MCP servers for RAG 515
These MCP servers and clients focus on RAG, matched from their name, description and GitHub topics. MCP Harbor lists 515 of them; the most starred are open-webui (★156,612), graphify (★134,032) and claude-mem (★102,636).
85% open source · mostly Python, TypeScript, JavaScript · 348 updated in the last 30 days · fastest this week: graphify (+6,459 stars)
No servers on this page match that filter. Try one word, such as a product name, or .
open-webui · Python+650 stars this week (+0.4%)
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Graphify-Labs · Python+6,459 stars this week (+5.1%)
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
thedotmack · TypeScript+1,292 stars this week (+1.3%)
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
infiniflow · Go+413 stars this week (+0.4%)
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
ruvnet · TypeScript+2,953 stars this week (+3.9%)
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
headroomlabs-ai · Python+2,109 stars this week (+2.8%)
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
JeecgBoot★ 48,269
jeecgboot · Java+24 stars this week (+0%)
【低代码v2.0，一句话即可生成整个系统】企业级AI低代码平台，一键生成前后端代码甚至整个系统。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖：AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，解决 Java 项目 90% 重复工作，提高效率又不失灵活。
HKUDS · Python+808 stars this week (+1.9%)
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
PageIndex★ 39,590
VectifyAI · Python+353 stars this week (+0.9%)
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
MaxKB★ 23,023
1Panel-dev · Python+36 stars this week (+0.2%)
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
xerj★ 14,291
xerj-org · Rust
Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
claude-context★ 12,644
zilliztech · TypeScript+24 stars this week (+0.2%)
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
MemOS★ 12,064
MemTensor · TypeScript+157 stars this week (+1.3%)
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
voltagent★ 10,864
VoltAgent · TypeScript+44 stars this week (+0.4%)
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
xberg★ 9,441
xberg-io · Rust
Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.
PraisonAI★ 9,287
MervinPraison · Python+46 stars this week (+0.5%)
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
honcho★ 7,754
plastic-labs · Python+96 stars this week (+1.3%)
Memory library for building stateful agents
Yuxi★ 7,475
xerrors · Python+54 stars this week (+0.7%)
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
genkit★ 6,545
genkit-ai · TypeScript
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
learn-ai-engineering★ 6,142
ashishps1+16 stars this week (+0.3%)
Learn AI and LLMs from scratch using free resources
UltraRAG★ 5,731
OpenBMB · Python+3 stars this week (+0.1%)
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
openagent★ 5,712
the-open-agent · Go+14 stars this week (+0.2%)
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org
wigolo★ 5,501
KnockOutEZ · TypeScript+20 stars this week (+0.4%)
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
code-graph-rag★ 5,279
vitali87 · Python+14 stars this week (+0.3%)
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Kiln★ 5,229
Kiln-AI · Python+34 stars this week (+0.7%)
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
DeskcommCRM★ 4,826
melgarafael · TypeScript+169 stars this week (+3.6%)
Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.
LongMemory★ 4,543
CaviraOSS · TypeScript+2 stars this week (+0%)
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
m_flow★ 4,512
FlowElement-xinliuyuansu · Python+1 stars this week (+0%)
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
gptme★ 4,462
gptme · Python+6 stars this week (+0.1%)
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
ragent★ 4,339
nageoffer · Java+56 stars this week (+1.3%)
企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景，从 0 到 1 完整工程实现。
Hyper-Extract★ 4,198
yifanfeng97 · Python+32 stars this week (+0.8%)
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
SimpleMem★ 3,848
aiming-lab · Python+13 stars this week (+0.3%)
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
pipeshub-ai★ 3,846
pipeshub-ai · Python+10 stars this week (+0.3%)
The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.
atmosphere★ 3,823
Atmosphere · Java+3 stars this week (+0.1%)
Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.
ReMe★ 3,679
agentscope-ai · Python+45 stars this week (+1.2%)
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
EvoAgentX★ 3,403
ANative-Lab · Python+18 stars this week (+0.5%)
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
korean-law-mcp★ 2,767
chrisryugj · TypeScript+40 stars this week (+1.5%)
법제처 국가법령정보를 LLM에서 바로 조회하는 MCP 서버. 법령·판례·조례 검색과 인용 검증 | MCP server for Korean law — search statutes, precedents, and ordinances, and verify citations
chrisryugj · TypeScript+189 stars this week (+7.5%)
모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form filling and diff
wanwu★ 2,377
UnicomAI · Go
China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome al
mcp-crawl4ai-rag★ 2,269
coleam00 · Python
Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants
agentset★ 2,111
agentset-ai · TypeScript
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
mcp-memory-service★ 2,038
doobidoo · Python+17 stars this week (+0.8%)
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
py-gpt★ 2,001
szczyglis-dev · Python
Desktop AI Assistant powered by GPT, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and speech recognition, web search, memory, presets, canvas, assistants, themes, computer use. Windo
contextplus★ 1,986
forloopcodes · TypeScript+3 stars this week (+0.2%)
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.
