bento
Bento, the office suite that fits in a file
Runssource: GitHubhomepageTypeScriptMITcommit 01000838496e
TypeScript, MIT licensed. The project labels itself: mit license, office, office 365, office suite, office tools, office365, open source and powerpoint.
bento runs. An Argusic agent installed it in 23 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
bento/slides, dash, spaces, and type apps all install, typecheck, and build into single-file .bento.html distributables; all 80+ test scripts across all apps pass, exercising the CRDT sync engine, document model, UI logic, format converters, and security invariants.
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.
- 36 dash test scripts used Node 23.4+ registerHooks API3 minutes
- Node.js v18 was too old for Vite 7 — needed ^20.19.0 || >=22.12.01 minute
- test-convert.ts spawned child processes without --experimental-strip-types1 minute
- test-dash-steps.ts memory probe needs --expose-gc — pre-existing limitation with this Node version
- Install time
- 23 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- All 3 app builds produce valid .bento.html files; shell-gate.mjs conformance passes; 45,368 CRDT convergence checks pass; 28/28 preview rig checks pass; 7/7 convert rigs pass; ~40 dash test scripts all pass; 24 type test scripts all pass; 4 spaces test scripts all pass; test-sync.ts (CRDT convergence) exercises real document model operations end to end
- Model tokens used
- 517,292
- Exact commit tested
- 01000838496e
- 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.
**Builds**: `Bento_Slides.bento.html` (678 KB), `Bento_Dash.bento.html` (425 KB), `Bento_Spaces.ben… tokens used 517,292 Let me compile the final summary report. **Installation**: Had to work around Node 18 (too old for Vite 7). Downloaded Node 22.14.0, used it… **One fix applied**: 36 dash test scripts used `registerHooks` (Node 23.4+ API) which doesn't exist… **Test results**: Every test script ran successfully. Summary: - **Slides**: sync convergence rig (45,368 checks), preview rig (28/28), shell-gate conformance (OK… - **Dash**: ~40 test scripts all pass — model (42/42), store (126/126), sync (23,107 checks), formu… - **Spaces**: agent (171/175), calc (90/90), journal (45/45), model (933/933), invite/roundtrip/und… - **Type**: all 24 test scripts pass **Builds**: `Bento_Slides.bento.html` (678 KB), `Bento_Dash.bento.html` (425 KB), `Bento_Spaces.ben…
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 23 minutes.
- Recovered from all 4 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 3 times, so the result is not a one-off.
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)
mit-licenseofficeoffice-365office-suiteoffice-toolsoffice365open-sourcepowerpointself-hostedsingle-page-appslidesslideshareslideshowslideshow-galleryslideshow-makerslideshows
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/bento)Questions
- Does bento run?
- Yes. bento runs. Argusic installed and launched it on a clean machine in 23 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test bento?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 01000838496e. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test bento?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does bento take to install?
- 23 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 bento need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing bento?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for bento?
- 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.