codegraph
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent, fewer tokens, fewer tool calls, 100% local
Runssource: GitHubhomepageTypeScriptMITcommit 6560052a6f85
TypeScript, MIT licensed.
codegraph runs. An Argusic agent installed it in 10.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CodeGraph v1.6.2 builds from source, passes 5702/5975 tests, indexes source into SQLite knowledge graphs, and serves MCP tools over stdin/stdout with correct protocol handshake
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.
- System Node.js v18.19.1 too old (requires >=20); install script bundled binary works anyway but source build needs >=22.54 minutes
- bundle-launcher.test.ts fails because zip utility is not installed (tests call `zip` to validate release archives)
- Install time
- 11 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test exited 0: 5702 passed, 2 failed (only zip-missing failures in bundle-launcher.test.ts), 271 skipped; codegraph init -y on a test project indexed 6 TS files into 93 nodes/344 edges in 342ms; codegraph query and node returned correct symbol data; codegraph serve --mcp responded to JSON-RPC initialize + tools/list with correct protocol handshake and tool schemas
- Model tokens used
- 45,103
- Exact commit tested
- 6560052a6f85
- 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.
NOW_SEC="'$(date +%s) echo "Start seconds: $START_SEC" echo "Now seconds: $NOW_SEC" echo "Elapsed minutes: $(( (NOW_SEC - START_SEC) / 60 )).$(( (NOW_SEC - START_SEC) % 60 / 6 ))"' in… succeeded in 0ms: Start seconds: 1793463380 Now seconds: 1793464010 Elapsed minutes: 10.5 Now I have all the data. Let me compile the final assessment. tokens used 45,103 Now I have all the data. Let me compile the final assessment.
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 2 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 2 times, so the result is not a one-off.
What did not, or is not known
- Took 10.5 minutes to install, slower than the median of the 6 comparable projects Argusic has measured.
Of the 7 C projects Argusic has installed and timed, codegraph was the 5th fastest to reach a running state, and 5 of 7 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.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codegraph)Questions
- Does codegraph run?
- Yes. codegraph runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test codegraph?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6560052a6f85. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test codegraph?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codegraph 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 codegraph need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codegraph?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does codegraph compare with the alternatives?
- Of the 7 C projects Argusic has installed and timed, codegraph was the 5th fastest to reach a running state, and 5 of 7 reached one at all.
- Where is the evidence for codegraph?
- 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.