mcp★ 1,952
MicrosoftDocs · TypeScript
Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.
trpc-agent-go★ 1,877
trpc-group · Go+10 stars this week (+0.5%)
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
oxideterm★ 1,727
AnalyseDeCircuit · Rust
AI-native workspace for local shells and remote machines.Zero Webview, zero OpenSSL, zero telemetry, and no app subscription.Written in Rust+GPUI
llmwiki★ 1,713
lucasastorian · Python+18 stars this week (+1.1%)
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
fim-one★ 1,586
fim-ai · Python
Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
arkon★ 1,496
nduckmink · Python+1 stars this week (+0.1%)
Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.
chunkhound★ 1,455
chunkhound · Python+4 stars this week (+0.3%)
Your entire engineering context, deeply understood
nocturne_memory★ 1,408
Dataojitori · Python+14 stars this week (+1%)
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
langchain4j-aideepin★ 1,385
moyangzhan · Java
AI 应用平台（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | AI application platform (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
repobrain★ 1,354
study8677 · Python+14 stars this week (+1%)
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
langchat★ 1,319
LangChat · Vue
LangChat 是Java&LangChain4j生态的开源 AI Agent 应用平台，支持多模型、Agent、知识库 RAG、Skills、MCP 与智能问数。
heymrun · Python+113 stars this week (+9.5%)
Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
nautilus-compass★ 1,254
chunxiaoxx · Python
Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform
ongrid★ 1,219
ongridio · Go
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.
MODULAR-RAG-MCP-SERVER★ 1,187
jerry-ai-dev · Python
A modular RAG (Retrieval-Augmented Generation) system with MCP Server architecture. Using Skill to make AI follow each step of the spec and complete the code 100% by AI.
liliu-z · TypeScript+83 stars this week (+7.8%)
An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.
minima★ 1,056
Minima-AI-Inc · Python+2 stars this week (+0.2%)
On-premises conversational RAG with configurable containers
anymd★ 1,051
SylphxAI · Rust+9 stars this week (+0.9%)
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
cuga-agent★ 1,049
cuga-project · Python
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
selfhost-ai★ 952
kossakovsky · Shell
One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative.
Box★ 940
jegly · Kotlin+20 stars this week (+2.2%)
The most advanced, fully offline client-side AI suite on Android today.
AgentChat★ 924
Shy2593666979 · Python
AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。
MCPHub-Desktop★ 921
skrstop · Rust
MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。
NornicDB★ 916
orneryd · Go+8 stars this week (+0.9%)
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Au
CodeAbra · Python+1 stars this week (+0.1%)
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
llm-server-docs★ 846
varunvasudeva1
End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.
IncarnaMind★ 843
IncarnaMind · TypeScript
Don't trust the AI. Click the source. Every answer shows the page it came from and highlights the quote. Free, open-source desktop app for Mac, Windows and Linux: check your own drafts against your documents, take meeting notes on your computer. Works with ChatGPT, Claude, Gemini or Ollama. A Notebo
Wax★ 805
christopherkarani · Swift+1 stars this week (+0.1%)
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
context-portal★ 765
GreatScottyMac · Python
Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.
ai-code-helper★ 761
liyupi · Vue
2025 年 AI 编程助手实战项目（作者：程序员鱼皮），基于 Spring Boot 3.5 + Java 21 + LangChain4j + AI 构建智能编程学习与求职辅导机器人，覆盖 AI 大模型接入、LangChain4j 核心特性、流式对话、Prompt 工程、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、Web 爬虫、安全防护、Vue.js 前端开发、SSE 服务端推送等企业级 AI 应用开发技术。帮助开发者掌握 AI 时代必备技能，熟悉 LangChain 框架，提升编程学习效率和求职竞争力，成为企业需要的 AI 全栈开发人才。
memora★ 744
agentic-box · Python+2 stars this week (+0.3%)
Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
swarmvault★ 730
swarmclawai · TypeScript
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
calmrocks · Jupyter Notebook
Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, a
cavemem★ 676
JuliusBrussee · TypeScript
Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.
