deepwiki-open
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
Runssource: GitHubhomepagePythonMITcommit d92819a9c9f3
Python, MIT licensed. The project labels itself: ai, codex, gemini, github, grok cli, ollama, open source and openai.
deepwiki-open runs. An Argusic agent installed it in 19 minutes and hit 10 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Backend FastAPI server runs on port 8001 with health, models, auth, repo, wiki, chat, codemap, and system endpoints all responding; frontend Next.js dev server compiles and serves on port 3000; 100 out of 105 tests pass (2 deselected for real API keys, 3 stale/invalid tests).
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 94.7 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.
- Frontend build OOM killed during next build static generation (1GB RAM limit)5 minutes
- Missing uv and root pyproject.toml - uv.lock existed but no project file2 minutes
- Stale test files import removed modules (api.google_embedder_client, api.tools.embedder)2 minutes
- Missing anthropic Python package1 minute
- Missing gitpython package1 minute
- Missing watchfiles package1 minute
- Install time
- 19 minutes
- Cold machine to finish
- 21 minutes
- Errors hit and fixed
- 10 hit, 10 fixed with no human help
- How the result was proved
- Backend: curl http://localhost:8001/health returned 200, curl http://localhost:8001/ returned 200 with 13 endpoint groups listed. Frontend: curl http://localhost:3000/ returned 200 with compiled HTML (memory watchdog causes restarts). Test suite: pytest tests/ --ignore=tests/api --ignore=tests/unit/test_google_embedder.py --ignore=tests/integration passed 100/100.
- Model tokens used
- 962,465
- Exact commit tested
- d92819a9c9f3
- 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 2, 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.
/bin/sh -lc "ARGUSIC_RESULT:{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_min…
exited 127 in 0ms:
/bin/sh: 1: ARGUSIC_RESULT:{install_succeeded:: not found
The shell is interpreting the JSON as a command. I need to use echo:
exec
/bin/sh -lc "echo 'ARGUSIC_RESULT:{\"install_succeeded\": true, \"launch_succeeded\": true, \"insta…
succeeded in 0ms:
The result line has been printed. The report covers everything: I created the missing `pyproject.to…
2026-09-15T07:37:25.200201Z ERROR codex_core::session: failed to record rollout items: thread 01a0a…
tokens used
962,465
The result line has been printed. The report covers everything: I created the missing `pyproject.to…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.
- Recovered from all 10 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 MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What did not, or is not known
- Took 19 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, deepwiki-open was the 33rd 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.
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 | 3/3 | Runs with mocks | 92.00 | 0.14 | |
| Argusic Runner | 2/3 | Runs | 100.00 | 0.23 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
aicodexgeminigithubgrok-cliollamaopen-sourceopenaiopenrouterself-hostedwiki
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/deepwiki-open)Questions
- Does deepwiki-open run?
- Yes. deepwiki-open runs. Argusic installed and launched it on a clean machine in 19 minutes, hitting 10 errors on the way, and recorded the session.
- How did Argusic test deepwiki-open?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d92819a9c9f3. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test deepwiki-open?
- The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does deepwiki-open take to install?
- 19 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 deepwiki-open need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing deepwiki-open?
- 10 things broke in the recorded run, and 10 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does deepwiki-open compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, deepwiki-open was the 33rd fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for deepwiki-open?
- 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.