Explore
MCP servers and skills: search, filter by where they run, and compare.
hybrid-rag-mcpLynncX
Locala rag mcp supporting for both ways of local model and api . base on https://github.com/shinpr/mcp-local-rag.
Node.jsMIT★ 1Few starsNo key
MCP servers and skills: search, filter by where they run, and compare.
a rag mcp supporting for both ways of local model and api . base on https://github.com/shinpr/mcp-local-rag.
Node.jsMIT★ 1Few starsNo key
Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'BM25 or sparse vectors?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from
OfficialSkillMIT★ 40k in collectionNo key
Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or
OfficialSkillMIT★ 40k in collectionNo key
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
PythonMIT★ 644No key
Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.
PythonMIT★ 299No key
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
SkillMIT★ 213No key
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
SkillMIT★ 231No key
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ran
SkillMIT★ 121No key
Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.
Node.jsMITFew starsNo key
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.
PythonMIT★ 20No key
A research harness for ML, built on the Claude Agent SDK. Claude Code with a literature funnel, a prediction ledger, and gates in front of every dollar.
SkillMIT★ 7No key
A local, code-aware RAG engine for Claude Code and Cursor with exact line citations.
PythonMIT★ 1Few starsNo key
A local-first retrieval engine that turns notes, docs, and code into a searchable knowledge base for humans and AI agents.
SkillMIT★ 5No key
Code-search platform for AI coding agents: vector search fused with BM25 keyword scoring and reranking, tree-sitter AST chunking, a web app, a REST API and a 12-tool MCP server.
SkillMIT★ 11No key
⚡ Blazing-fast skill routing engine for AI coding agents. Discovers, indexes, and routes 300+ agent skills in <50ms. Supports Gemini/OpenAI embedding reranking.
SkillMIT★ 3Few starsNo key
Find a past Claude Code or Codex conversation from a vague memory — no exact keywords needed. 用模糊的印象找回過去的 AI 對話。
SkillMIT★ 9No key
A high-performance MCP (Model Context Protocol) server for semantic code search, written in Rust.
SkillMIT★ 9No key
AI-powered code generator for Arbitrum Stylus, SDK bridging, dApps & Orbit chains — 19 MCP tools with RAG
PythonMIT★ 24No key
Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assembly, export/reload and bounded hill climbing. TypeSafe Jev is
SkillMIT★ 13No key
Code Knowledge: AST-aware chunking + graph expansion for precise code retrieval.
SkillMIT★ 7No key
A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing a
SkillMIT★ 16No key
Who stands behind it
