#rag-memory · IA & ML
RAG & mémoire des IA
Chaînes de génération augmentée par recherche (RAG) et couches de mémoire qui permettent aux agents de se souvenir.
Sur les dernières 24 heures, en tête : RustXNG (+316), cs329z-chinese (+71) et graphmemory (+36). Les 59 projets classés ont gagné 6 477 étoiles.
Mis à jour le 2 nov., 14:38 UTC · classé toutes les heures à partir des étoiles quotidiennes de GitHub
Mis à jour il y a 16 min
Classement sur 24 h
- 1sahenjp/RustXNG Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later)Gagnées en 24 h +316 Score 17,1 Total 656
- 2wanghao-SunSky/cs329z-chinese 斯坦福 Stanford CS329Z Engineering AI Agents 中文教程:面向 Python 开发者的 AI 智能体课程,19 讲与 4 项实践,涵盖 LLM、RAG、工具调用、记忆、多智能体、评测与安全。完整 Markdown、在线与离线 HTML。Chinese course notes.Gagnées en 24 h +71 Score 3,7 Total 432
- 3gh9ko8y/graphmemory Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)Gagnées en 24 h +36 Score 3,6 Total 130
- 4thedotmack/claude-mem 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 + MoreGagnées en 24 h +1,2 k Score 3,5 Total 110 k
- 5patchy631/ai-engineering-hub In-depth tutorials on LLMs, RAGs and real-world AI agent applications.Gagnées en 24 h +685 Score 3,4 Total 40,9 k
- 6SLEEPYBQ/MemoSync Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.Gagnées en 24 h +42 Score 3,1 Total 222
- 7xerj-org/xerj AI search engine and MCP server for bots and 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.Gagnées en 24 h +377 Score 2,8 Total 18,8 k
- 8weir36/novel-config-copilot 网文平台资源配置决策助手:GraphRAG 两阶段检索 + ReAct Agent + 规则引擎兜底,方案合法率 60%→100%Gagnées en 24 h +26 Score 2,6 Total 26
- 9HKUDS/DeepTutor DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.Gagnées en 24 h +558 Score 2,4 Total 54,1 k
- 10peterpoal134/memory-brain 给 AstrBot 的可落地 AI 记忆与生活层:五类记忆、混合检索、遗忘治理、情绪边界、自主生活循环。不覆盖人格。Gagnées en 24 h +24 Score 2,4 Total 107
- 11vectorize-io/hindsight Hindsight: Agent Memory That LearnsGagnées en 24 h +476 Score 2,0 Total 58 k
- 12anonnerdfrenzy/survival-llm A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.Gagnées en 24 h +62 Score 1,8 Total 1,3 k
- 13 Gagnées en 24 h +32 Score 1,7 Total 373
- 14BotHarness/DeepSeekBot Open-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins.|基于 DeepSeek Harness 的开源 GrokBot 平替:有长期记忆的个人 AI Bot 团队,支持多 Bot 协作、身份权限与插件生态扩展。MIT.Gagnées en 24 h +34 Score 1,5 Total 535
- 15Graphify-Labs/graphify 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.Gagnées en 24 h +448 Score 1,2 Total 141 k
- 16axoviq-ai/synthadoc Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.Gagnées en 24 h +30 Score 0,7 Total 1,8 k
- 17DemonDamon/AgenticX 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).Gagnées en 24 h +21 Score 0,7 Total 887
- 18666ghj/MiroFish A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物Gagnées en 24 h +177 Score 0,6 Total 83,4 k
- 19SuanmoSuanyangTechnology/MemoryBear MemoryBear Equip AI with human-like memory capabilityGagnées en 24 h +55 Score 0,6 Total 9,3 k
- 20akitaonrails/ai-memory Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendorsGagnées en 24 h +67 Score 0,6 Total 14,9 k
- 21datawhalechina/hello-agents 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程Gagnées en 24 h +139 Score 0,5 Total 85,8 k
- 22TencentCloud/Octop A smarter, self-hosted AI assistant — multi-user, multi-agent.Gagnées en 24 h +50 Score 0,5 Total 11,5 k
- 23bojieli/ai-agent-book 《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码Gagnées en 24 h +106 Score 0,4 Total 57 k
- 24WenyuChiou/awesome-agentic-ai-zh A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。Gagnées en 24 h +37 Score 0,4 Total 8,4 k
- 25Asymptote-Labs/agent-beacon The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBuGagnées en 24 h +21 Score 0,4 Total 3 k
- 26Tencent/WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Gagnées en 24 h +71 Score 0,4 Total 36,3 k
- 27lfnovo/open-notebook An Open Source implementation of Notebook LM with more flexibility and featuresGagnées en 24 h +73 Score 0,4 Total 41,3 k
- 28datawhalechina/all-in-rag 🔍大模型应用开发实战一:RAG 技术全栈指南,在线阅读地址:https://datawhalechina.github.io/all-in-rag/Gagnées en 24 h +38 Score 0,3 Total 12,8 k
