Upstar existe aussi en français.

Voir cette page en français

Upstar ranks the fastest-rising GitHub projects every hour, across 69 topics. Browse topics

#rag-memory · AI & ML

RAG & AI memory

Retrieval-augmented generation pipelines and the memory layers that let agents remember.

This month (Oct 4 – Nov 2), the top-ranked are xerj (+16,204), Hy-Memory (+1,915) and survival-llm (+1,275). The 432 ranked repos gained 263,907 stars.

Updated Nov 2, 11:35 UTC · ranked every hour from GitHub’s daily star counts

Updated 50 min ago

GitHub topic ↗ (opens in new tab)

This month’s ranking

Showing 50 of 432

How Upstar ranks

  1. 1
    xerj-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. Rust Rust · 18.7k total Healthy Spotted at 5,752 stars
    Gained in 30 d +16.2k Score 321.3 Total 18.7k
  2. 2
    Tencent-Hunyuan/Hy-Memory Python Python · 1.9k total Spotted at 438 stars
    Gained in 30 d +1.9k Score 191.5 Total 1.9k
  3. 3
    anonnerdfrenzy/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. Python Python · 1.3k total Spotted at 203 stars
    Gained in 30 d +1.3k Score 127.5 Total 1.3k
  4. 4
    AgentMemoryRepo/agentmemoryrepo Spec for Agent Memory Repo 844 total
    Gained in 30 d +844 Score 84.4 Total 844
  5. 5
    FengZhenfei/carrel Ontology-Augmented Generation for AI agents. Python Python · 681 total
    Gained in 30 d +680 Score 68.0 Total 681
  6. 6
    HKUDS/DeepTutor DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. Python Python · 54k total Healthy
    Gained in 30 d +13.5k Score 66.8 Total 54k
  7. 7
    akitaonrails/ai-memory Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors Rust Rust · 14.9k total Healthy
    Gained in 30 d +6.1k Score 65.6 Total 14.9k
  8. 8
    VictorTaelin/uniichat TypeScript TypeScript · 637 total
    Gained in 30 d +637 Score 63.7 Total 637
  9. 9
    vectorize-io/hindsight Hindsight: Agent Memory That Learns Python Python · 57.9k total Healthy
    Gained in 30 d +13.2k Score 62.4 Total 57.9k
  10. 10
    TencentCloud/Octop A smarter, self-hosted AI assistant — multi-user, multi-agent. Python Python · 11.5k total Healthy
    Gained in 30 d +4.9k Score 61.1 Total 11.5k
  11. 11
    sahenjp/RustXNG Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later) Rust Rust · 549 total
    Gained in 30 d +549 Score 54.9 Total 549
  12. 12
    BotHarness/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. TypeScript TypeScript · 522 total
    Gained in 30 d +518 Score 51.8 Total 522
  13. 13
    Graphify-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. Python Python · 141k total Healthy
    Gained in 30 d +17.9k Score 51.2 Total 141k
  14. 14
    tigerless-labs/agent-memory Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key. Python Python · 4.3k total Healthy
    Gained in 30 d +2.3k Score 51.1 Total 4.3k
  15. 15
    MemTensor/MemT-1.0 Official repository for MemT-1.0 Python Python · 498 total
    Gained in 30 d +498 Score 49.8 Total 498
  16. 16
    Graphicle-AI/graphicle Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client. Rust Rust · 492 total
    Gained in 30 d +492 Score 49.2 Total 492
  17. 17
    thedotmack/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 + More TypeScript TypeScript · 110k total Healthy
    Gained in 30 d +14.8k Score 48.0 Total 110k
  18. 18
    LazyAGI/LazyMind An AI Skill Runtime for knowledge-intensive work which makes everything under your control. Go Go · 537 total Healthy
    Gained in 30 d +462 Score 46.2 Total 537
  19. 19
    FalkorDB/FalkorDB A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG). Rust Rust · 10.5k total Healthy
    Gained in 30 d +3.8k Score 45.8 Total 10.5k
  20. 20
    Yuuyuko-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。 JavaScript JavaScript · 456 total
    Gained in 30 d +455 Score 45.5 Total 456
  21. 21
    zgcagi/Harness-RSI Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website. TeX TeX · 431 total
    Gained in 30 d +431 Score 43.1 Total 431
  22. 22
    wanghao-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. HTML HTML · 418 total New
    Gained in 30 d +418 Score 41.8 Total 418
  23. 23
    DemonDamon/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). Python Python · 881 total Healthy
    Gained in 30 d +638 Score 40.9 Total 881
  24. 24
    zqiren/Orbital Context is yours. Agents are replaceable. Python Python · 970 total Healthy
    Gained in 30 d +663 Score 37.8 Total 970
  25. 25
    Mieksido/surfcore JavaScript JavaScript · 367 total
