Knowledge graph pathfinder scoring candidate edges with Jev and traversing paths via beam search.
Real data. Real impact.
Emerging
Developers
git clone https://github.com/jexp/neo4jev.gitPer week
Excellent
One command unlocks capabilities that would take hours to build.
Knowledge graph pathfinder scoring candidate edges with Jev and traversing paths via beam search.
Assigns transition probabilities to candidate graph relations for low-latency traversal.
Accelerates multi-hop graph reasoning by orders of magnitude.
A graph-navigation demo; no measurement on tens of millions of nodes or tens-fold speedup was found. Without a key, the docs explicitly use labeled substitute answers. Not independently retested 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: jexp/neo4jev — 16 stars, MIT. Listed by Awesome Jev.
MIT
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.