Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

Self-hosted agentic memory MCP server backed by Qdrant, inspired by supermemory. Provides semantic memory storage, entity/relation knowledge graph, and optional reranking as MCP tools.

Local-first Context7 alternative — indexes JS/TS dependency docs with a 4-stage RAG pipeline. Uses TEI (Text Embeddings Inference) Docker containers for embeddings and reranking.

Production-ready RAG (Retrieval-Augmented Generation) for JavaScript & React - Built on official Ollama & LM Studio SDKs with Hybrid Search, Reranking, Query Transformation, Caching, Conversation Management & Evaluation

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

OpenClaw memory backend: hybrid BM25 + vector search with reranking and CJK support

RAG chunk reordering, retrieval reranking, and context packing to mitigate lost-in-the-middle in LLM context windows. Drop-in reordering for LangChain, LlamaIndex, Vercel AI, and any RAG pipeline.

Hybrid BM25 + vector search CLI for personal knowledge bases. Cross-encoder reranking, SQLite + sqlite-vec.

ZeroEntropy AI Provider for Vercel AI SDK

QMD (Quick Markdown Search) extension for pi coding agent - on-device knowledge base search with BM25, vector search, and LLM reranking

🔍 AI-powered semantic search library with Azure OpenAI embeddings, intelligent reranking, and local SQLite storage. Find documents by meaning, not just keywords.

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

A lightweight package providing information about various Large Language Models (LLMs), including embedding, reranking, and other models.

Multimodal memory for OpenClaw agents — powered by Gemini Embedding-2. Hybrid search (BM25 + vectors), cross-encoder reranking, image/audio/PDF memory.

Kjarni - Cross-platform ML inference engine. Embeddings, classification, reranking, and RAG search.

Remote MCP server for searching U.S. FOIA statutes via Supabase. Provides hybrid search (BM25 + vector + RRF) with VoyageAI embeddings and reranking.

MemberJunction: AI - core components for abstracting LLMs and other AI model types that are usable anywhere without ANY other MJ dependencies past @memberjunction/global which itself has zero additional dependencies.

A native Capacitor plugin that embeds llama.cpp directly into mobile apps, enabling offline AI inference with chat-first API design. Complete iOS and Android support: text generation, chat, multimodal, TTS, LoRA, embeddings, and more.

Query Markup Documents - On-device hybrid search for Org-mode and Markdown files with BM25, vector search, and LLM reranking

A lightweight package providing information about various Large Language Models (LLMs), including embedding, reranking, and other models.