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.
Agentvault
Unified memory layer for AI coding agents — searchable by humans (Obsidian) and by AI (MCP). Supports Claude Code, Cursor, Codex, OpenCode.
Spec Driven Development Hackathons
Digital FTE (Full-Time Equivalent) — an AI agent system (Employee) that works 24/7 to manage personal and business affairs
Readwise Integration Obsidian Vault GraphRAG
readwise obsidian integration and a minimal chat UI
Cortex AI
Cortex AI is an engineering template for Claude Code (and others) focused on zero context loss. It features a 4-layer architecture with 12 specialized subagents, custom slash comm…
Omnex
Universal retrieval. Structure-aware. Token-efficient.
Indexa
The local context engine for AI. Summarizes every file, rolls folders up into whole-project context, and serves any AI tool (Claude Code, Cursor, local models) a ranked slice over…
Agenr V0
Local-first memory for AI agents. Extract, store, and recall knowledge from conversation transcripts.
Session Seek
Search your AI coding agent session history with semantic + keyword search via MCP. Supports Claude Code and Codex CLI.
DevAnalystAgent
Self-hosted multi-agent platform that automates data analysis and customer support using MCP tools, agentic RAG, guarded SQL, sandboxed Python, traceable workflows, and evaluation…
Clay Backend Plugin
Claude Code plugin that fills Clay's aggregation gap — collect per-row AI analyses via webhook or CSV into SQLite + semantic search, and let Claude find patterns across all your r…
Aftos Agent Stack
Self-hosted AI agent infrastructure: multiple autonomous agents running concurrently on local hardware, shipping production code with a 30-min/day human review loop.
AI Property Maintenance Advisor
Photograph an equipment data plate, get a cited service brief, or a straight answer that there is no reliable one. v2 is a LangGraph agent with memory, also served as an MCP serve…
LLM Agent Harness
TypeScript runtime turning local LLMs into controlled, observable agents (MCP, tools, traces) + document classification platform
LLM 101
从 0 开始，按照真实小白的认知路径，建立一张从 AI、LLM 到 RAG、Agent、MCP、Coding Agent，再到 AI 产业与硬件的完整知识地图。
Kollectiv
Plan, dispatch and review work across pooled AI workers, with free shared storage (Cloudflare R2/TeraBox), GitHub sync and connectors. Self-hosted, open source, no telemetry.
MNEMOS
Self-editing, bi-temporal memory runtime for AI agents — 6-signal hybrid retrieval, Neo4j knowledge graph, FSRS cognitive decay, sleep consolidation. Not another vector DB wrapper.
Context Engine Agent
面向 Vibe Coding 开发流程，解决"问题记录与经验知识难以复用"的痛点：把踩坑日志与产出笔记沉淀为独立 Skill —— AI 只出草稿、必须人工过审才生效（可 diff / 回滚，带版本与触发词），接入 Agent + RAG 链路供编码智能体直接调用。自研 Router → Retrieve / Tool / Writer 多 Agent 编…
Aegis
AEGIS — Agentic AI Security Mesh: MCP-aware proxy enforcing OWASP LLM Top-10 (injection, secrets, trajectory) with 100% red-team coverage, 74 tests, OTel
Folio Lattice
Company-hosted, provider-neutral platform for safe artifacts and provenance-backed knowledge graphs
SOVARA
Sovara is a local-first AI agent workspace for coding, execution, and knowledge work with real tool use.
AI Agent Engineering Lab
Teaching lab for production-oriented AI agents, RAG, tools, MCP, and workflow engineering.
Agent Memory Skill
Give your coding agent a second memory without a size ceiling. Indexes your agent's memory directory into a local Mnemosyne OS vault, searchable by meaning.
Pkmrag
Local-first Hybrid GraphRAG engine + MCP server for Obsidian vaults — LadybugDB graph + LanceDB vector/BM25 with RRF, no Docker, no cloud.
Molecula
Medicines chatbot that answers with real 3D molecular structures: RAG over FDA drug labels, agent tools over a local chemistry store, Next.js 3D viewer.
