lollms_hub
A proxy server for multiple ollama instances with Key security
Runs with mockssource: GitHubPythonApache-2.0commit eb5a10676d7d
Python, Apache-2.0 licensed. The project labels itself: agent, api gateway, federation, load balancer, ollama, personal, proxy and rate limiting.
lollms_hub runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Installed via venv+pip (exit 0), the hub launched under gunicorn/uvicorn, served /admin/login 200 and the Admin Dashboard after login 200, and proxied chat/generate/embeddings to a local Ollama-format mock with HTTP 200 responses.
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 92 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.
- run.sh hub installer froze waiting on TTY input (read blocks) and ./run.sh exited 126 because it lacked +x; it also tries sudo apt for missing cairo dev headers6 minutes
- A DB-full API key owned by non-admin user 2 defaulted to NoneType user during streaming, crashing the proxy task; gunicorn default (non-setsid) invocations also kept dying ~40s after start in this container5 minutes
- Streaming returned only '{}' until the mock was upgraded to HTTP/1.1 chunked transfer; httpx then delivered chunks and the hub streamed them4 minutes
- Mock Ollama backend was unreachable from the hub because the hub bound its outbound connection to the Docker gateway 127.0.0.11 while my first mock listened only on 127.0.0.13 minutes
- The repo ships only dummy tests (tests/test_dummy.py: 3 assertions) and no test_api/test_core directories despite DEVELOPMENT.md describing them1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 41 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- curl -s -H 'Authorization: Bearer <SECRET_KEY>' -d '{"model":"mock-llama","messages":[{"role":"user","content":"hi"}],"stream":false}' http://127.0.0.1:8080/api/chat returned HTTP 200 with body {"model":"mock-llama","message":{"role":"assistant","content":"Hello from mock-llama"},"done":true,"eval_count":5}; stream:true returned two data: NDJSON chunks; pytest -v exited 0 with 3 passed
- Model tokens used
- 4,156,930
- Exact commit tested
- eb5a10676d7d
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Logged in with `admin`/`changeme` (bootstrap creds from `.env`): POST login → redirected to `/adm…
- Stood up a schema-correct Ollama mock on port 11434 (Ollama /api/tags, /api/chat stream+non-strea…
- End-to-end real proxy calls against that mock: `POST /api/chat` (stream:false) returned `{"model"…
- Verified staying power: the gunicorn master (PID 2637) was still alive 17 minutes after startup, …
- `## Errors encountered`
- `run.sh` interactive wizard froze on the TTY `read` and required an interactive PTY; also `./ru…
- Mock backend was unreachable because the hub connected from Docker network gateway `127.0.0.11`…
- `/api/tags` showed no mock model until the server model refresh ran; it then synced the mock mo…
- A stored-API-key (user_id=2) caused `'NoneType' object has no attribute` as its user relationsh…
- The `chunked` streaming trigger required the mock to use `Transfer-Encoding: chunked` with `HTT…
- Grand of these: each was diagnosed from logs and fixed; notably none blocked the final end-to-e…
**Final proof line (must match `verified_how`)**: `curl -s -H "Authorization: Bearer <SECRET_KEY>" …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
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, 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 140 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 141 agent projects Argusic has installed and timed, lollms_hub was the 96th fastest to reach a running state, and 94 of 141 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 | 92.00 | 0.08 |
Topics (from GitHub)
agentapi-gatewayfederationload-balancerollamapersonalproxyrate-limitingsecurityuser-managementworkflow
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/lollms-hub)Questions
- Does lollms_hub run?
- lollms_hub runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test lollms_hub?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit eb5a10676d7d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test lollms_hub?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does lollms_hub 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 lollms_hub need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing lollms_hub?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does lollms_hub compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, lollms_hub was the 96th fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for lollms_hub?
- 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.