9 projects · checked 2026-09-20

Decision models for search and retrieval

Source selection, query routing and relevance filtering. Deciding which retrieved chunks are actually worth passing on is a classic typed decision.

8 of these 9 call the hosted API rather than running open weights.

jev-search294 ★superagents-labSearch the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.TypeScript · MIT · pushed 2026-09-20jev-mcp157 ★jkudishFast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.TypeScript · MIT · pushed 2026-09-20jegrep53 ★can1357Semantic grep: find code by describing what you're looking for, powered by Jev.Rust · MIT · pushed 2026-09-20blink27 ★ellipsis-devCodebase search powered by Jev from @typesafe-aiTypeScript · pushed 2026-09-16jev-recall25 ★samdotmakRetrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's JevTypeScript · MIT · pushed 2026-09-20jevgrep21 ★nassim-arifetteJev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.TypeScript · MIT · pushed 2026-09-20Cheshi16 ★CheshiAIJev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.C · MIT · pushed 2026-09-20jgrep12 ★keltokhygrep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.Python · MIT · pushed 2026-09-20pi-jev11 ★madeyeJev-assisted file retrieval and request caching for faster Pi workflowsTypeScript · MIT · pushed 2026-09-20

Find out what your data actually supports

We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.