Explore
Every listed MCP server and skill. Filter by where it runs, what it needs, and how it is licensed.
Every listed MCP server and skill. Filter by where it runs, what it needs, and how it is licensed.
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
python/MIT/★ 628/no key
Use when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and deployed Retriever services. Use for PDFs, images,
official/skill/Apache-2.0/★ 3.6k in collection/no key
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
python/Apache-2.0/★ 282/no key
Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agen
skill/MIT/★ 111/no key
Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.
skill/MIT/★ 109/no key
Calibre library automation via FastMCP — metadata, shelves, RAG-friendly export. Companion to Calibre, not a replacement. For Cursor / Claude Desktop.
python/MIT/★ 47/no key
Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase. Zero config, zero cloud, full context.
skill/Apache-2.0/★ 20/no key
Persistent memory for AI assistants — semantic search, knowledge graph, and MCP server integration. Built in Rust.
skill/Apache-2.0/★ 15/no key
Local-first markdown notes with a first-class MCP server. 16 tools + 2 resources for Claude Code, Claude Desktop, Cursor and any MCP agent. Per-folder permissions, semantic RAG via LanceDB, single Bun
skill/AGPL-3.0/★ 33/no key
A rag + rag-graph native code intelligence layer for Java microservice estates, exposed to LLM agents via CLI
skill/MIT/★ 9/no key
ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector
skill/MIT/★ 29/no key
Who stands behind it
Who stands behind it
