Cross-encoder semantic re-ranking for knowledge search

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-ranking, relevance filtering and lost-in-the-middle avoidance, citation-aware injection, library_cite_check and library_d

Semantic memory retrieval with re-ranking and diversification strategies

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

Dynamic tool selection for the Vercel AI SDK. Automatically picks the right tools per step.

A simple example showing how to do result re-ranking with RAG using Mastra, OpenAI, and PGVector.

Lightweight fuzzy-search

Turn any embeddings dataset into an agentic retrieval loop with query expansion, LLM re-ranking, and iterative refinement

A simple example showing how to do result re ranking with RAG using Mastra, OpenAI, and PGVector.

Model-facing skill loading tool for the DeepSeek Harness

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

rerank library for easy reranking of results

A library for finite automata and regular expressions in the context of JS RegExp

Resizable component for React.

Local-first RAG orchestrator SDK — hybrid search, knowledge graph, multi-modal indexing, agentic re-ranking

glicko2 ranking system

Fast and tiny fuzzy-search utility

Declarative routing for React web applications

A module for the search backend that implements search using PostgreSQL

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.