MM
MGI-Mind io.github.madgodinc/mgi-mind 1.8 · 36/100 Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.
Version check not run yet
Security Official MCP Registry · npm Local APACHE-2.0
-
MCP server for code intelligence — semantic context, dependency graphs, and compressed symbol indexes for TypeScript/JavaScript, plus git-aware diffs and fast search. Zero external dependencies: no ve
Version check not run yet
Developer tools npm Local 99 a week MIT
BR
brain-rag io.github.dasportillo/brain-rag 1.8 · 36/100 Local, private RAG second brain over your Claude Code & Codex transcripts, served back to both agents as an MCP server.
Version check not run yet
Memory and context npm Local 95 a week MIT
AT
Attestor io.github.bolnet/attestor 1.8 · 36/100 Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.
Version check not run yet
Security Official MCP Registry Local
-
Local-first, auto-injecting, self-aware-about-staleness context + memory layer for coding agents (Claude Code, Codex, MCP). Trust contract, hooks-first, hybrid retrieval + compression, zero infra.
Version check not run yet
Memory and context npm Local 86 a week MIT
-
MCP server for semantic code search using vector embeddings
Not run: needs install scripts
Search and retrieval (RAG) npm Local 193 a week MIT
PA
Palace io.github.AncientiCe/palace-rs 1.8 · 36/100 Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Version check not run yet
Search and retrieval (RAG) Official MCP Registry Local
-
AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.
Version check not run yet
DevOps and infrastructure Official MCP Registry · GitHub MCP Registry Local
-
Turn documents into structured, AI-ready data by parsing, enriching, chunking, and embedding.
100% up · 30 days
Office documents and spreadsheets Official MCP Registry · GitHub MCP Registry Remote
-
Local-first AI workflow for Eristack projects: MCP server, FTS+vector index, backlog/sprint/ADR artifacts — low-token agent tools that do not replace existing editors or Intent
Version check not run yet
Project management npm Local 76 a week MIT
-
A Model Context Protocol (MCP) server for Obsidian vault management via SSE transport, with optional pgvector-backed semantic search
Version check not run yet
Docs and knowledge bases npm Local 74 a week MIT
-
Sciverse MCP server — exposes academic paper retrieval (search_papers / semantic_search / read_content) to MCP-compatible coding agents (Claude Code, Cursor, Codex CLI, Windsurf, ...).
Version check not run yet
Science and research npm Local 72 a week APACHE-2.0
-
Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Version check not run yet
Search and retrieval (RAG) npm Local 4 a week MIT
OQ
org-qmd io.github.tobi/qmd-jrfnmt 1.8 · 35/100 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 1.8 · 35/100 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 1.8 · 35/100 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
HV
Hebbian Vault io.github.onetrueclaude-creator/hebbian-vault 1.8 · 35/100 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 1.8 · 35/100 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