The e2e suite just went model-free. tester-army's e2e, trending on github oct 6, lets an agent…
the e2e suite just went model-free. tester-army's e2e, trending on github oct 6, lets an agent drive your app tests once, then replays the whole run with zero model calls.
the regression now runs on a recording.
Context
Verified event date: TesterArmy introduced its open source e2e framework on Oct 1, 2026 (TesterArmy blog). It combines Playwright-style locators and assertions with agent steps such as agent.act(), and runs the same tests on web, iOS and Android. AICoder (Oct 5) reports it topped GitHub daily trending with natural-language agent steps for web and mobile tests, replayed with zero model calls, and PromptCrates (Oct 5) reports the repo after its 0.17 release.
The TesterArmy docs say an agent step is one agent.act, agent.assert, agent.waitFor or agent.extract call, where the model reads the screen and every step has a deadline and a model-call budget.
The Oct 1 launch and the GitHub trending run match the sources, but the trending coverage is dated Oct 5, a day before his Oct 6. The zero model call replay comes from the AICoder headline; the TesterArmy pages read describe deterministic steps, agent steps with a model-call budget and artifacts from the latest run, not a record-once replay mode. 'The regression now runs on a recording' is the author's opinion. Replay-with-zero-LLM tools also exist elsewhere, such as Windup and flowproof.
Related work
- Windup: natural-language E2E tests with deterministic replay ↗Plans once with an LLM, then replays with zero LLM calls.
- flowproof v0.8.0 on PyPI ↗Records an agent run once and replays it with zero LLM calls.
- PromptCrates: TesterArmy e2e trends on GitHub after 0.17 release ↗Oct 5, 2026.
Watch next
- Find where the e2e docs describe replaying a recorded run without model calls.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 15:39 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →