#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.
Cette semaine (27 oct. – 2 nov.), en tête : survival-llm (+1 212), RustXNG (+578) et DeepTutor (+10 455). Les 242 projets classés ont gagné 71 148 étoiles, 14 % de plus que la semaine précédente.
Mis à jour le 2 nov., 13:34 UTC · classé toutes les heures à partir des étoiles quotidiennes de GitHub
Mis à jour il y a 8 min
Classement de la semaine
- 1anonnerdfrenzy/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 7 j +1,2 k Score 121,2 Total 1,3 k
- 2sahenjp/RustXNG Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later)Gagnées en 7 j +578 Score 57,8 Total 615
- 3HKUDS/DeepTutor DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.Gagnées en 7 j +10,5 k Score 50,0 Total 54,1 k
- 4wanghao-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 7 j +418 Score 41,8 Total 418
- 5 Gagnées en 7 j +367 Score 36,7 Total 367
- 6thomasunise/casecite CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.Gagnées en 7 j +239 Score 23,9 Total 244
- 7SLEEPYBQ/MemoSync Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.Gagnées en 7 j +220 Score 22,0 Total 222
- 8thedotmack/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 7 j +7 k Score 21,7 Total 110 k
- 9xerj-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 7 j +2,5 k Score 20,0 Total 18,7 k
- 10 Gagnées en 7 j +617 Score 17,1 Total 1,9 k
- 11vectorize-io/hindsight Hindsight: Agent Memory That LearnsGagnées en 7 j +4 k Score 17,0 Total 57,9 k
- 12Graphify-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 7 j +5 k Score 13,5 Total 141 k
- 13Yuuyuko-uu/dsh-fish-memory 🐋 DSH 鱼的记忆:给会话一份会淡忘的长期记忆,每条都带时间。名字里的「鱼」来自 DeepSeek 的鲸鱼。Gagnées en 7 j +209 Score 13,3 Total 456
- 14roandejager/Hillock Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.Gagnées en 7 j +159 Score 13,3 Total 302
- 15gh9ko8y/graphmemory Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)Gagnées en 7 j +130 Score 13,0 Total 130
- 16patchy631/ai-engineering-hub In-depth tutorials on LLMs, RAGs and real-world AI agent applications.Gagnées en 7 j +2,4 k Score 12,3 Total 40,8 k
- 17metadist/synaplan 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.Gagnées en 7 j +203 Score 12,0 Total 487
- 18chatvia/chatvia Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and…Gagnées en 7 j +112 Score 11,2 Total 112
- 19BotHarness/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 7 j +201 Score 11,0 Total 535
- 20peterpoal134/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 7 j +107 Score 10,7 Total 107
- 21akitaonrails/ai-memory Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendorsGagnées en 7 j +1,2 k Score 9,9 Total 14,9 k
- 22jaikydota/BullFlow 推量牛 BullFlow — 开源企业级 RAG 解决方案:从企业知识库、营销内容自动化生产到全域内容分发 | Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. 知识库全链路本地开源模型,无需付费模型;AI Agent 创作图文 / 图片 / 视频,一键发布抖音、小红书、公众号、LinkedIn、YouTube 等 17 个平台。Commercial-grade, multi-tenant, billing & admin…Gagnées en 7 j +125 Score 9,9 Total 286
- 23YOLOW92/pagesift Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP server, Python/Node SDKs. Self-hosted single binary.Gagnées en 7 j +88 Score 8,8 Total 185
- 24zj-unicom-ai/UniEmployee 面向企业的数字员工构建与运行平台:把专业员工的经验、流程与判断标准,固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。Gagnées en 7 j +190 Score 7,9 Total 762
- 25Sallyn0225/eidolon-sc 和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身:日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆;支持 Google/GitHub 登录与自带密钥,Docker Compose 一键部署(参考 LAPLACE Eidolon)Gagnées en 7 j +120 Score 7,6 Total 367
- 26sno-ai/sno-station When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.Gagnées en 7 j +214 Score 7,2 Total 1,1 k
- 27SuanmoSuanyangTechnology/MemoryBear MemoryBear Equip AI with human-like memory capabilityGagnées en 7 j +653 Score 7,0 Total 9,3 k
- 28EvannZhongg/Nosis Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.Gagnées en 7 j +70 Score 7,0 Total 117
- 29Graphicle-AI/graphicle Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.Gagnées en 7 j +131 Score 6,9 Total 493
- 30DemonDamon/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 7 j +180 Score 6,8 Total 887
- 31Sidiora-Labs/hyperfide The ai agent workflow tool that scales from small, simple projects to large, complex codebases.Gagnées en 7 j +147 Score 6,6 Total 639
- 32LazyAGI/LazyMind An AI Skill Runtime for knowledge-intensive work which makes everything under your control.Gagnées en 7 j +133 Score 6,6 Total 539
- 33Windsander/Mebular One shared graph for every AI assistant and device — memory and tasks, local-first, signed, auditable, direct P2P sync. MCP tools; no hosted account.Gagnées en 7 j +59 Score 5,9 Total 86
- 34memvid/memvid Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.Gagnées en 7 j +726 Score 5,6 Total 17,3 k
- 35himovo/movo Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.Gagnées en 7 j +111 Score 5,6 Total 501
- 36xcosmosbox/Cairn Open-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-layer knowledge graph — versioned, hot-swapped and rolled back via a GitOps pipeline like software releases, and served to AI agents over MCP. RAG, but with…Gagnées en 7 j +54 Score 5,4 Total 83
- 37GroundedCoreAI/nexusdesk Open-source, self-hosted, extensible Agent platform built around ReAct and Harness engineering, with AI customer support as its first complete reference application.Gagnées en 7 j +56 Score 5,3 Total 166
- 38Usmansayed/scubiee Save up to 30% of your AI coding tokens. Scubiee turns any codebase into searchable context for your AI coding agent. A local context engine for Cursor, Claude Code, Copilot, Codex, and more: semantic search, code relationships, live sync, MCP integration, and code that never leaves your machine.Gagnées en 7 j +51 Score 5,1 Total 145
- 39BlueRingsLabs/no-shortcuts Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security. 173 lessons, 166 runnable labs, no shortcuts. Free under CC BY-NC 4.0.Gagnées en 7 j +52 Score 4,8 Total 168
- 40EternalNight996/memory-eternal Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor and any MCP client, with an immutable audit log and a token ledger. Open source, self-hosted, no cloud.Gagnées en 7 j +47 Score 4,7 Total 121
- 41omdsh-dev/dsh-mnemon Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.Gagnées en 7 j +126 Score 4,7 Total 845
- 42axoviq-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 7 j +182 Score 4,6 Total 1,8 k
- 43666ghj/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 7 j +1,3 k Score 4,6 Total 83,4 k
- 44WenyuChiou/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 7 j +409 Score 4,6 Total 8,4 k
- 45metadist/synaplan-nextcloud Synaplan AI integration into nextcloud for RAG powered discussions, translations and summaries. Run your own AI platform next to your nextcloud!Gagnées en 7 j +62 Score 4,5 Total 255
- 46ruvnet/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 7 j +1,2 k Score 4,2 Total 80,6 k
- 47StarTrail-org/PixelRAG https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/Gagnées en 7 j +429 Score 4,2 Total 10,8 k
- 48MemTensor/MemT-1.0 Official repository for MemT-1.0Gagnées en 7 j +85 Score 4,2 Total 501
- 49ombharatiya/ai-system-design-guide AI system design guide for engineers building production AI systems and evals.Gagnées en 7 j +257 Score 4,1 Total 4,1 k
- 50StarTrail-org/LEANN [MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.Gagnées en 7 j +474 Score 4,1 Total 13,8 k
- 51bojieli/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 7 j +969 Score 4,1 Total 56,9 k
- 52FuRongJun-1999/dsh-memory 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。Gagnées en 7 j +87 Score 3,9 Total 573
- 53Tencent/WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Gagnées en 7 j +729 Score 3,9 Total 36,2 k
- 54FengZhenfei/carrel Ontology-Augmented Generation for AI agents.Gagnées en 7 j +93 Score 3,8 Total 681
- 55lfnovo/open-notebook An Open Source implementation of Notebook LM with more flexibility and featuresGagnées en 7 j +753 Score 3,7 Total 41,3 k
- 56electricsheephq/lcm-x LCM-X — Lossless Context Memory eXtensionGagnées en 7 j +38 Score 3,7 Total 142
- 57TencentCloud/Octop A smarter, self-hosted AI assistant — multi-user, multi-agent.Gagnées en 7 j +378 Score 3,6 Total 11,5 k
- 58datawhalechina/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 7 j +1 k Score 3,6 Total 85,7 k
- 59myneace/Gaussian_Clef_RAG Probabilistic retrieval-augmented generation on statistical manifolds with sub-100ms Cloudflare Clef decision routing, Woodbury-accelerated geometric kernels, and universal corpus generation. Every chunk of knowledge is a Gaussian distribution, not a flat vector. Retrieval is information geometry…Gagnées en 7 j +55 Score 3,5 Total 306
- 60JEen-wang/Adaptive-rag 按问题复杂度自动分流的电商客服 RAG:简单问题直接回答;复杂问题经过多跳检索并自我纠错;查单、退改通过工具调用完成,且高风险写操作必须先经人工确认。基于 FastAPI 和 LangGraph,混合检索并附带引用,内置离线评测与 Prometheus 指标。涵盖简历写法和项目面试拷打Gagnées en 7 j +44 Score 3,4 Total 207
- 61dodo-labs-ai/mem-forge Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.Gagnées en 7 j +31 Score 3,1 Total 31
- 62virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.Gagnées en 7 j +586 Score 3,1 Total 36,7 k
