Explore
MCP servers and skills: search, filter by where they run, and compare.
fhir-mcp-serverthe-momentum
LocalFHIR MCP Server for handling medical data standard.
PythonMIT★ 102No key
mempalace-extendedqudadd
Local
MCP servers and skills: search, filter by where they run, and compare.
FHIR MCP Server for handling medical data standard.
PythonMIT★ 102No key
Extension of the original MemPalace with document ingestion, image assets, MCP tooling, and folder watch.
PythonMIT★ 1Few starsNo key
Model Context Protocol server for advanced RAG with Knowledge Graphs
PythonMIT★ 6No key
Local SQLite memory for LangGraph agents, with provenance, TTL, export, and MCP.
PythonMIT★ 17No key
Self-hosted document intelligence for RAG — parse, classify, split, and extract from PDF/DOCX/PPTX and images: searchable, cited, retrieval-ready chunks and schema-driven extraction
PythonMIT★ 5No key
Universal document ingestion engine — any file in, agent-ready Markdown out. PDF, Word, PowerPoint, Excel, HTML, EPUB and more, with structure preserved, page anchors you can cite, and an MCP server.
PythonApache-2.0Few starsNo key
PythonUnlicense★ 3Few starsNo key
Decision-aware knowledge graph on LightRAG: extends (head, relation, tail) triples into contextual quadruples (h, r, t, rc) that capture decision lineage — who approved what, why, via which channel, u
PythonMIT★ 2Few starsNo key
Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.
PythonMIT★ 36No key
the best mcp server for lightrag with support for idempotent uploads
PythonApache-2.0★ 8No key
LLM document ingestion pipeline with AI readiness scoring and structured Markdown/JSON output.
MCPLink only★ 9
Give your agent a memory it can prove. One Python file: local SQLite vault, hybrid FTS5 + vector retrieval, Cloudflare-aware fetching, and a research loop whose [V]/[E]/[H] citations are machine-verif
SkillMIT★ 8No key
Air-gapped multi-format document ingestion, local OCR fallback, structural legal/business chunking, and PostgreSQL/pgvector indexing for the Krusch Ecosystem.
PythonMIT★ 1Few starsNo key
MCP-native agentic RAG: a private corpus searched before the web, every claim cited, retrieval you can measure.
PythonMIT★ 1Few starsNo key
Agent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.
SkillMIT★ 2Few starsNo key
Local-first knowledge engine with semantic search, GraphRAG, and Claude Desktop integration via MCP. Features hybrid search (vector + BM25), cross-encoder reranking, multi-format document ingestion (P
PythonMIT★ 1Few starsNo key
lightweight MCP server for universal document ingestion into parsable Markdown
PythonMIT★ 2Few starsNo key
All-in-one RAG framework for Nepali Documents
PythonMIT★ 2Few starsNo key
MCP knowledge server for persistent memory: ingest text, files, URLs, and YouTube transcripts, then retrieve semantically relevant results (with optional source citations) across namespaces.
PythonMIT★ 1Few starsNo key
NOEMA-AI — a hybrid RAG platform combining vector + BM25 retrieval (Reciprocal Rank Fusion), multi-turn chat with session memory, streaming answers (SSE), a LangGraph pipeline with guardrails, an MCP
PythonMIT★ 3Few starsNo key
A self-hostable workbench for source acquisition, evidence preservation, retrieval and reviewed intelligence, with local inference and optional governed APIs.
PythonApache-2.0★ 1Few starsNo key
Production RAG with continuous evaluation — hybrid retrieval (BM25 + vector/RRF), LLM-as-judge scoring on faithfulness/relevance/hallucination, MCP server, adaptive retrieval tuning. 68 tests.
PythonMITFew starsNo key
Claude Code / Codex CLI plugin for generating reviewable HTML documents with preview, inline review comments, and agent feedback ingestion.
SkillMIT★ 300No key
Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB.
PythonMIT★ 68No key
Who stands behind it
