matrixhub
An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.
Runssource: GitHubhomepageGoApache-2.0commit d540d926a72a
Go, Apache-2.0 licensed. The project labels itself: artificial intelligence, dynamo, huggingface, kubernetes, llm, llm inference, model registry and self hosted.
matrixhub runs. An Argusic agent installed it in 10.5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
MatrixHub Go backend compiles and runs with SQLite on port 3001, health/endpoint returns 200, login (admin/changeme) authenticates and returns a session cookie, authenticated user CRUD works, built React UI assets are served correctly, and make test.unit passes all 17 test packages (excluding the known-broken hf handler package)
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
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.
- pnpm not installed2 minutes
- Go compiler not installed1.5 minutes
- Node.js 18.19.1 too old for Vite 7 (requires 20+)1.5 minutes
- internal/apiserver/handler/hf tests fail (EOF / connection refused)
- Install time
- 11 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- make test.unit exited 0 (17 packages passed); curl http://127.0.0.1:3001/healthz returned 200 OK; curl -X POST /api/v1alpha1/login returned 200 with Set-Cookie session token; curl GET /api/v1alpha1/users returned 200 with admin user JSON; curl GET /assets/index-*.js returned 200; pnpm build completed
- Model tokens used
- 67,442
- Exact commit tested
- d540d926a72a
- 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.
**Verification:** - `go build ./cmd/matrixhub` — success, produced 69MB binary - `./matrixhub --help` — prints usage with apiserver, completion, help commands - `./matrixhub apiserver -c config/config-sqlite.yaml` — starts on port 3001, SQLite migrations run - `curl localhost:3001/healthz` — returns `200 OK` - `POST /api/v1alpha1/login` — returns `200` with session cookie - `GET /api/v1alpha1/users` (authenticated) — returns `200` with admin user - `POST /api/v1alpha1/users` (authenticated) — returns `200`, creates test user - `GET /assets/index-*.js` — returns `200` (serving built UI) - `pnpm build` — UI build succeeds - `make test.unit` — all 17 packages pass (excluding known-broken `hf` handler) - `make test.sqlite` — all 3 SQLite packages pass
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 10.5 minutes.
- Recovered from all 4 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 it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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
Topics (from GitHub)
artificial-intelligencedynamohuggingfacekubernetesllmllm-inferencemodel-registryself-hostedsglangvllm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/matrixhub)Questions
- Does matrixhub run?
- Yes. matrixhub runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test matrixhub?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d540d926a72a. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test matrixhub?
- 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 matrixhub take to install?
- 10.5 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 matrixhub need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing matrixhub?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for matrixhub?
- 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.