- 63cporter202/ai-agent-data-apis A mega collection of 2,070 AI agent data APIs: MCP servers, LLM tools, RAG pipelines, live web data, vision & voice. Give your AI agent live web data.Gagnées en 7 j +30 Score 3,0 Total 51
- 64oceanbase/powercontext Agent memory: long-term memory & agent memory handoff. Claude Code & Codex.Gagnées en 7 j +110 Score 3,0 Total 1,5 k
- 65youngyangyang04/llm-master 大模型(LLM)全栈学习路线与中文教程🔥:覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试,从入门到生产实践。Gagnées en 7 j +112 Score 3,0 Total 1,5 k
- 66vstorm-co/agenticos 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.Gagnées en 7 j +32 Score 2,9 Total 153
- 67dheerajponnaganti/thenwise Thenwise: a local memory of your past Claude Code work, searchable by date and link.Gagnées en 7 j +29 Score 2,9 Total 29
- 68melgarafael/DeskcommCRM 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.Gagnées en 7 j +197 Score 2,8 Total 5,1 k
- 69microsoft/ai-agents-for-beginners 18 Lessons to Get Started Building AI AgentsGagnées en 7 j +781 Score 2,8 Total 78,7 k
- 70headroomlabs-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 7 j +766 Score 2,7 Total 78,6 k
- 71Asymptote-Labs/agent-beacon The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBuGagnées en 7 j +146 Score 2,7 Total 3 k
- 72weir36/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 7 j +26 Score 2,6 Total 26
- 73volcengine/OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.Gagnées en 7 j +510 Score 2,5 Total 41,4 k
- 74dgesteves/ondocs Open-source Ask AI for your docs, with an MCP server for agents: cited answers on your own model key, from one static index built with your site. No vendor, no vector database. Starlight, Docusaurus and VitePress plugins, Next.js, or one script tag.Gagnées en 7 j +25 Score 2,5 Total 39
- 75aliengiraffe/rhizome Rhizome lets Claude Code, Codex, and OpenCode sessions discover each other, follow selected work, and exchange messages through MCP. Use it to coordinate parallel tasks on your laptop or connect your agents with a colleague's agents over a LAN or Tailscale network.Gagnées en 7 j +25 Score 2,5 Total 48
- 76harrytted/ai-agent-interview-playbook AI Agent/大模型应用工程师中文学习手册:10 章基础、12 章进阶、92 道完整详解题、276 组追问与答案、92 个实战案例,含双向学习链接、Python 实验与复习工具。用场景和易记类比理解机制,用故障与评测练习工程取舍。Gagnées en 7 j +25 Score 2,5 Total 25
- 77Phantomduke375846-alt/clinic_rag_rpocket_bot A domain-specific medical Retrieval-Augmented Generation (RAG) system that answers health-related questions strictly based on retrieved evidence from a local vector database.Gagnées en 7 j +25 Score 2,5 Total 25
- 78SorcererEarl/crypto-rpocket-accumulation-scanner Python crypto scanner: finds coins in quiet accumulation, back tested on 961 samples, rebuilt from the evidence, automated with Telegram alerts.Gagnées en 7 j +25 Score 2,5 Total 25
- 79WUnicorn67526/memochka-rpocket-team-bot 😼 AI-участница Telegram-чата с памятью, локальными мемами, реакциями и собственным характеромGagnées en 7 j +25 Score 2,5 Total 25
- 80PeaceOfElf37336/resilient-telegram-rpocket-bot A Telegram bot built around what happens when the API doesn't answer — retry with jittered backoff, structured logging, systemd deployment. Runs with --demo, no token needed.Gagnées en 7 j +25 Score 2,5 Total 25
- 81pwnedlabs/ai-security-labs AI security training: hands-on labs, tools and courses for LLM, RAG and agent security. Maintained by Pwned Labs.Gagnées en 7 j +25 Score 2,5 Total 25
- 82SourceWeft/SourceWeft 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/Gagnées en 7 j +45 Score 2,5 Total 372
- 83adongwanai/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 7 j +264 Score 2,5 Total 11,6 k
- 84AidaShika/personal-agent-dossier Move a personal AI agent between platforms without losing its job, memory, or schedules. A neutral dossier format with adapters for Grok Bot, Muse, Hermes, and OpenClaw.Gagnées en 7 j +24 Score 2,4 Total 24
- 85TencentCloud/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 7 j +409 Score 2,4 Total 30,3 k
- 86Gentleman-Programming/gentle-shell Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).Gagnées en 7 j +89 Score 2,4 Total 1,5 k
- 87xzf-thu/VoiceMem Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.Gagnées en 7 j +121 Score 2,3 Total 2,8 k
- 88eugeniughelbur/obsidian-second-brain Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.Gagnées en 7 j +162 Score 2,3 Total 5,1 k
- 89didilili/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 7 j +169 Score 2,3 Total 5,8 k
- 90nashsu/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 7 j +323 Score 2,2 Total 21,3 k
Émergents en RAG & mémoire des IA Semaines passées : 26 oct.19 oct.