OpenGateLLM
An open-source, unified interface for running and managing self-hosted LLMs.
Runs with mockssource: GitHubPythonMITcommit 4faf1f3b119c
Python, MIT licensed. The project labels itself: api, llm and self hosted.
OpenGateLLM runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 7 errors on a clean machine with no GPU, and the whole session was recorded.
After fixing the Alembic downgrade revisions, OpenGateLLM installs, its unit (580) and integration (747 pass, 1 skipped) suites pass against real local Postgres 16.2 and Redis 6.2.14, and uvicorn serves /health 200, bootstraps the admin, and completes a real chat request end to end through a local 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 89.1 of 100 (the mean of this project's run scores).
At a glance
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- alembic downgrade failed: Cannot emit DROP CONSTRAINT ... has no name in revisions 4cbcc969c660, 9fd5b6491d48, 9ba1f6a21f20, 2d2550e0771d, c1e54102255e, 8c5ae2a3d4d0, e78eaed1bcb214 minutes
- upgrade head after a full downgrade base still fails: type "modeltype" already exists12 minutes
- docker/Postgres/Redis absent in container; background processes spawned by exec_command were reaped after the call (mock provider and a Redis helper died)8 minutes
- revision 9ba1f6a21f20 downgrade failed: relation "model" does not exist (model_client created before model)5 minutes
- full downgrade leaves httpmethod/limittype/permissiontype enum types behind, so a later upgrade fails with duplicate type5 minutes
- alembic downgrade base failed: type "collectionvisibility" already exists (enum type never dropped with its table)4 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 30 minutes
- Errors hit and fixed
- 7 hit, 6 fixed with no human help
- How the result was proved
- pip install '.[api,playground,dev,test]' exited 0; pytest api/tests/unit exited 0 (580 passed); pytest api/tests/integration exited 0 (747 passed, 1 skipped); alembic upgrade head and downgrade base each exited 0 on fresh DBs; uvicorn api.main:app served /health 200 {"status":"ok"}, /docs 200, login 200, real chat completion 200 with content 'echo:hello' (alias and stream), usage list 200, revoked key 401, unauthenticated chat 401
- Model tokens used
- 1,222,638
- Exact commit tested
- 4faf1f3b119c
- 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.
- `POST /v1/auth/login` with the documented `admin`/`changeme` returned 200 and a key. `/v1/me`, `/… - Created a router and a provider pointing at a local Argusic-compatible mock (HTTP 201 each), then… - Key lifecycle: create, rename, revoke returned 200/200/200, and the revoked key's next request re… **Fixed errors (all in Alembic revisions)** - `alembic downgrade base` failed with `type "collectionvisibility" already exists`. The type was n… - Several revisions emitted unnamed constraints (`Cannot emit DROP CONSTRAINT ... has no name`) in … - Downgrade of `9ba1f6a21f20` added NOT NULL columns to tables holding rows and failed with not-nul… - Downgrade of `9ba1f6a21f20` recreated `model_client` before its referenced `model` table; reorder… - A full downgrade left `httpmethod`, `limittype`, `permissiontype`, and `collectionvisibility` beh… - After these fixes, a fresh `upgrade head` → `downgrade base` both exit 0, and the app starts on a… **Still broken:** running `upgrade head` *again* after a full `downgrade base` fails with `type "mo… **Unavailable here:** Docker and `make quickstart`/`make dev` (Docker isn't installed; I didn't run…
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
- 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 12 minutes to install, slower than the median of the 61 comparable projects Argusic has measured.
- Hit 7 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 62 api projects Argusic has installed and timed, OpenGateLLM was the 48th fastest to reach a running state, and 39 of 62 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 89.14 | 0.63 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opengatellm)Questions
- Does OpenGateLLM run?
- OpenGateLLM runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test OpenGateLLM?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4faf1f3b119c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test OpenGateLLM?
- The run that produced this verdict cost $0.63: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does OpenGateLLM take to install?
- 12 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 OpenGateLLM need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenGateLLM?
- 7 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does OpenGateLLM compare with the alternatives?
- Of the 62 api projects Argusic has installed and timed, OpenGateLLM was the 48th fastest to reach a running state, and 39 of 62 reached one at all.
- Where is the evidence for OpenGateLLM?
- 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.