    Gained in 30 d +367 Score 36.7 Total 367
  26. 26
    Sallyn0225/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） Python Python · 365 total
    Gained in 30 d +365 Score 36.5 Total 365
  27. 27
    sno-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. TypeScript TypeScript · 1.1k total
    Gained in 30 d +697 Score 35.1 Total 1.1k
  28. 28
    aerovato/operator-memory The self-improving context engine for coding agents. TypeScript TypeScript · 492 total Healthy
    Gained in 30 d +372 Score 34.0 Total 492
  29. 29
    aakarim/OpenLore A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable Go Go · 1.7k total Healthy
    Gained in 30 d +888 Score 30.7 Total 1.7k
  30. 30
    myneace/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… Python Python · 306 total Low activity
    Gained in 30 d +306 Score 30.6 Total 306
  31. 31
    Asymptote-Labs/agent-beacon The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu Go Go · 3k total Healthy
    Gained in 30 d +1.2k Score 29.8 Total 3k
  32. 32
    1105216375-alt/resimind Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse. Python Python · 294 total
    Gained in 30 d +294 Score 29.4 Total 294
  33. 33
    Sidiora-Labs/hyperfide The ai agent workflow tool that scales from small, simple projects to large, complex codebases. TypeScript TypeScript · 639 total Healthy
    Gained in 30 d +426 Score 29.2 Total 639
  34. 34
    666ghj/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 Python Python · 83.4k total Low activity
    Gained in 30 d +7.8k Score 28.6 Total 83.4k
  35. 35
    aoci-spec/aoci-code A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code… Go Go · 1.8k total Healthy
    Gained in 30 d +875 Score 28.2 Total 1.8k
  36. 36
    jaikydota/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… TypeScript TypeScript · 279 total
    Gained in 30 d +279 Score 27.9 Total 279
  37. 37
    ZipengWu365/TOMC TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients. Python Python · 264 total
    Gained in 30 d +264 Score 26.4 Total 264
  38. 38
    ruvnet/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 Integrated TypeScript TypeScript · 80.6k total Healthy
    Gained in 30 d +7k Score 26.0 Total 80.6k
  39. 39
    heaven999b/hello-agent-system 👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营 Python Python · 310 total
    Gained in 30 d +257 Score 25.7 Total 310
  40. 40
    zj-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。 Python Python · 762 total Healthy
    Gained in 30 d +451 Score 25.6 Total 762
  41. 41
    SuanmoSuanyangTechnology/MemoryBear MemoryBear Equip AI with human-like memory capability Python Python · 9.3k total Healthy
    Gained in 30 d +2.1k Score 25.3 Total 9.3k
  42. 42
    metadist/synaplan-nextcloud Synaplan AI integration into nextcloud for RAG powered discussions, translations and summaries. Run your own AI platform next to your nextcloud! PHP PHP · 254 total Mixed signals
    Gained in 30 d +252 Score 25.2 Total 254
  43. 43
    crow-hq/llm-wiki-v2 Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW classifier routing: 89% right note vs 62%, 2.1× faster ingest, 68% fewer tokens. Python Python · 251 total
    Gained in 30 d +251 Score 25.1 Total 251
  44. 44
    Tencent/WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. Go Go · 36.2k total Healthy
    Gained in 30 d +4.4k Score 24.9 Total 36.2k
  45. 45
    thomasunise/casecite CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform. Python Python · 244 total Mixed signals
    Gained in 30 d +243 Score 24.3 Total 244
  46. 46
    metadist/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. PHP PHP · 486 total Healthy
    Gained in 30 d +307 Score 22.9 Total 486
  47. 47
    bojieli/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 Python Python · 56.9k total Healthy
    Gained in 30 d +4.9k Score 21.4 Total 56.9k
  48. 48
    SLEEPYBQ/MemoSync Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi. TypeScript TypeScript · 210 total
    Gained in 30 d +210 Score 21.0 Total 210
  49. 49
    SourceWeft/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/ TypeScript TypeScript · 372 total Healthy
    Gained in 30 d +238 Score 20.6 Total 372
  50. 50
    JEen-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 Python Python · 202 total
    Gained in 30 d +202 Score 20.2 Total 202

1 repository with unusual star growth is not shown. Show the full ranking

Show more

Emerging in RAG & AI memory Past weeks: Oct 26Oct 19