Back to benchmarks & research
jev-deepresearch project preview
Benchmarks & research

jev-deepresearch

Deep research crawl where Jev (a System One model) makes every per-page decision and an LLM only plans and writes

How it uses Jev

A depth-crawling research agent built to find out what a System One model is good for. Jev (TypeSafe AI) generates no text: you hand it a state and typed questions — a choice, a score, a yes/no — and get calibrated probabilities back in one forward pass, in a few hundred milliseconds, for a fraction of a cent. That turns out to be exactly the shape of every decision a research crawl has to make per page.

Languages
JavaScript 79% · HTML 21%
License
MIT
Latest release
Unfold 0.1.0
Last activity
Sep 2026
Added
2026-09-23
Stars at snapshot
2
Status
Community listing

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Listed in Jev Library

If this is your project, the badge below links back to this page. Paste it near the top of your README.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/tashfeenahmed-jev-deepresearch)](https://jevlibrary.dev/projects/tashfeenahmed-jev-deepresearch)

Something wrong on this page, or would you rather not be listed? Tell us and it will be changed.