RAGLight★ 673
Bessouat40 · Python
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
nexus-agent★ 667
java-up-up · Java
企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。
AgenticX★ 641
DemonDamon · Python
AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
haiku.rag★ 635
ggozad · Python
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
Kwipu★ 610
benmaster82 · Python
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No clou
docsagent★ 578
docsagent · TypeScript+4 stars this week (+0.7%)
⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.
n8n-claw★ 560
freddy-schuetz · Shell
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templates, Expert Agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script
ethora★ 551
dappros · JavaScript
SDK monorepo for the Ethora chat / messaging platform. (1) Pick an SDK for your frontend stack. (2) Integrate manually or with ethora-setup. (3) Optionally configure app settings, deploy AI agents etc. Server: ethora.com cloud (free), self-hosted (AWS, Docker, Helm, Cloudron) or a managed dedicated
Weave★ 550
liaotxcn · Go
A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.
askimo★ 536
askimo-ai · Kotlin
AI desktop app for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)
ratel★ 521
ratel-ai · Rust
Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
Deuz-SDK★ 519
Deuz-AI · TypeScript
TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemi
octocode★ 513
Muvon · Rust+1 stars this week (+0.2%)
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.
caura★ 509
caura-ai · Python
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
telemem★ 494
TeleAI-UAGI · Python
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
solon-ai★ 467
opensolon · Java
Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
cortexdb★ 467
liliang-cn · Go
AI memory and a knowledge graph in one SQLite file. Pure Go: vectors, RAG, agent memory, RDF/SPARQL, Cypher, 80+ MCP tools. Works without an embedding model.
dsh-memory★ 463
FuRongJun-1999 · Python
白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。
ai4j★ 436
LnYo-Cly · Java
Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...),unified AI service(image/video/audio...), Tool Calling, MCP, RAG, SKILLS,Agent Runtime, A2A, agent blueprint, agent harness, and a built-in Coding Agent CLI/TUI/ACP.
marm-memory★ 422
Lyellr88 · Python
Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.
mcp-local-rag★ 420
shinpr · TypeScript+6 stars this week (+1.4%)
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.
aura★ 404
mezmo · Rust+6 stars this week (+1.5%)
AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.
pageindex-mcp★ 404
VectifyAI · TypeScript
MCP server for PageIndex. PageIndex is a vectorless reasoning-based RAG system which uses multi-step reasoning and tree search to retrieve information like a human expert would.
EDDI★ 387
labsai · Java
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 19+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.
ai-localbase★ 383
veyliss · Go
一个本地优先的AI知识库系统（RAG），用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf（文本）、xlsx、cvs类型。支持mcp服务
TrueMemory★ 382
buildingjoshbetter · Python+1 stars this week (+0.3%)
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
agentica★ 357
shibing624 · Python
One person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and self-evolving skills. 一个人，一支 Agent 团队：支持多终端协作、持久记忆与技能自进化的 AI Agent 框架。
fojin★ 352
xr843 · Python
Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search
GoogleCloudPlatform · Python
Demo of a customer service agent (Cymbal Air) using LangGraph, Tools, and RAG to interact with Google Cloud Databases via MCP Toolbox.
tw-legal-rag★ 332
aa0101181514 · Python+4 stars this week (+1.2%)
台灣法律 MCP 伺服器 + CLI（免費、免註冊、免 API key）：2,270 萬筆裁判書、行政函釋、憲法法庭裁判，附引用查核。Free Taiwan legal MCP server for Claude/ChatGPT/Codex: bring your own LLM, retrieval-only.
rushdb★ 325
rush-db · TypeScript
RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.
SourceWeft★ 310
SourceWeft · TypeScript
Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure. Free to use GPT 6: https://SourceWeft.com/
knowledge-rag★ 300
lyonzin · Python
Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.
rust-docs-mcp-server★ 299
Govcraft · Rust
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.
engrim★ 299
timgordontg · Python
The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, and OpenCode. Zero cloud lock-in.
orchestkit★ 298
yonatangross · TypeScript
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
backlot★ 298
brekkylab · Python
A local emulator for enterprise SaaS APIs — Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and more — with the real response shapes, pagination, auth and per-document ACLs, over a corpus you supply.
pmb★ 286
oleksiijko · Python
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
guaardvark★ 282
guaardvark · Python
Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.
deepcontext-mcp★ 278
Wildcard-Official · TypeScript
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agents for faster, smarter context on large codebases.
uteke★ 275
codecoradev · Rust
🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with semantic embeddings. Single Rust binary, zero config, fully offline.
