graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Runssource: GitHubhomepagePythonApache-2.0commit 33362d969292
Python, Apache-2.0 licensed. The project labels itself: ai agents, antigravity, ast, claude code, code analysis, code search, codex and cursor.
graphify runs. An Argusic agent installed it in 23 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
graphify 0.9.53 is installed via uv, all 5299 tests pass, and graph extraction+clustering works end-to-end on the repo codebase with --code-only.
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 66.7 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.
- tree-sitter-dm build failure: missing Python.h (python3.12-dev headers not installed in container)5 minutes
- Install time
- 23 minutes
- Cold machine to finish
- 36 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- Exact commit tested
- 33362d969292
- Container image
- sha256:33ceb71981b6
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
- Model tokens used
- not recorded for this run
- 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 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.
7. `uv run pytest tests/ -q --tb=short` - 3min 4sec, all passed
8. End-to-end `graphify . --code-only` - worked
9. `graphify cluster-only .` - worked
Total elapsed is about 25-30 minutes of work, but the actual "install" (downloading, waiting for bu…
exec
/bin/sh -lc 'export PATH="$HOME/.local/bin:$HOME/.local/share/uv/bin:$PATH" && echo "ARGUSIC_RESULT…
succeeded in 0ms:
ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 23, "error…
ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 23, "error…
tokens used
270,025
ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 23, "error…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 1 error 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 23 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
Of the 12 ai-agents projects Argusic has installed and timed, graphify was the 11th fastest to reach a running state, and 8 of 12 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
Topics (from GitHub)
ai-agentsantigravityastclaude-codecode-analysiscode-searchcodexcursordeveloper-toolsgeminigraphragknowledge-graphleidenllmmcpopenclawragskillstree-sitter
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/graphify)Questions
- Does graphify run?
- Yes. graphify runs. Argusic installed and launched it on a clean machine in 23 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test graphify?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 33362d969292. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test graphify?
- The run that produced this verdict cost $0.37: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does graphify take to install?
- 23 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 graphify need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing graphify?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does graphify compare with the alternatives?
- Of the 12 ai-agents projects Argusic has installed and timed, graphify was the 11th fastest to reach a running state, and 8 of 12 reached one at all.
- Where is the evidence for graphify?
- 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.