Jev in production › Search, ranking and matching

jevcrawl

Jev selects links and passages to pursue during agent web crawls; the maintainer reports 54% vs 33% answer-page recall and 8x lower cost than Crawl4AI (author).

Open on GitHub ↗

54% vs 33%measured against a baseline, as published by the source
Use
Search, ranking and matching
Industry
AI infrastructure
Form
Open-source tool
Stage
In production
Listed
2026-10-14
Found via
github
Repository
RayenMlayeh/jevcrawl
Stars
82
Forks
8
Last push
2026-10-26
Language
Python
License
Apache-2.0

The README opens with

The web crawler for AI agents that finds the answer, not just pages.

A small decision model picks every link and every passage, so your agent's LLM reads only what answers its question at a few cents per crawl.

Quick start · Benchmarks · Tools · How it works · Configuration

Agents that browse a site have two bad options. They can read everything a crawler fetches, which buries the answer in navigation and boilerplate and burns tokens. Or they can let the LLM pick each link, which is slow and costs dollars per question. jevcrawl does neither:

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for search, ranking and matching