MCP servers and skills: search, filter by where they run, and compare.
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-fl
Node.jsAGPL-3.0★ 3.3kNo key
PythonAGPL-3.0★ 29No key
Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.
GoAGPL-3.0★ 25No key
Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exists today (file systems
SkillAGPL-3.0★ 4Few starsNo key
Obsidian plugin that runs a local MCP server, exposing vault semantic search and file operations to AI assistants.
SkillAGPL-3.0★ 14No key
Memory that abstains instead of guessing: agent memory on your own Postgres with a verdict, confidence and provenance on every hit, and a calibrated refusal when nothing clears the threshold.
PythonAGPL-3.0★ 6Needs a key
Open-source RAG system that turns your ChatGPT export into a searchable knowledge base with Claude MCP integration.
SkillAGPL-3.0★ 9No key
Local-first GraphRAG: turn your documents into an inspectable knowledge graph you can search, chat with, and export. Self-hosted, bring-your-own-LLM (or fully offline with Ollama).
PythonAGPL-3.0★ 3Few starsNo key
Self-hosted MCP server for governed retrieval. Agents get cited passages from your Markdown, text, PDF, Word and Excel files, and only what their person or group may read, enforced in PostgreSQL befor
DockerAGPL-3.0★ 1Few starsNeeds a key
MCP server with 40 tools for web design analysis — layout extraction, motion detection, quality scoring, accessibility audit, Core Web Vitals, design comparison, and semantic search via Playwright, pg
Node.jsAGPL-3.0★ 2Few starsNeeds a key
Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination
PythonAGPL-3.0★ 4Few starsNo key
NameWhisper MCP server — 44 ENS intelligence tools for AI agents. Search, value, trade, and manage ENS names via the Model Context Protocol.
Hosted by authorAGPL-3.0Few starsNo key
Self-hosted RAG stack for crawl, scrape, search, ingest, query, and ask workflows with Qdrant, TEI embeddings, Chrome rendering, MCP/CLI/REST, and Gemini synthesis.
SkillAGPL-3.0★ 4Few starsNo key
Offline semantic search for everything on your disk - documents, code, PDFs, scanned images (OCR), video by the second. 100% local AI: hybrid RAG with keyword + vector + rerank, no API key, no cloud.
SkillAGPL-3.0★ 4Few starsNo key
Plug for SilverBullet to integrate LLM functionality
Node.jsAGPL-3.0★ 107No key
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
SkillAGPL-3.0★ 250No key
Open-source, self-hosted AI gateway for multi-tenant orgs: OpenAI-compatible LLM routing, RAG & vector stores, MCP hub, GPU fleet (MIG slicing), sandboxed coding agents, AI red-teaming & guardrails, a
SkillAGPL-3.0★ 26No 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
SkillAGPL-3.0★ 34No key
Obsidian Turbocharged — governed, agent-ready Obsidian MCP server. 163 tools across 31 domains, multi-vault native, pluggable embeddings. TypeScript + Rust. AGPL-3.0-only.
Node.jsAGPL-3.0★ 10No key
Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.
PythonAGPL-3.0★ 9No key
Agentic gateway providing persistent LLM memory via a markdown wiki. Open-source core of Kortexio.
Hosted by authorAGPL-3.0★ 8No key
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. A push for data sovereignty.
Node.jsAGPL-3.0★ 7Needs a key
Who stands behind it
