Semantic code search with decision models

Local code search for coding agents: ripgrep/BM25 shortlist, then Jev judges each chunk's relevance, served over MCP.

Speed-focused Pi extension combining a local coding model with Jev judgments for file retrieval and cached requests.

Pi codemode tool that classifies whole project files with caller-defined Jev questions, returning paths and typed answers, not source.

Code navigation tool where a lexical index proposes candidates and Jev's typed judgments decide which files and lines belong.

Grep by meaning: a zero-dependency Node CLI where Jev scores each line against a described meaning, combinable with AND/OR/NOT.

MCP server that finds relevant code with Jev Choice and Noul checks instead of grep sweeps, and audits diffs against task intent.

Codex and Claude Code skills that narrow a repository locally and let Jev judge which candidate files the coding model needs.

Codebase search where an ensemble of walkers descends the file tree, with Jev ranking which files and folders look relevant at each level.

Taboo-style browser game where Jev guesses which of 135 UI components you are describing and buzzes at 0.85 confidence.

Codex skill using the local Jev CLI to rank candidate code snippets before reproduction, root-cause analysis and a verified fix.

Codex search plugin that runs ripgrep and keeps only passages Jev judges relevant to the question.

Experimental Python CLI for semantic line search with Jev via OpenRouter, meant to complement exact search for agents and notes.

PiJev: Pi-based coding agent where Jev shortlists skills, ranks code excerpts and triages tool failures while your model writes code.

Locates the file a bug report is about, or flags defects in a diff, by asking Jev yes/no over small source batches.

Code search CLI and agent skill (jg) where Jev judges relevance across folders, files and declarations to return excerpts.

Grep-shaped Rust CLI for coding agents: BM25 recall plus Jev Noul window checks and a listwise Choice return path:line results with scores.

grep where the pattern is a description: each line, record, function or diff hunk becomes a streamed Jev yes/no question.

CLI that scans TS/JS and Python code for LLM calls that are really decisions, converts them to Jev and shadow-tests them on real traffic.

find(1) with a semantic --like predicate: ordinary filters run locally and Jev judges whether each remaining file matches a description.

Local markdown mirror of TypeSafe's docs with a Rust BM25 and knowledge-graph search tool, Lume.

399M ModernBERT-large decision model with one universal choice head answering Choice, Noul and Score in a single forward pass.

CLI and MCP server giving coding agents Jev-powered semantic search, focused reads and list picking in about a second for about a cent.

Reproducible benchmark of SubQ Snap, TypeSafe Jev and three open decision models on software-engineering decisions.

Repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.