codemap
a project brain for your AI. Give LLMs instant architectural context without burning tokens
Runssource: GitHubGoMITcommit df8436b746fc
Go, MIT licensed. The project labels itself: claude, claude code, cli, codex, codex cli, context, cursor and developer tools.
codemap runs. An Argusic agent installed it in 16 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
codemap and codemap-mcp build and run with bundled ast-grep, the HTTP API answers 200 on /api/health, the MCP server completes the initialize handshake, and the full Go test suite passes.
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.
- go: not found on PATH3 minutes
- ast-grep not found; --deps and scanner tests degraded to Go-parser-only fallback2 minutes
- --diff/blast-radius/repo-handoff fail: no main branch (detached HEAD with no remote refs)2 minutes
- collide requires gh CLI + GitHub auth; gh not installed1 minute
- TestRunSetupCreatesConfigAndHooks fails under container PATH because codex binary exists on PATH while project ships no Codex CLI1 minute
- gofmt reported deep non-style issue trigged by -d flag passthrough in e2e test under Go 1.271 minute
- Install time
- 16 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- env PATH=/tmp/opt/go/bin:/tmp/tools:/usr/bin:/bin HOME=/tmp/cleanhome go test ./... returned exit 0 (16 packages ok); ./codemap --version returned 'codemap dev'; curl -s -o /dev/null -w %{http_code} 127.0.0.1:18000/api/health returned 200; codemap-mcp initialize returned valid JSON-RPC with serverInfo codemap dev
- Model tokens used
- 653,745
- Exact commit tested
- df8436b746fc
- 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.
- Test suite: `go test ./...` exit 0 — all 16 packages pass. ## Errors recorded - `go` missing → installed local toolchain (3 min). - ast-grep missing for deps + tests → bundled v0.42.1 installed (2 min). - `--diff`/`blast-radius`/repo `handoff` fail because the checkout has no `main` branch (detached H… - `collide` needs `gh` (not installed, no mock possible) → documented, not fixed (1 min). - One packaged test `TestRunSetupCreatesConfigAndHooks` fails only in this container because `codex… ## Environment notes - Test binaries need ast-grep on PATH — run tests as `env PATH=/tmp/tools:$PATH go test ./...` (REA… - Artifacts `codemap`, `codemap-mcp`, `ast-grep` are in the repo but excluded from git via `.git/in… - `go vet` and `gofmt` both clean. - A verifiable brand-new-user path: with only `go` and `ast-grep` available, the binary runs and th…
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 6 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.
What did not, or is not known
- Took 16 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 9 claude projects Argusic has installed and timed, codemap was the 9th fastest to reach a running state, and 5 of 9 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)
claudeclaude-codeclicodexcodex-clicontextcursordeveloper-toolsllmopenaiproject-management
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codemap)Questions
- Does codemap run?
- Yes. codemap runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test codemap?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit df8436b746fc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test codemap?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codemap take to install?
- 16 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 codemap need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codemap?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does codemap compare with the alternatives?
- Of the 9 claude projects Argusic has installed and timed, codemap was the 9th fastest to reach a running state, and 5 of 9 reached one at all.
- Where is the evidence for codemap?
- 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.