Chatbi
基于 LangGraph 多 Agent 编排 + RAG 语义层 + MCP 的自然语言问数平台(Text2SQL):一句中文,秒级返回图表、结论与归因。内置六道 SQL 安全闸门、50 条执行准确率评测与混合检索,支持 Cursor 等 Agent 接入与私有化部署。
AI Image Understanding Content Matching Engine
An end-to-end AI-powered relevance and visual content-matching engine with MCP and RAG capabilities, designed to evaluate, rank, and pair imagery with textual context using multim…
Cortex
Building my second brain that will link to all my useful workflows
Iphone Use Wireless
Wireless iPhone control for Codex via direct WDA. Pair over USB, then operate over Wi-Fi. 无线直连，无需 Appium Server。
Trinity
Trinity: A Triune Architecture for AGI Long-Term Memory
HEIG Kit
Student toolkit: A course knowledge base and study materials, as a CLI, MCP server and Claude Code plugin.
Diagram First Agent
Agent 学习手册：一套以架构图为主线的中文 Agent 教程，它先给出 Agent 平台的分层总览，再沿八级演进逐层展开：ReAct → 工具调用 → 模型网关 → 工具网关 → RAG → 意图识别 → 多 Agent → 平台化。每一章以架构图开篇，配读图步骤、请求时序、故障模式与优化矩阵，并补充内容安全、隐私、合规、测试、发布、长任务可靠性等生产…
Cloudflare Free Web Pi
A free, multi-user web Pi agent workspace on Cloudflare Workers + Durable Objects. 中文优先：文件工作台、独立知识库、分享链接。
Staffwright
Open-source AI staff for small teams — shared memory, knowledge base & document search on your own hardware. Deploy once, reach it from every device. Up to ~20 people. MIT.
Neosian
The state layer for LLM agents: durable conversations, agent-curated memory, skills, a shared board and a ledger of who did what — on storage you own.
Codex Memory
多智能体共用的项目状态控制平面：任务、检查点、代码地图、实时事件流
Saihm Crewai
Portable memory for AI agents, in CrewAI — a StorageBackend your crew owns: enterprise-ready, encrypted client-side, shareable, portable across models, provably erasable (GDPR Art…
Minas Skill
小米智能存储 Samba 文件助手 / Agent skill for Xiaomi Smart Storage file ops over SMB
AI Memory
Production-oriented AI Memory Server with explicit evidence-state memory interaction, deterministic policy, evaluation harness, ADD gating, and canonical duplicate handling.
Univec SDK
Unofficial UniVec API SDKs in 6 languages + CLI + MCP server, generated by Voxgig sdkgen. Not affiliated with UniVec.
Mem Rfm
Outcome-ranked agent memory in one SQLite file with Claude Code integration
Cyberbrain
Cited, trust-tiered, local-first memory for AI coding agents. One native binary: hybrid BM25 + vector recall over plain Markdown notes, trust rings that decide which note wins a c…
Pylance MCP Server
AI powered python - Python MCP Server | Lightning Fast
Retellai MCP Server
MCP server wrapping the Retell AI REST API — 64 tools, 100% API coverage. Deployed via Docker + Traefik on Hostinger VPS.
Langgraph Rag MCP Server
MCP server exposing RAG-based Q&A over LangGraph docs — Qdrant vector search, Dockerized, with a formal groundedness eval harness
Xinliqiu SDK
Unofficial SDK for the OPPO AI 心力球: pair from any computer, sync and decrypt your own recordings, optional ciphertext-only storage, MCP server for agents.
InvoiceForge
Invoices for freelancers and small businesses, with an AI assistant that turns one sentence into an invoice draft. MCP server for Claude & Cursor, multi-currency, PDF export. Buil…
Connoisseur Companion RAG Agentic AI
IBM RAG & Agentic AI Capstone | Multimodal RAG, multi-agent recommendations, and MCP-powered chatbot built with Python, IBM Granite, LangChain, ChromaDB, and Gradio.
Unicloud
Universal multi-cloud management platform & zero-disk transfer mesh. Transfer across local storage, 40+ clouds, and GoPro USB streams with task supervisor, web UI, and FastMCP.
Smartcommerce Agent
基于 LangGraph、RAG、Skills 与 MCP 的电商多智能体客服系统
Advanced AI Chatbot Project
Enterprise Multi-Agent AI Chatbot & Hybrid RAG Platform with LangGraph, FastAPI, MCP, and Qdrant