OQ
org-qmd io.github.tobi/qmd-jrfnmt Query Markup Documents - On-device hybrid search for Org-mode and Markdown files with BM25, vector search, and LLM reranking
Version check not run yet
Search and retrieval (RAG) npm Local 2 a week MIT
VI
vidilearn io.github.alfo-tech-lab/vidilearn AI-native universal knowledge ingestion and semantic retrieval engine with hybrid BM25+vector search, MCP server integration, and offline embeddings
Version check not run yet
Search and retrieval (RAG) npm Local 19 a week MIT
-
An [MCP server](https://modelcontextprotocol.io) and CLI tool that makes your Obsidian vault queryable by AI assistants. Indexes notes into SQLite with FTS5 full-text search, trigram fuzzy matching, a
Version check not run yet
Docs and knowledge bases npm Local MIT
TR
tea-rags io.github.artk0de/tearags-mcp-pxw2s0 MCP server for semantic search using local Qdrant and Ollama (default) with support for OpenAI, Cohere, and Voyage AI
Version check not run yet
Search and retrieval (RAG) npm Local 67 a week MIT
-
A zero-configuration RAG memory server for MCP clients
Version check not run yet
Memory and context npm Local 64 a week MIT
-
Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.
Version check not run yet
Docs and knowledge bases Official MCP Registry Local
LO
Longmem io.github.marerem/longmem Persistent cross-project memory for Cursor and Claude Code using local semantic search.
Version check not run yet
Memory and context Official MCP Registry Local
-
Chroma MCP Server - Vector Database Integration for LLM Applications
Version check not run yet
Search and retrieval (RAG) PyPI Local APACHE-2.0
-
Lightweight semantic memory service with ONNX embeddings - no PyTorch required. 80% smaller install size. REST API + MCP transport.
Version check not run yet
Memory and context PyPI Local APACHE-2.0
-
Experimental MCP proxy for filtering large tool lists using hybrid semantic and keyword retrieval
Version check not run yet
Search and retrieval (RAG) PyPI Local MIT
-
Portable cognitive engine for AI agents — storage, embeddings, memory, FSRS, and MCP server
Version check not run yet
Search and retrieval (RAG) npm Local 57 a week MIT
-
MCP Server for Qdrant Vector Database - Search, manage collections, and points
Version check not run yet
Search and retrieval (RAG) npm Local MIT
-
MCP server for fetching and searching documentation with semantic search
Version check not run yet
Docs and knowledge bases npm Local MIT
R2
r2mcp io.github.dmokong/r2mcp Persistent semantic memory layer for Claude Code — PostgreSQL + pgvector + OpenRouter embeddings
Version check not run yet
Search and retrieval (RAG) npm Local 52 a week MIT
-
SNIPER MCP server for domain knowledge indexing and retrieval
Version check not run yet
Search and retrieval (RAG) npm Local MIT
-
Context compression and persistent retrieval for Claude Code
Version check not run yet
Memory and context npm Local 50 a week MIT
-
Token-efficient memory, code indexing, and validation for Claude Code agents — SQLite + FTS5, TF-IDF + Qdrant retrieval, AST skeleton pruning, diff-aware context, Logic Guardian drift detection
Version check not run yet
Search and retrieval (RAG) npm Local 49 a week MIT
-
Adaptive Retrieval-Augmented Self-Refinement MCP Server — a closed-loop system that lets LLMs iteratively verify and correct their own claims using uncertainty-guided retrieval.
Version check not run yet
Search and retrieval (RAG) npm Local MIT
-
ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with token-efficient Skeletonization.
Version check not run yet
Developer tools npm Local 44 a week SEE-LICENSE-IN
-
Lightweight persistent memory for Claude Code and OpenCode. In-process embeddings, no external services.
Version check not run yet
Memory and context npm Local 44 a week APACHE-2.0