YourMemory★ 270
sachitrafa · Python
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
santosomar · Python
Hands-on code, labs, and reference material by Omar Santos for building, securing, and operating AI agents in cybersecurity.
empirica★ 251
EmpiricaAI · Python
Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond
ArcRift★ 247
Eshaan-Nair · TypeScript
Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
PharosRAG★ 241
Laurent00TT · Python
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
mcp-victoriametrics★ 240
VictoriaMetrics · Go
The implementation of Model Context Protocol (MCP) server for VictoriaMetrics
ksor★ 232
panaversity · TypeScript
KSoR (Knowledge System of Record) is an open-source SDK for building governed, authoritative knowledge systems for humans and AI agents. It is a foundation of an AI-native knowledge platform.
synaplan★ 219
metadist · PHP
Open-source, self-hosted AI platform (PHP/Symfony): chat with any model, RAG over your docs, embeddable widget, MCP — see the cost of every answer. Apache-2.0.
MakerAi★ 215
gustavoeenriquez · Pascal
The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI, Claude, Gemini, Ollama, and more. Delphi 10.4+ (limited), full support from Delphi 12 Athens.
ClawMem★ 212
yoloshii · TypeScript
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
ETOS-LLM-Studio★ 211
Eric-Terminal · Swift
A native LLM client for iOS & Apple Watch. Run local GGUF models offline via llama.cpp, or connect to OpenAI/Claude/Gemini. Features local RAG, Model Context Protocol (MCP) tools, Siri Shortcuts, and cross-device sync. Built with Swift.
mangaba_ai★ 207
Mangaba-ai · Python
Framework profissional de orquestracao multi-agente em Python: crews, flows orientados a eventos, ReAct, RAG, memoria, MCP/A2A e multi-provider LLM
notebooklm-mcp★ 206
roomi-fields · TypeScript
Google Gemini Notebook (formerly NotebookLM) over MCP + a local HTTP REST API. Citation-backed Q&A, full Studio generation, chat history, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.
RobThePCGuy · Python
USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with skills and autonomous agents.
corpusos★ 205
Corpus-OS · Python
Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.
mengram★ 204
alibaizhanov · Python
Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.
exstruct★ 204
harumiWeb · Python
Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.
smart-coding-mcp★ 200
omar-haris · JavaScript
An extensible Model Context Protocol (MCP-Local-MRL-RAG-AST) server that provides intelligent semantic code search for AI assistants. Built with local AI models, inspired by Cursor's semantic search.
meilisearch-mcp★ 197
meilisearch · Python
A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces.
flexible-graphrag★ 194
stevereiner · Python
Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch DBs. 14 data sources, 10 auto sync: Alfresco, Nuxeo, etc. KG auto-building, Ontologies, LLMs, Docling, LlamaParse, LiteParse, GraphRAG, RAG, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends
trace-mcp★ 193
nikolai-vysotskyi · TypeScript
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity
memov★ 193
memovai · Python
Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for every coding agents by MCP. Self-evolution for skills.
OWASP · Python
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
TAgent★ 187
pengmoubuaixuexi · Java
TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。 它不是只封装一次模型调用，而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批、执行中干预，到 SSE 流式输出和全链路观测的完整过程。
samyama-graph★ 184
samyama-ai · Rust
Rust graph-vector database: OpenCypher (99.9% of evaluated TCK scenarios pass), vector search, graph algorithms, RESP + HTTP. LDBC SNB Interactive and BI complete; 1B edges on one machine.
AgenticGoKit★ 182
AgenticGoKit · Go
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agnostic, event-driven, with multi-agent workflows, MCP tool discovery, and production-grade observability.
searxNcrawl★ 181
DasDigitaleMomentum · Python
Open-source MCP server that gives AI agents web search (SearXNG) and clean Markdown crawling of pages, whole sites and logged-in areas. Self-hosted, no API key. Firecrawl-compatible API planned.
mneme★ 176
slow-stack · JavaScript
🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall (keyword/vector/BM25/entity), and a memory panel. 10 model tools, MCP server, CLI.
Sibyl-Memory★ 173
Sibyl-Labs · Python
Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.
engraph★ 172
devwhodevs · Rust
Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults.
Forge★ 172
nihalashetty · Python
Forge is an open-source, self-hosted alternative for visually building and shipping AI agents and workflows without giving up control of your infrastructure.
context-engineering★ 171
bonigarcia · Python
Context Engineering: Build Consistent, Accurate, Predictable AI Systems
self-hosted-ai-stack★ 170
hwdsl2 · Shell
Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authentication, lightweight stacks, optional HTTPS and NVIDIA GPU support
eShopLite★ 168
Azure-Samples · C#
eShopLite is a set of reference .NET applications implementing an eCommerce site with features like Semantic Search, MCP, Reasoning models and more.
