Local alternative
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Details →★ 21,612
jev-capability-atlas
Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙語 repo。
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-18
- GitHub stars
- 26
- Evidence checked
- 2026-09-24T08:40:10.508Z
- Metadata checked
- 2026-09-24T08:40:10.508Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
**獨立、非官方、非 TypeSafe 贊助的社群專案**（除了一般的早鳥候補名單，我們沒有收到 TypeSafe 任何報酬或提前使用權）。 這個 repo 存在的目的，是幫你、我、還有任何想用 [Jev]（TypeSafe 的 System One 模型）的人，**正確識別手上的任務適不適合交給它**——用真實 API 呼叫的收據，畫出它「校準決策」這個宣稱在哪裡站得住、在哪裡站不住的邊界地圖。給人看怎麼用，給 agent 帶進專案看哪裡能試著換上去，也給任何做過真實驗的人一個把結果貢獻進來的地方。
Evidence commit: e3a904da6ccddf983894b431f3573f72118b3a90
Discovered through: awesome-jev, typesafe-field-guide.
How we review →