 comparable projects Argusic has measured.

Of the 47 Python projects Argusic has installed and timed, experiential was the 47th fastest to reach a running state, and 32 of 47 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.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.47
Argusic Runner1/3Runs100.000.32

Embed the badge

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

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

Questions

Does experiential run?
Yes. experiential runs. Argusic installed and launched it on a clean machine in 45 minutes, hitting 7 errors on the way, and recorded the session.
How did Argusic test experiential?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1253c82fe479. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test experiential?
The run that produced this verdict cost $0.47: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does experiential take to install?
45 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 experiential need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing experiential?
7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does experiential compare with the alternatives?
Of the 47 Python projects Argusic has installed and timed, experiential was the 47th fastest to reach a running state, and 32 of 47 reached one at all.
Where is the evidence for experiential?
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