Axon.MCP.Server★ 166
ali-kamali · Python
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants
bgts-context-engine★ 166
bgts-ai-org · Python
Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.
akb★ 163
dnotitia · Python
AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.
andylow92 · TypeScript
Self-improving, AI-native markdown vault you hand to an AI agent. GitHub-style file tree + Notion editing, exposed to Claude/Cursor via a built-in MCP server (24 tools): semantic & hybrid search, RAG, cited answers. Learns your voice from your edits; human-approved review queue. Local-first .md.
arbor★ 161
Anandb71 · Rust
Graph-native code intelligence that replaces embedding-based RAG with deterministic program understanding.
neurolink★ 157
juspay · TypeScript
The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across three inference types: generate, stream, and a calibrated decide (via TypeSafe Jev). MCP-native, voice (TTS/STT/realtime), RAG, memory, file processors. Powers Tara, Yama and Clairvoyance a
pdf-mcp★ 155
jztan · Python
MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: agentic RAG with hybrid semantic + keyword search, selective page reads, tables, images, OCR, chart data, and multi-column/CJK layouts.
DM-Code-Agent★ 154
hwfengcs · Python
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.
mnemosyne★ 151
28naem-del · TypeScript
Local-first long-term memory for AI agents: an MCP server, TypeScript SDK, CLI and HTTP service over one SQLite file. Evidence-backed recall, corrections that retire stale guidance, temporal history. 409/500 on LongMemEval-S with the misses published.
kaas★ 151
bybit-exchange · Python
Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.
apowerb★ 150
apowerb · Python
The open-source agentic framework to build, orchestrate, and operate production AI agents.
WaLiAPI★ 147
fuzhengwei · Rust
WaLiAPI 是一款本地运行的 LLM API 网关桌面软件（Tauri 2 + React + Rust）。支持各类 LLM 厂商渠道接入、Ollama 自部署模型、CPA 方式 ChatGPT 渠道接入，统一支持 Chat Completions / Responses / Anthropic Messages 三协议转换使用。内置安全审计引擎、知识库 RAG（HNSW + FTS5 混合检索）、Wiki 知识引擎和 MCP Server（29 个工具），配合 Codex、Claude Code、Gemini CLI 等 AI 编程工具使用。
spring-ai-playground★ 145
spring-ai-community · Java
Safe local execution layer for AI agent tools. Build and test-run MCP tools (no pass, no run), serve them from a built-in MCP server, and use them in Agentic Chat with RAG, human-in-the-loop approval, and built-in observability. Cross-platform desktop app powered by Spring AI.
recruitops-agent★ 145
849879772 · Python
Local-first recruitment intelligence and application operations agent
vellium★ 140
tg-prplx · TypeScript
Local-first desktop AI workbench for roleplay, multi-character chat, long-form writing, RAG, MCP tools, plugins, and local models.
dkg★ 140
OriginTrail · TypeScript
OriginTrail Decentralized Knowledge Graph (DKG) is a decentralized knowledge infrastructure for multi-agent AI memory — enabling agents to publish, verify, and query shared knowledge as cryptographically verifiable graph assets across a peer-to-peer network.
heimdall★ 137
ArihantDeva · JavaScript
A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.
airbyte-agent-sdk★ 136
airbytehq · Python
🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.
mcp-local-rag★ 134
nkapila6 · Python
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
docmancer★ 133
docmancer · Python
Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.
OGAD★ 132
off-grid-ai · TypeScript
Your private, on-device personal AI assistant for macOS and Windows. Chat, create, search files, and connect tools with local models. Includes an OpenAI-compatible API. Opt-in Pro sees, remembers, reflects, and acts with your approval. No cloud or account.
ai-dfir-toolkit★ 129
depalmar · Python
A vendor-neutral collection of Sigma, YARA, and Suricata rules for detecting compromise of LLM applications, MCP servers, ML supply chains, AI infrastructure, AI-powered insider threats, and RAG/vector database attacks.
llm-wiki-memory★ 129
ctxr-dev · JavaScript
Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.
circuitron★ 129
Shaurya-Sethi · Python
Circuitron: Agentic PCB Design Accelerator — Generate, plan, and layout circuits from natural language prompts.
EimanTahir027 · Python
An MCP-powered agentic RAG system that transcribes, indexes, and intelligently queries audio content using advanced retrieval-augmented generation.
agentkeeper★ 122
Thinklanceai · Python
Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.
apple-rag-mcp★ 121
BingoWon · TypeScript
Apple developer docs and WWDC transcripts with RAG retrieval and Jev relevance ranking.
vera★ 120
VeraTools · Rust
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.
model-compose★ 120
hanyeol · Python
Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.
