Jev in production › Agent tool and action selection

jev-ra

Vendor claims Jev-driven single-round-trip browser navigation beat browser-use with gemini-flash by 3.96x to 8.5x on real tasks, e.g. 2.7s vs 23s on Wikipedia (author).

Open on GitHub ↗

3.96x to 8.5xmeasured against a baseline, as published by the source
Use
Agent tool and action selection
Industry
Developer tools
Form
Open-source tool
Stage
Announced
Listed
2026-09-25
Found via
github
Repository
brnyxx/jev-ra
Stars
4
Forks
1
Last push
2026-09-29
Language
Python
License
MIT
jev-ra screenshot
assets/demo/wikipedia.gif in the brnyxx/jev-ra README, MIT; shown from GitHub.

The README opens with

Site: brnyxx.github.io/jev-ra replays a real recorded run and explains the pipeline.

A fast browser-use layer for CLI coding agents. Claude Code, Codex, or any MCP client hands jev-ra a goal. TypeSafe Jev, a System One decision model, picks the operation and the target element for every step in one round trip. Your agent plans, supplies the text values, reads what the page says, and takes over when jev-ra escalates. No second LLM runs inside the loop.

Badge

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

Listed in Jev in production

Also used for agent tool and action selection