private-gpt
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Runssource: GitHubhomepagePythonApache-2.0commit 065814007608
Python, Apache-2.0 licensed. The project labels itself: ai, ai tools and on premise.
private-gpt runs. An Argusic agent installed it in 10 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
PrivateGPT server launches with mock LLM/embedding models on port 18080, responds to /v1/models, /health, and /v1/messages API endpoints. Test suite: 2079 passed, 1 failed (pre-existing), 4 errors (transient DB state).
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.
- Missing libmagic system library (python-magic dependency)5 minutes
- Missing celery, pandas, anthropic extras2 minutes
- settings-mock.yaml had no model definitions, server could not register models2 minutes
- Python 3.11 required but 3.12 present in container1 minute
- Mock profile not loaded from APP_ENV env var - profiles use PGPT_PROFILES
- Install time
- 10 minutes
- Cold machine to finish
- 51 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- Model tokens used
- 477,726
- Exact commit tested
- 065814007608
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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.
'test_depth': 'tier1_real',
'notes': 'Pre-existing test bug in tests/components/multimodality/test_describe_audio.py::test_…
'final_state': 'PrivateGPT server launches with mock LLM/embedding models on port 18080, respon…
}
print(json.dumps(result))
\"" in /work/repo
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 10, "errors": [{"msg": "Py…
2026-09-05T20:54:38.062617Z ERROR codex_core::session: failed to record rollout items: thread 01a07…
2026-09-05T20:54:38.062659Z ERROR codex_core::session: failed to record rollout items: thread 01a07…
tokens used
477,726Replay 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 5 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 3 times, so the result is not a one-off.
What did not, or is not known
- Took 10 minutes to install, slower than the median of the 36 comparable projects Argusic has measured.
Of the 37 ai projects Argusic has installed and timed, private-gpt was the 27th fastest to reach a running state, and 30 of 37 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 10 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs | 100.00 | 0.20 | |
| Argusic Runner | 2/3 | Ran out of time | 0.00 | 0.20 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.22 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/private-gpt)Questions
- Does private-gpt run?
- Yes. private-gpt runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test private-gpt?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 065814007608. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test private-gpt?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does private-gpt take to install?
- 10 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 private-gpt need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing private-gpt?
- 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 private-gpt compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, private-gpt was the 27th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for private-gpt?
- All 3 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.