Graph and knowledge navigation with decision models
Choosing which edge, link or node to follow next when walking a knowledge graph, wiki or taxonomy.
16 public projects
Local-first Windows writing studio with knowledge graphs and author voice, where optional Jev evaluates candidates and editorial decisions.
ProjectbetaTypeScriptFifteen live arcade games where Jev and LLMs play each other, led by WikiRace in which Jev picks only real links.
ProjectbetaTypeScriptTerminal tool that finds link paths between Wikipedia articles: Jev ranks each page's outgoing links while Python runs the search.
ProjectbetaPythonLinter for Obsidian vaults and LLM wikis that flags contradictions, stale claims, unresolved markers and dangling links with Jev.
ProjectbetaPythonOn-call tooling where Jev judges alerts and incident hypotheses and plain code decides: alert routing plus a no-LLM root-cause benchmark.
ProjectbetaPythonnpm library that walks a taxonomy with one Jev Choice per level so you can select among thousands of leaves despite the 255-option cap.
ProjectbetaTypeScriptMilvus-based multi-hop graph RAG library where two-stage Jev Noul scoring selects relations and reranks passages.
LibrarybetaPythonWindows file organiser that uses Jev Choice and Noul to suggest which folder a new file belongs in and to drill down to find files.
ProjectprototypeTypeScriptNeo4j demos using Jev as a calibrated judge in GraphRAG pipelines, starting with entity resolution and a review queue.
AppprototypePythonGraph-database-agnostic GraphRAG framework where swappable Laya or Jev decisions score edges, route intents and gate hallucinations.
ServicebetaPython- neo4jev★ 173
Demo that navigates a Neo4j graph hop by hop, asking Jev which relationship to follow and whether the goal is reached.
LibraryprototypePython CLI and agent skill that shortlist notes in Obsidian or Logseq locally, then have Jev rerank them, returning original passages.
DemobetaJavaScriptOpen protocol for decision-based agents: apps expose evidence and typed decisions, Jev assesses, and app code guards commits.
AppprototypeTypeScriptTraining library for a small one-pass model that scores a changing list of text options and returns a probability per option.
LibraryresearchPythonIndependent experiments on Jev for search stopping, memory reranking and multi-hop relation selection, with stated limits.
ArticleresearchX demo where Jev picks which candidate link to click on a page to move toward a goal.
Discussiondiscussion