FrontAgent★ 120
ceilf6 · TypeScript
Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、VS Code 插件、桌面端、MCP 服务、RAG、Skills、SDD、浏览器自动化与 LoRA 规划模型
OpenDocuments★ 120
joungminsung · TypeScript
Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.
agent-brain★ 119
SpillwaveSolutions · Python
Local-first RAG memory for AI agents: hybrid + GraphRAG search, MCP server with OAuth 2.1, plugin for Claude Code / OpenCode / Codex.
Parrot★ 118
turantekin · Swift
Meeting recorder for your Mac with a live AI assistant. On-device transcription, answers from your own docs mid-call. Local-first and open source.
gno★ 118
gmickel · TypeScript
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.
bansalkanav · Jupyter Notebook
Learn GenAI and Agentic AI from Zero to Production
agenticos★ 117
vstorm-co · Python
Open-source AI teammates for your company. The self-hosted agent layer: build, run and govern AI agents on your own servers, models and rules. RAG, skills, a real browser, 4,700+ MCP servers and an API, with budgets, approvals and an audit trail. Apache-2.0, built on Pydantic AI.
deepmem★ 114
deepmemteam · Python
Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.
basemind★ 112
Goldziher · Rust
Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.
docsmint★ 110
HiAi-gg · TypeScript
Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsMint Cloud.
ai-microcore★ 108
Nayjest · Python
A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.
doc-scraper★ 107
Sriram-PR · Go
Go web crawler to scrape documentation sites and convert content to clean Markdown for LLM ingestion (RAG, training data)
metronix-memory★ 107
mtrnix · Python
Self-hosted AI agent memory — MCP memory server with durable recall for agents
1c-ai-connector★ 106
andromanpro · 1C Enterprise
ИИкона — AI-коннектор для 1С:Предприятие 8.3: LLM-провайдеры, агентская петля (function calling), RAG, MCP-сервер, мониторинг ошибок с ИИ-анализом, генератор диаграмм
schemagate★ 105
ashishsinha1602 · Python
Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware table pruning for LangChain, MCP and any SQL agent. Postgres, Oracle, MySQL, SQL Server. 75% fewer prompt tokens.
MDalamin5 · Jupyter Notebook
This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.
pluggedin-app★ 103
VeriTeknik · TypeScript
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
Micro-Agent★ 101
fdueblab · Python
A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架
zlibrary-mcp★ 101
rookslog · Python
MCP server for Z-Library: search, download, and process books into RAG-ready text for AI assistants (Claude Code, Claude Desktop, Cline, RooCode)
sqlmap-skynet★ 100
drcrypterdotru · Python
SQLMap with Autonomous AI, phased workflows, RAG memory, and MCP Agent Tools
matryca-plumber★ 100
MarcoPorcellato · Python
Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.
continuum★ 98
pouyahasanamreji · TypeScript
Shared memory + orchestration for your coding agents — one MCP server, persistent vector memory, agent registry
libre-webui★ 97
libre-webui · TypeScript
A local-first workspace for chat, private knowledge, artifacts, and isolated model-driven work. Self-hosted. Provider-flexible. Apache 2.0.
dna-memory★ 96
AIPMAndy · Python
Claude Code 记忆 / AI Agent 记忆 MCP：本地优先的统一记忆层，Codex、Claude Code、Hermes 共用一套 Markdown 记忆｜Local-first shared memory MCP server for Claude Code, Codex & AI agents
loci★ 94
IvenKooLab · Python
Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.
toolmaker-agent★ 92
phcp-tech
Toolmaker Agent is an Agentic AI SDLC platform — humans and agents collaborate on the same structured data model.
seerai★ 91
dralkh · TypeScript
Zotero AI plugin Research assistant for Zotero 10. Chat with your library, run federated scholarly search, RAG, OCR, systematic reviews, and manage cloud storage. Includes standalone MCP, Agentic capabilities, and skills library.
omerbsezer · Python
This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands Agents, Google Agent Development Kit, Fundamentals.
lumen★ 90
ahmedEid1 · Python
Lumen — learner-owned AI education platform. Tell the AI what you want to learn: it builds you a private course in ~a minute, tutors you with course-scoped RAG + citations, and lets you share, clone & remix via a moderated catalog. BYOK, custom no-LangChain multi-agent orchestrator, golden evals in
codealive-mcp★ 90
CodeAlive-AI · Python
Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.
bike4mind★ 90
Bike4Mind · TypeScript
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.
