QUATCODE AGENT — project brain: scanning and relevance ranking

Lightweight fuzzy-search

Intelligent MCP server for LLM context management — progressive disclosure, dependency graphs, relevance ranking

The fastest grep tool built for AI agents — structured JSON output, relevance ranking, token budgets

Advanced Google search query construction, result filtering, and relevance ranking for OpenClaw Agent

The fastest grep tool built for AI agents — structured JSON output, relevance ranking, token budgets

Concrete ctx.sessionQuery backend with SQLite FTS5 search

A highly efficient, isomorphic, full-featured, multilingual text search engine library, providing full-text search, fuzzy matching, phonetic scoring, document indexing and more, with micro JSON state hydration/dehydration in-browser and server-side.

AWS SDK for JavaScript Kendra Ranking Client for Node.js, Browser and React Native

Tiny but powerful full-text search engine for browser and Node

glicko2 ranking system

Fast and tiny fuzzy-search utility

A module for the search backend that implements search using PostgreSQL

Vibgrate relevance kernel: query analysis over the compiled relevance pack. Proprietary distribution — the compiled WASM engine plus a minified wrapper; the relevance pack and the reference implementation are not included.

Wrapper around the Botpress Client to call LLMs

The always-include AI Matrx kit: the little primitives every Matrx app speaks — autosave that never loses a keystroke, stale-response guards, clipboard with graceful fallbacks — one per subpath, tree-shaken to what you use.

Evidence-backed model capability observations, deterministic catalogs, and runtime-aware ranking.

Score AI agent context for relevance with Jev, and decide what to keep, drop, or summarize.

For NPM module authors that would like to support Deno but do not want to write and maintain a port.

[DAN] RECALL DASHBOARD — Remember. Recall. Forget. Real BM25-ranked recall by default, real hybrid (BM25 + semantic) when OPENAI_API_KEY is set.