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: GitHubCMITcommit 6560052a6f85
C, MIT licensed.
codegraph runs. An Argusic agent installed it in 12 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CodeGraph v1.6.2 builds, the CLI runs and indexes JavaScript/Python projects, queries symbols via FTS5, and reports node-sqlite WAL backend, all when executed with Node 24.16.0 (node:sqlite required).
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. 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.
- Container Node.js v18.19.1 does not have node:sqlite (requires >=22.5) — all DB-backed tests fail with 'No such built-in module: node:sqlite'8 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 45 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test on Node 24.16.0: 8 core test files passed (453 tests, 8 skipped). CLI: node dist/bin/codegraph.js --version → 1.6.2; init + sync + query + status --json all returned correct output with node-sqlite backend.
- Model tokens used
- 236,817
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- `node dist/bin/codegraph.js status --json` → Reports `"backend":"node-sqlite"`, `"journalMode":"w… - Core test suite: `8 files passed, 453 passed | 8 skipped` in 47s, covering installer targets, fra… tokens used 236,817 All the key information is gathered. Let me compile the final report. The project builds and runs fully. The primary issue was **Node version** - the container has Node … Key evidence: - `node dist/bin/codegraph.js --version` → `1.6.2` - `node dist/bin/codegraph.js init` → Indexes JS/Python, reports 8 nodes, 11 edges in 232ms - `node dist/bin/codegraph.js query` → Finds symbols by name correctly - `node dist/bin/codegraph.js status --json` → Reports `"backend":"node-sqlite"`, `"journalMode":"w… - Core test suite: `8 files passed, 453 passed | 8 skipped` in 47s, covering installer targets, fra…
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 MIT, as reported by its host.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 4 C projects Argusic has installed and timed, codegraph was the 3rd fastest to reach a running state, and 4 of 4 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 12 minutes, hitting 1 error 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. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test codegraph?
- The run that produced this verdict cost $0.18: 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?
- 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 codegraph need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codegraph?
- 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 codegraph compare with the alternatives?
- Of the 4 C projects Argusic has installed and timed, codegraph was the 3rd fastest to reach a running state, and 4 of 4 reached one at all.
- Where is the evidence for codegraph?
- 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.