NEDONION · Java
A self-hosted RAG agent platform for knowledge management, LLM orchestration, and MCP tool integration. 面向知识管理、LLM 编排与 MCP 工具集成的自托管 RAG 智能体平台。
takeshy · TypeScript
All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully private, no cloud required.
DocSentinel★ 88
arthurpanhku · Python
MCP server for AI agent for cybersecurity: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge base,Risks, compliance gaps, remediations.
CiteProof-AI★ 88
Aryan-Pardeshi · Python
Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim checks, and reproducible exports with human oversight.
agent-search★ 86
brcrusoe72 · Python
Self-hosted search API + MCP server for AI agents. Bundles SearXNG. Zero API keys, one-command deploy. Open-source alternative to Tavily, Exa, and Serper.
pdfmux★ 84
NameetP · Python
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
ShibaClaw★ 84
RikyZ90 · Python
🐕 Self-hosted security-first AI agent · 28 providers · 11 chat channels · WebUI · 3-level memory · task-schedule · automation · skills · MCP
antares★ 84
enowdev · Go
Antares: a self-hosted AI pentest agent and assistant in one binary. Authorized penetration testing with security specialists, 7,000+ procedures and reports, plus files, shell, a real browser, memory and RAG.
DecisionNode★ 83
decisionnode · TypeScript
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
YanpengQi7 · TypeScript
Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.
MySQL_MCP★ 81
guangxiangdebizi · TypeScript
这是一个功能强大且易用的MySQL数据库MCP（Model Context Protocol）服务器，让你的AI助手可以安全地进行完整的数据库操作，支持多数据库连接管理、增删改查、事务管理和智能回滚功能。
jevcrawl★ 80
RayenMlayeh · Python
MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than letting Claude crawl.
Kompl★ 79
tuirk · TypeScript
A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zero upkeep.
maximem-ai · Python
The memory layer for production AI agents. Python + JS SDKs, 24 framework integrations, MCP server.
ruvnet-brain★ 76
stuinfla · JavaScript
RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.
osk-system★ 76
lpaiu-cs · Python
Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.
vinagent★ 75
datascienceworld-kan · Python
Vinagent is a comprehensive Agentic AI library that helps integrate tools, memory, workflows, and observability.
excel-parser★ 75
knowledgestack · Python
XLSX parser for LLMs, RAG, LangChain, LangGraph, CrewAI, Claude, MCP — turns Excel (.xlsx) into citation-ready JSON with formulas, charts, dependency graphs, and token-counted chunks. Open-source Python library (MIT).
LIA-Assistant★ 75
jgouviergmail · Python
Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages)
mcp-agent★ 74
Haohao-end · Python
A modular Python framework implementing the Model Context Protocol (MCP). It features a standardized client-server architecture over StdIO, integrating LLMs with external tools, real-time weather data fetching, and an advanced RAG (Retrieval-Augmented Generation) system.
vbcherepanov · Python
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.
Agent-Fusion★ 73
krokozyab · Kotlin
Agent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documentation (Markdown, Word, PDF). Query your codebase from code agents without hallucinations. Runs 100% locally, includes a lightweight embedding model, and optional multi-agent task orche
kglite★ 73
kkollsga · Rust
Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.
SirChatalot★ 72
sazonovanton · Python
A Telegram bot that proves you don't need a body to have a personality. Works with any OpenAI-compatible LLM; agentic tools, MCP, RAG over your files, memory, vision, voice and image generation.
Yan-AutoTravel-★ 71
YongyanLiututu · Java
AI Travel Planner 是一个基于 Spring Boot + Spring AI 的后端与 Vue 3 + Vite 的前端组合项目，面向智能旅游场景，提供 智能行程规划、多模态问答与个性化推荐 能力。 系统集成了 MCP (Model Context Protocol) 工具链，支持从 自然语言理解 → RAG (Retrieval-Augmented Generation) → 多 Agent 协同 → 个性化生成 的完整 AI 应用流程。同时配套 CSV 向量化预处理脚本，实现高效的数据清洗、向量化与检索。
baml-agents★ 70
Elijas · Python
Building Agents with LLM structured generation (BAML), MCP Tools, and 12-Factor Agents principles
agentcairn★ 68
ccf · Python
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
minirag-mcp★ 68
sfrangulov · Python
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. Nothing leaves your machine.
enowxcli★ 68
enowdev · Rust
An open-source AI coding agent for your terminal: specialist agents that plan, build, review and test, with built-in code search and any model provider. One binary.
claude-mem-lite★ 67
sdsrss · JavaScript
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
yantrikdb★ 67
yantrikos · Rust
Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.
research-hub★ 66
WenyuChiou · Python
AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.
zettelforge★ 66
ThreatRecall · Python
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
mcp-automem★ 65
verygoodplugins · TypeScript
MCP client for AutoMem — give Claude, Cursor, Codex, and other MCP tools durable graph+vector memory across conversations.
lilbee★ 65
tobocop2 · Python
The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio nee
memory-vault★ 65
MihaiBuilds · Python
A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.
zeph★ 65
bug-ops · Rust
A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed tools. MCP · ACP · A2A. One Rust binary.
devrag★ 64
tomohiro-owada · Go
Markdown vector search MCP server for Claude Code. Natural language search for markdown files using multilingual-e5-small embeddings.
