WHAT NEW IN X11.05 THU

AI collections from X · 23 collections · 69,408 posts

jevVIDEO

Jev community projects: trading bots, browsers, Doom and more

Roundup of nine community projects that use Jev for decisions, covering Monad limit-order trading, browser clicking, Doom and the dinosaur game, drones and tax form classification.

kiosa
@thegreatest_svArchived 2026.09.25Originally posted 2026.09.25
kiosa @thegreatest_svOriginally posted 2026.09.25
Open original on X

Jev dropped and people immediately started doing stupid sh*t with it people gave this thing trading bots, browsers, Doom, drones, dinosaurs and tax forms and basically said: “you decide.” here’s what happened: > jev-trader Jev gets a new Monad block every ~300ms and decides whether to place a live limit order. no essay. just the decision. 1,911 stars ▸ ⁠http://github.com/jarrodwatts/jev-trader > jev-ultrafast a browser agent where Jev decides every click. the text model only wakes up when something actually needs to be written. 16,758 stars ▸ ⁠http://github.com/browser-use/jev-ultrafast > jev-doom-agent someone compiled actual Chocolate Doom to WebAssembly and let Jev make the tactical decisions every frame. yes. Doom. ▸ ⁠http://github.com/lukaske/jev-doom-agent > jev-t-rex-runner remember that stupid Chrome dinosaur? now Jev plays it. jump → duck → run → repeat ▸ ⁠http://github.com/joshlarsen/jev-t-rex-runner > typesafe-chess Jev went against a real chess search engine. two games. colors swapped. the search engine won both — and overruled Jev’s first instinct on roughly half the moves. ▸ ⁠http://github.com/TholeG/typesafe-chess > jev-drone camera → Jev → drone. a simulated quadrotor has to clear five stations while Jev looks at the situation twice a second and decides what happens next. ▸ ⁠http://github.com/RomanSlack/jev-drone > tax-doc-classifier then someone gave it IRS forms. 261 documents. 100% strict accuracy. roughly $0.001/page. ▸ ⁠http://github.com/kyotofin/tax-doc-classifier > killmyidea this one is evil lol tell it your startup idea. Jev looks at it from different angles and gives you: KILL / FIX / SHIP ▸ ⁠http://github.com/monteduro/killmyidea > jev-curate throw huge Parquet / JSONL datasets at it. Jev judges 1,500+ rows/sec and keeps only the stuff that passes your rules. ▸ ⁠http://github.com/AkashPriyadarshii/jev-curate > pg-jev and now it’s inside PostgreSQL. ask questions about your own tables in plain English → get the decision back. ▸ ⁠http://github.com/realZachi/pg-jev and this is the weird part: none of these need Jev to write you a beautiful paragraph. they need it to look at a situation and pick: BUY / WAIT CLICK A / CLICK B JUMP / DUCK KILL / FIX / SHIP KEEP / DROP that’s basically the whole Jev idea. LLMs think and write. Jev decides. code does. full setup + my three-question Jev test below

This post quotes another post: x.com/thegreatest_sv/status/2102802378378621355

x.com/thegreatest_sv/status/2103184942872346801Archived 2026.09.25 10:04