jev-demos
Maze experiments comparing Jev single-step choices with multi-step lookahead.
AI Skill Market Insights
Real data. Real impact.
Emerging
Developers
Quick Start
Install Command
git clone https://github.com/Bud-ro/jev-demos.gitMaze experiments comparing Jev single-step choices with multi-step lookahead.
Real data. Real impact.
Emerging
Developers
git clone https://github.com/Bud-ro/jev-demos.gitPer week
Excellent
One command unlocks capabilities that would take hours to build.
Maze experiments comparing Jev single-step choices with multi-step lookahead.
Chooses moves from direction candidates, then checks collisions, paths and completion.
Keeps experiment settings and failures visible for studying limitations.
README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.
Source: Bud-ro/jev-demos — 0 stars. Listed by Awesome Jev.
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.