MCP-Markdown-RAG★ 64
Zackriya-Solutions · Python
A semantic search engine for markdown files based on MCP architecture.
clangd-graph-rag★ 63
2015xli · Python
Source code graph RAG (GraphRAG) for C/C++ development based on clang/clangd
ctxvault★ 63
Filippo-Venturini · Python
Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control and query.
rag-app-on-aws★ 62
genieincodebottle · Python
Build and deploy a full-stack RAG app on AWS with Terraform, using free tier Gemini Pro, real-time web search using Remote MCP server and Streamlit UI with token based authentication.
OmniMem★ 61
richarvey · Rust
Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.
vobase★ 61
vobase · TypeScript
The app framework built for AI coding agents. Own every line. Your AI already knows how to build on it.
Fractera · TypeScript
Deploys your OS, databases, and SSL on your VPS in just 10 minutes. Orchestrates a team of AI agents for coding, marketing, and sales. The built-in optimizer saves up to 90% on token costs, letting you build and manage your online business directly through chat. Fully open-source.
MetaSearchMCP★ 60
gefsikatsinelou · Python
Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.
webfetch★ 60
firish · Python
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.
deepcloak★ 60
Mrbaeksang · Python
Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.
ctxd★ 59
ctxd-dev · Python
Your AI agents can't see your files. ctxd connects your cloud data and makes it searchable via API, CLI, or MCP.
vidxp★ 59
grayhatdevelopers · Python
VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.
msdanyg · TypeScript
Give Claude semantic memory of your Obsidian vault — local semantic search over Smart Connections embeddings via MCP. Multi-vault, block-level, 100% private.
knowledge-mcp★ 59
olafgeibig · Python
A MCP server that is a locally running knowledge base with a hybrid vector and graph RAG engine using LightRAG
stashseek★ 58
deequoique · Python
Chat with the videos you've saved: evidence-backed answers with timestamps that jump back to the source. Browser extension + MCP, self-hostable. 和你收藏的视频对话，答案带时间戳，一键回到原视频。
TomoriBot★ 58
Bredrumb · TypeScript
A highly customizable personal AI assistant for Discord featuring smart agentic AI features such as memory, personas, tool usage, and more! ｜ 長期記憶やペルソナ、ツール連携を完備。 次世代の「自律型AIエージェント」Discordボット！
snippets★ 58
cheolwanpark · Python
Automatically extracts, processes, and indexes code snippets from GitHub repositories into a searchable vector database.
Java-Agent-Study★ 58
zeroaihub · Java
从 Java 开发者到 AI Agent 工程师的 30 天实战之路 | Spring Boot + Spring AI + MCP + Multi-Agent
ocpp-rag★ 58
nader0913 · Python
MCP server with RAG knowledge base for OCPP 1.6, OCPP 2.0.1, and EV charging standards
qdrant-loader★ 56
cbtw-apac · Python
Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assi
Memory-Plus★ 56
Yuchen20 · Python
🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to ac
Frequently asked questions
What is the best MCP server for RAG?
By GitHub stars, the most adopted RAG entries on MCP Harbor are open-webui (★156,612), graphify (★134,032) and claude-mem (★102,636). Popularity is a starting point only. Check whether the project is maintained by the vendor, when it was last updated and which permissions it needs, then try it on a test account before giving it real credentials.
How do I add an MCP server for RAG?
Open a listing below, copy the package name or server URL from its README, and add it to your client: claude mcp add in Claude Code, mcpServers in Cursor or Claude Desktop, servers in VS Code. The install guide has copy-paste config for each one.
How many RAG MCP servers are there?
MCP Harbor currently lists 515 projects that match RAG. 348 of them were updated in the last 30 days and 85% of the GitHub projects carry an open-source license. The list is rebuilt every day from the official MCP Registry, GitHub, npm and PyPI, so a new server shows up here on the first daily update after it meets the listing criteria.
MCP servers for other tools
Data last updated . Stars and downloads are refreshed every day from GitHub and npm.