Graft
One shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up where you left off.
Runssource: GitHubhomepageTypeScriptMITcommit 05760b07abc0
TypeScript, MIT licensed. The project labels itself: ai agents, anthropic, claude code, cli, code graph, codex, context engineering and cursor.
Graft runs. An Argusic agent installed it in 2.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install completes, TypeScript compiles, the CLI builds/checks/queries a structural code graph on a real repo without any keys, and all 1220 tests run with 0 failures.
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.
- Test 'a process killed while holding the lock releases it' (graph-refresh.test.ts:434) failed: `node -e` with top-level await throws SyntaxError because Node 20's -e runs as CommonScript by default4 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, 1219 tests passed, 0 failed, 1 skipped (expected Node 24 skip)
- Model tokens used
- 220,497
- Exact commit tested
- 05760b07abc0
- 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 verdict above comes from a different attempt, so read this as one session and not as the current result. 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.
Everything works. Let me compile the final report: - **`npm install`** succeeded on Node.js 20.18.0 (required >=20). The build step (`tsc` + viewer bu… - **1 error fixed**: test `graph-refresh.test.ts` line 456 — `node -e` ran as CommonJS where top-le… - **1220 tests: 1219 pass, 0 fail, 1 skip** (expected Node 24-only skip for V8 Turboshaft). - **CLI binary** works: `graft build`, `graft check`, `graft ask` all function without API keys for… tokens used 220,497 Everything works. Let me compile the final report: - **`npm install`** succeeded on Node.js 20.18.0 (required >=20). The build step (`tsc` + viewer bu… - **1 error fixed**: test `graph-refresh.test.ts` line 456 — `node -e` ran as CommonJS where top-le… - **1220 tests: 1219 pass, 0 fail, 1 skip** (expected Node 24-only skip for V8 Turboshaft). - **CLI binary** works: `graft build`, `graft check`, `graft ask` all function without API keys for…
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.
- Installed in 2.5 minutes, faster than the median of the 114 comparable projects Argusic has measured.
- 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.
- Measured 3 times, so the result is not a one-off.
Of the 115 ai-agents projects Argusic has installed and timed, Graft was the 33rd fastest to reach a running state, and 85 of 115 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.
- A quick evaluation: it was running 2.5 minutes after the clone.
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-agentsanthropicclaude-codeclicode-graphcodexcontext-engineeringcursordeveloper-toolsgeminiknowledge-graphllmmcpmcp-serveropen-sourceopenaitree-sitter
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/graft)Questions
- Does Graft run?
- Yes. Graft runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test Graft?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 05760b07abc0. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Graft?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Graft take to install?
- 2.5 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 Graft need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Graft?
- 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 Graft compare with the alternatives?
- Of the 115 ai-agents projects Argusic has installed and timed, Graft was the 33rd fastest to reach a running state, and 85 of 115 reached one at all.
- Where is the evidence for Graft?
- 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.