otari

Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

Runssource: GitHubhomepagePythonApache-2.0commit 1fbdc65e2d9e

Python, Apache-2.0 licensed. The project labels itself: ai, ai gateway, anthropic, api key management, budgets, cost tracking, gateway and litellm alternative.

otari runs. An Argusic agent installed it in 0.3 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The Otari LLM gateway installed from source with uv, boots as a standalone server on port 8000 serving the management API, bootstrap, health, docs, OpenAPI spec, and tutorial root page, and the OSS edition smoke test exercises all key lifecycle stages (health, bootstrap, user/keys, providers, routing, completions, usage, mail) against a mock provider.

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

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.05 (measured)
recorded runs
2
last tested
stars
960
forks
141
open issues
260
watchers
8
size
219 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 otari, 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 not installed on the system0.1 minutes
  • Python 3.13 not available on system (only 3.12)0 minutes
Install time
under a minute
Cold machine to finish
20 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
scripts/oss_edition_smoke.py passed all 10 stages. Server verification via Python urllib: /api/v1/bootstrap -> 200 (deployment_type=standalone), / -> 200 (Otari tutorial HTML), /api/v1/health -> 200, /api/v1/health/liveness -> 200, /api/v1/health/readiness -> 200, /api/v1/docs -> 200, /api/v1/openapi.json -> 200 (193 paths), /api/v1/chat/completions (no auth) -> 401. Unit tests: tests/unit/agent_gates/ 254 passed, test_gateway_cli.py 11 passed, test_gateway_bootstrap.py 5 passed, test_gateway_root_page.py 17 passed, test_gateway_metrics.py 13 passed, test_guardrails_generate_cli.py 39 passed.
Model tokens used
210,535
Exact commit tested
1fbdc65e2d9e
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

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.

4. /api/v1/health/readiness: 200
5. Chat (no auth): 401 (expected)
6. OpenAPI spec: 200, paths=193
Server stopped cleanly
All tests passed and the OSS smoke test succeeded. Let me compile the final result
exec
/bin/sh -lc 'cd /work/repo && kill $(pgrep -f "otari") 2>/dev/null; echo "cleanup done"' in /work/r…
 exited 143 in 0ms:
2026-10-17T19:36:23.494218Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
2026-10-17T19:36:23.494258Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
tokens used
210,535

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 0.3 minutes, faster than the median of the 236 comparable projects Argusic has measured.
  • Recovered from all 2 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.

Of the 237 ai projects Argusic has installed and timed, otari was the 9th fastest to reach a running state, and 168 of 237 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 0.3 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.16
Argusic Runner1/3Runs100.000.05

Topics (from GitHub)

aiai-gatewayanthropicapi-key-managementbudgetscost-trackinggatewaylitellm-alternativellmllm-gatewayllm-proxyllm-routingllmopsmulti-provideropen-sourceopenaiopenai-compatiblepythonself-hosted

Embed the badge

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

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

Questions

Does otari run?
Yes. otari runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test otari?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1fbdc65e2d9e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test otari?
The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does otari take to install?
0.3 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 otari need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing otari?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does otari compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, otari was the 9th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for otari?
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