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-Paper-Radar
Let Jev read every new arXiv paper each morning and surface the few you should read. Plain-English interests, calibrated probabilities, ~$0.06/day, fork and go.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-23
- GitHub stars
- 7
- 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.
\* Measured, not guessed: a real run on 2026-09-23 read 50 papers in 5 seconds for 46,584 input tokens and $0.0020 (932 tokens per paper, `jev-1.13.0`). All of arXiv, about 1,500 papers per weekday, works out to roughly $0.06 a day. Output tokens are free. Every run logs its own tokens and cost in `data/runs.jsonl`; `paper-radar check` estimates your profile before you spend anything.
Evidence commit: 33eaa6f3784e5fb28926bf7175752f7884432bae
Discovered through: awesome-jev, typesafe-field-guide.
How we review →