- 29volcengine/OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.Gagnées en 24 h +68 Score 0,3 Total 41,4 k
- 30ruvnet/ruflo 🌊 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 IntegratedGagnées en 24 h +89 Score 0,3 Total 80,6 k
- 31headroomlabs-ai/headroom 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.Gagnées en 24 h +83 Score 0,3 Total 78,6 k
- 32adongwanai/AgentGuide https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习|数据合成Gagnées en 24 h +31 Score 0,3 Total 11,6 k
- 33microsoft/ai-agents-for-beginners 18 Lessons to Get Started Building AI AgentsGagnées en 24 h +74 Score 0,3 Total 78,7 k
- 34didilili/ai-agents-from-zero 🚀 2026 最系统的 AI Agent 速成指南|智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化Gagnées en 24 h +20 Score 0,3 Total 5,8 k
- 35langchain-ai/langgraph Build resilient agents.Gagnées en 24 h +50 Score 0,2 Total 44,3 k
- 36promptfoo/promptfoo Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.Gagnées en 24 h +36 Score 0,2 Total 26,7 k
- 37virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.Gagnées en 24 h +41 Score 0,2 Total 36,7 k
- 38nashsu/llm_wiki LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。Gagnées en 24 h +29 Score 0,2 Total 21,3 k
- 39langgenius/dify Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.Gagnées en 24 h +75 Score 0,2 Total 160 k
- 40semantica-agi/semantica Graph-Native Infrastructure for Context and Accountable AI SystemsGagnées en 24 h +22 Score 0,2 Total 14,4 k
- 41ConardLi/garden-skills ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.Gagnées en 24 h +21 Score 0,2 Total 13,5 k
- 42mem0ai/mem0 The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.Gagnées en 24 h +45 Score 0,2 Total 68,3 k
- 43Shubhamsaboo/awesome-llm-apps 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.Gagnées en 24 h +65 Score 0,2 Total 144 k
- 44PaddlePaddle/PaddleOCR Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.Gagnées en 24 h +51 Score 0,2 Total 92,1 k
- 45infiniflow/ragflow RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.Gagnées en 24 h +49 Score 0,2 Total 93,4 k
- 46comet-ml/opik Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.Gagnées en 24 h +24 Score 0,2 Total 23,1 k
- 47getzep/graphiti Build Real-Time Knowledge Graphs for AI AgentsGagnées en 24 h +27 Score 0,1 Total 32,4 k
- 48unclecode/crawl4ai Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord https://discord.gg/VuxzM8mtfGagnées en 24 h +42 Score 0,1 Total 86,8 k
- 49liyupi/ai-guide 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude / GLM)、最新 AI 资讯、Prompt 提示词大全、AI 知识百科(Agent Skills / RAG / MCP / A2A)、AI 编程教程(Harness Engineering)、AI 工具用法(Cursor / Claude Code / TRAE / Codex / Copilot)、AI 开发框架教程(Spring AI / LangChain)、AI 产品变现指南,帮你快速掌握 AI…Gagnées en 24 h +21 Score 0,1 Total 21,8 k
- 50open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...)Gagnées en 24 h +53 Score 0,1 Total 158 k
- 51langchain-ai/langchain The agent engineering platform.Gagnées en 24 h +50 Score 0,1 Total 149 k
- 52garrytan/gbrain Garry's Opinionated OpenClaw/Hermes Agent BrainGagnées en 24 h +22 Score 0,1 Total 31,4 k
- 53ItzCrazyKns/Vane Vane is an AI-powered answering engine.Gagnées en 24 h +24 Score 0,1 Total 38 k
- 54TencentCloud/TencentDB-Agent-Memory TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.Gagnées en 24 h +20 Score 0,1 Total 30,3 k
- 55datawhalechina/happy-llm 📚 从零开始构建大模型Gagnées en 24 h +21 Score 0,1 Total 34,7 k
- 56tirth8205/code-review-graph Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.Gagnées en 24 h +20 Score 0,1 Total 32,6 k
- 57Mintplex-Labs/anything-llm Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experienceGagnées en 24 h +25 Score 0,1 Total 67,8 k
- 58MemPalace/mempalace The best-benchmarked open-source AI memory system. And it's free.Gagnées en 24 h +20 Score 0,1 Total 60,2 k
- 59dair-ai/Prompt-Engineering-Guide 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.Gagnées en 24 h +23 Score 0,1 Total 79,8 k
Émergents en RAG & mémoire des IA Semaines passées : 26 oct.19 oct.