flowgram.ai
FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.
Runssource: GitHubhomepageTypeScriptMITcommit ba1a9630f802
TypeScript, MIT licensed. The project labels itself: ai, automation, coze, data flow, diagram, flow, flowchart and graph.
flowgram.ai runs. An Argusic agent installed it in 7.3 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
With Node 18.20.4 and the repo's install-run-rush.js, rush install and rush rebuild complete without errors; rush test exits 0; the demo-free-layout dev server serves HTTP 200 on localhost:3000 and all 3 free-layout Playwright browser tests pass against it, and the free-stack-plugin bug fix is the only repository file changed.
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.
- rush test failed in @flowgram.ai/free-layout-editor: unhandled ReferenceError: document is not defined — free-stack-plugin StackingContextManager debounced _compute fired after jsdom teardown5 minutes
- fixed-layout e2e failed wholesale (8 failed) when it silently reused the running demo server on port 3000; its webServer runs 'rush', which is not on PATH; and Playwright had run with --update-snapshots before chromium existed4 minutes
- Rush requires Node >=18.20.3 but container had 18.19.1 (no root, no nvm); rush was not installed3 minutes
- runtime-js 'should handle network error' prints a stack from a mocked fetch rejection (HTTPExecutor.execute line 36 trace via retry loop) although the test passes1 minute
- Playwright didn't ship browsers: chromium_headless_shell-1194 missing0.8 minutes
- Cosmetic: rsbuild dev --open fails spawn xdg-open ENOENT (no desktop opener in container); server itself stays up
- Install time
- 7 minutes
- Cold machine to finish
- 29 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- curl -s -o /dev/null -w %{http_code} http://localhost:3000/ returned 200 (staffed 643B HTML; entry index.js 3.16MB and vendor chunks returned 200 and decoded); npx playwright test in e2e/free-layout: 3 passed (3.1s); e2e/fixed-layout: 8 passed, 1 flaky; node common/scripts/install-run-rush.js test exited 0 (6 unit-testing packages: 191+1skip, 298, 36, 4, 108+3skips, 245 passed); rush rebuild exited 0
- Model tokens used
- 894,817
- Exact commit tested
- ba1a9630f802
- 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.
All verification is complete. Final report: **What I did** - Freed a supported toolchain into user space (`~/node` Node 18.20.4, since the bundled 18.19.1 is … - `rush build` → 0 failures; `rush rebuild` (clean rebuild) → `rush rebuild (1 minute 24.7 seconds)… - `rush test` initially failed: `@flowgram.ai/free-layout-editor` reported an unhandled `ReferenceE… - **Fix:** in `packages/plugins/free-stack-plugin/src/manager.ts` — `dispose()` now sets `disposed … - `rush test` now: 6 unit-testing packages, 0 failures; totals observed per package = 191+1skip, 29… - Launched the demo: `npm run start` in `apps/demo-free-layout` → `Local: http://localhost:3000/`, … - Playwright Chromium was downloaded (`playwright install chromium`, 104MB). `e2e/free-layout`: `3 … - Pre-existing benign failure: `runtime-js` "should handle network error" prints a stack from a moc… **Files changed** - `packages/plugins/free-stack-plugin/src/manager.ts` (debounce cancellation on dispose).
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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 7.3 minutes to install, slower than the median of the 234 comparable projects Argusic has measured.
Of the 235 ai projects Argusic has installed and timed, flowgram.ai was the 150th fastest to reach a running state, and 166 of 235 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 7.3 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)
aiautomationcozedata-flowdiagramflowflowchartgraphintegration-frameworkjavascriptno-codenode-based-uireacttypescripttypescript-libraryvisualizationworkflowworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/flowgram-ai)Questions
- Does flowgram.ai run?
- Yes. flowgram.ai runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test flowgram.ai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ba1a9630f802. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test flowgram.ai?
- The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does flowgram.ai take to install?
- 7.3 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 flowgram.ai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing flowgram.ai?
- 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 flowgram.ai compare with the alternatives?
- Of the 235 ai projects Argusic has installed and timed, flowgram.ai was the 150th fastest to reach a running state, and 166 of 235 reached one at all.
- Where is the evidence for flowgram.ai?
- 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.