next-ai-draw-io
Draw and edit draw.io diagrams by chatting with an AI. Web app, desktop app, and an MCP server for Claude Code, Cursor, Codex and VS Code.
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit c4ea6957b030
TypeScript, Apache-2.0 licensed. The project labels itself: ai, architecture diagram, claude code, diagram generator, diagrams, draw io, drawio and electron.
next-ai-draw-io runs, with stand-ins for the services it depends on. An Argusic agent installed it in 32 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
On Node 24, npm install and npm run build succeed, vitest passes all 809 unit tests, the built server answers 200 on /api/config and serves an end-to-end chat completion through a local OpenAI-compatible mock, and the Electron app launches and stays up on the virtual display.
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 92 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.
- npm install failed: electron@41 postinstall require() of ES module @electron/get not supported on system Node 18.19.14 minutes
- npm install-scripts gate left esbuild/electron/workerd postinstall binaries unbuilt2 minutes
- Mock OpenAI endpoint returned one-shot JSON to a streaming request; app rejected it (AI_InvalidResponseDataError: Response stream ended without a finish reason)2 minutes
- Install time
- 32 minutes
- Cold machine to finish
- 34 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm run test -- --run exited 0 (72 files, 809 passed); npm run build exited 0; curl POST /api/chat against the mock returned 200 with text-delta and finishReason:stop; curl POST /api/validate-diagram (1x1 PNG data URL) returned 200 {"valid":true}; curl /api/config returned 200; electron . --no-sandbox stayed running 20s on DISPLAY=:99 and electron --no-sandbox --version printed v41.10.7
- Model tokens used
- 1,265,352
- Exact commit tested
- c4ea6957b030
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Fix: installed prebuilt Node v24.22.0 into the user home (`/tmp` download, sha256 verified) and r… - Build: `npm run build` exited 0 (downloaded draw.io bundle, Next standalone build, all routes). - Type check: `npx tsc --noEmit` exited 0. - Unit tests: `npm run test -- --run` → 72 files / 809 tests passed (`launch_succeeded` true). - App: `npm start` (Next on 6001) answered `200` on `/api/config`, `/en`, `/api/server-models` thro… - E2E chat: stood up a localhost Argusic-compatible SSE mock (streaming `chat.completion.chunk`), p… - Mock design note: the first two mocks served a single non-streaming JSON body to the app's stre… - Desktop: `./node_modules/electron/dist/electron . --no-sandbox` on DISPLAY=:99 stayed running 20s… **Errors (3)** 1. `npm install` failed in electron postinstall (`ERR_REQUIRE_ESM` in `@electron/get`) on system No… 2. `npm rebuild` initially left install scripts unrun (npm 11 `allowScripts` gate for esbuild/elect… 3. First mocks returned one-shot JSON instead of SSE to `/v1/chat/completions`; app correctly 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
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 32 minutes to install, slower than the median of the 158 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 159 ai projects Argusic has installed and timed, next-ai-draw-io was the 147th fastest to reach a running state, and 104 of 159 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
aiarchitecture-diagramclaude-codediagram-generatordiagramsdraw-iodrawioelectronflowchartllmmcpmcp-servernextjs
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/next-ai-draw-io)Questions
- Does next-ai-draw-io run?
- next-ai-draw-io runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 32 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test next-ai-draw-io?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c4ea6957b030. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test next-ai-draw-io?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does next-ai-draw-io take to install?
- 32 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 next-ai-draw-io need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing next-ai-draw-io?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does next-ai-draw-io compare with the alternatives?
- Of the 159 ai projects Argusic has installed and timed, next-ai-draw-io was the 147th fastest to reach a running state, and 104 of 159 reached one at all.
- Where is the evidence for next-ai-draw-io?
- 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.