RAG MCP servers
RAG MCP servers indexed by Conduid, ranked by trust score. 8.3K live listings from GitHub, npm, PyPI and the official registry, each with a 0–100 score, security checks, and install commands.
Curator
Local-first knowledge plane — any markdown vault + one embedded index + MCP for agents + a deterministic librarian. Rust CLI + MCP server.
Dukememory
Local-first AI agent memory for coding projects: SQLite context, MCP server, Codex skill, Rust CLI, and optional embeddings.
Codegraph Rust
100% Rust GraphRAG implementation with a MCP server for indexing large codebases with blazingly fast speed and querying the graph with natural language
Getpaper
Open-source, self-hosted wiki and knowledge base for teams: multiple workspaces, Microsoft Entra ID SSO, Confluence and Outline import, built-in MCP server.
Lumberroom
One memory every AI tool can read and write, with per-client policy deciding what each may see. Rust MCP server, Postgres and pgvector, built-in OAuth 2.1.
Runbook Assistant
Ask your team's runbooks/SOPs, get grounded cited answers: hybrid search + ONNX rerank, SSE streaming, MCP server, eval-gated CI with token/cost observability.
Petbox
Self-hosted .NET 10 module monolith: infrastructure for AI coding agents - session digests, hybrid FTS5+vector memory search (RRF + rerank), task boards with a methodology engine,…
Memory Server
Qdrant x Quarkus MCP Memory Server
Hydra
Context hydration engine for second brains — turns scattered agent work into a connected Obsidian vault. 100% Swift: SwiftUI app, CLI, and MCP server.
Glint
On-device multimodal search for macOS: photos, video moments, audio, PDFs and docs, by meaning. MLX + EmbeddingGemma 2, with an MCP server for agents.
Code Memory
transform repositories into queryable intelligence
RepoAI MCP
MCP server for the Python Projects to provide context for large databases via semantic precise meaningful vector embeddings
Amnis
☀️ Persistent Memory + RAG + Wiki Compilation for AI Agents — MCP server + Web UI with interactive knowledge graph
Ts RAG
Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp
Nokido
One memory, one set of guardrails and one MCP hub for all your coding agents (Claude Code, Codex CLI, Cline…) — local-first, on your machine. Alpha.
Codesearch
MCP server for semantic code search — AST-aware chunking, hybrid dense+sparse search, 160+ languages
Agent Platform Oci
Agent Framework is an enterprise-grade AI orchestration platform combining multi-agent intelligence with deterministic workflows. Unlike traditional AI solutions, it enables relia…
OpenMemory
TypeScript-powered AI memory that actually works. No more split personalities, no more lost context. Just pure memory continuity.
Engram Synapse
Semantic vector search for Engram memory — pure Go, zero CGO, MCP-native. Formerly 000Erick/synapse.
Ramorie CLI
Long-term memory for AI agents over MCP — CLI and MCP memory server for Claude Code, Cursor, Codex and more. Part of Ramorie.
Eve MCP
Retired: use https://github.com/evememory/eve-client
Filegoblin
Ingesting the messy world, spitting out clean context. Fast, zero-runtime CLI & MCP server converting PDFs, Office docs, images, audio, and websites into clean Markdown for LLMs.
Bara System
기억을 저장·검색·정리하는 개인 메모리 모듈 / Self-hosted personal memory for desktop pet, Discord, and AI agents (MCP)
Sift
Local RAG search and MCP server for AI agents like Claude Code: hybrid BM25 + semantic search with reranking over Markdown and Obsidian notes, PDF, Office files and emails. Backli…
Gus
Local context retrieval for AI coding agents: MCP server + CLI that returns only the code that answers the question
Sub Atlias
Agent harness for Claude Code, Codex, Antigravity, Gemini CLI: shared memory, guards, two-pass verification gate.
Agentic Memory
6-layer persistent memory (sensory, working, episodic, semantic, long-term, procedural) with non-destructive belief revision and injection-safe context synthesis — an MCP server f…
Grove
Self-hosted MCP memory server for AI agents: semantic search, knowledge graphs, and persistent project context. By Bramble Labs Inc.
Rlm MCP
MCP server implementing Recursive Language Model pattern for processing arbitrarily long contexts. Enables Claude Code to work with 1M+ character documents through session-based c…
Cairn
Shared memory for AI coding agents.
Engram Vscode Plugin
VS Code plugin for Engram that adds persistent memory lifecycle hooks to GitHub Copilot sessions.
SDK Typescript
ZiroAgent SDK — production-safe TypeScript agent runtime: durable execution, cost guardrails, replayable traces, MCP-native, sovereign-ready. https://ziroagent.com
Nexus Local Rag MCP
Offline MCP server for local document search — semantic and keyword search over your PDFs, Markdown and text, with no API keys, no cloud or Docker.
Hive
Local-first memory for AI tools: collects chats from ChatGPT, Claude, Gemini, Cursor and more into one encrypted SQLite store that AI assistants search over MCP.
Agentic
An agent is just a loop. This free book and site prove it by building one from scratch with Python and Ollama: tool calling, RAG over a real PDF, layered guardrails, and a live MC…
Ragforge
Hybrid RAG toolkit — BM25 + vectors with RRF, from-scratch HNSW, guardrails, verifiable citations, agentic retrieval and an MCP server. Zero dependencies.
MrKyaw
Principal AI Engineer & Forward-Deployed AI Architect | Enterprise & Solution Architecture | Agentic AI, Multi-Agent Systems, RAG & MCP | MLOps/LLMOps, Evaluation, Observability &…
Contextetech
Open-source European platform for verified AI context: prompts, guardrails, datasets and evals, each with its source and EU compliance. contextetech.com/en/
Arda Suite
Local-first Jarvis assistant, experimental ARDA agent runtime, and shared memory service.
Neurovault
NeuroVault - A self-evolving 3D knowledge brain that runs entirely on your machine. SQLite + FTS5, 31 autonomous circuits, HNSW vector search, Obsidian vault, MCP integration.
Lore
Local-first knowledge OS — your notes, your graph, your AI memory. Watches your files, builds a knowledge graph, and gives Claude/Codex persistent recall. No cloud required.
Confluence MCP
MCP server for Confluence wiki search and content retrieval
Hybrid Rag
Production-grade hybrid RAG in TypeScript — vector + BM25 + reranker across 14 vector stores (Qdrant, Pinecone, Weaviate, pgvector, LanceDB & more) behind one adapter API. Benchma…
Kindle Brain
Turn your Kindle highlights into a personal AI knowledge base. Claude reads your catalog, identifies relevant books, and synthesizes across your actual highlighted passages.
Argus
Framework-free, horizontally-autoscaled multi-agent deep-research engine. Own the loop, not the framework.
Anti Slop
KB-grounded AI consultation with citation discipline. Skills + gates + schema. Methodology at anti-slop.dev.
Saojingling Agent
智能扫地机器人客服助手 - ReAct Agent + RAG + MCP + FastAPI + Redis + SQL
Anchor
Anchor coordination methodology (four-role multi-agent framework). The architectural-invariant gate it spawned is now its own tool → github.com/johnpatrickwarren-oss/sprag
Almanac
Compile domain-specific, freshness-aware knowledge surfaces as CLI tools, MCP servers, and Claude Code Skills.
Sparql MCP
MCP server for SPARQL endpoints. LINDAS-aware, works with any SPARQL 1.1 endpoint / graph database.