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 week (Oct 27 – Nov 2), the top-ranked are survival-llm (+1,209), RustXNG (+640) and DeepTutor (+10,357). The 242 ranked repos gained 71,197 stars, 14% more than the week before.

Updated Nov 2, 16:33 UTC · ranked every hour from GitHub’s daily star counts

Updated 13 min ago

GitHub topic ↗ (opens in new tab)

This week’s ranking

Showing 200 of 242

How Upstar ranks

  1. 1
    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 7 d +1.2k Score 120.9 Total 1.3k
  2. 2
    sahenjp/RustXNG Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later) Rust Rust · 677 total Spotted at 158 stars
    Gained in 7 d +640 Score 64.0 Total 677
  3. 3
    HKUDS/DeepTutor DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. Python Python · 54.2k total Healthy
    Gained in 7 d +10.4k Score 49.5 Total 54.2k
  4. 4
    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 · 432 total New
    Gained in 7 d +432 Score 43.2 Total 432
  5. 5
    Mieksido/surfcore JavaScript JavaScript · 373 total
    Gained in 7 d +373 Score 37.3 Total 373
  6. 6
    thomasunise/casecite CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform. Python Python · 245 total Mixed signals
    Gained in 7 d +240 Score 24.0 Total 245
  7. 7
    SLEEPYBQ/MemoSync Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi. TypeScript TypeScript · 236 total
    Gained in 7 d +234 Score 23.4 Total 236
  8. 8
    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 7 d +7.1k Score 22.0 Total 110k
  9. 9
    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 · 18.8k total Healthy Spotted at 5,752 stars
    Gained in 7 d +2.4k Score 19.0 Total 18.8k
  10. 10
    vectorize-io/hindsight Hindsight: Agent Memory That Learns Python Python · 58k total Healthy
    Gained in 7 d +4k Score 17.2 Total 58k
  11. 11
    Tencent-Hunyuan/Hy-Memory Python Python · 1.9k total Spotted at 438 stars
    Gained in 7 d +617 Score 17.1 Total 1.9k
  12. 12
    gh9ko8y/graphmemory Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis) Python Python · 143 total New
    Gained in 7 d +143 Score 14.3 Total 143
  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 7 d +5k Score 13.5 Total 141k
  14. 14
    roandejager/Hillock Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI. Python Python · 304 total Mixed signals
    Gained in 7 d +161 Score 13.5 Total 304
  15. 15
    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 7 d +202 Score 12.7 Total 456
  16. 16
    patchy631/ai-engineering-hub In-depth tutorials on LLMs, RAGs and real-world AI agent applications. Jupyter Notebook Jupyter Notebook · 40.9k total Mixed signals
    Gained in 7 d +2.4k Score 12.5 Total 40.9k
  17. 17
    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 · 487 total Healthy
    Gained in 7 d +199 Score 11.7 Total 487
  18. 18
    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 · 546 total
    Gained in 7 d +209 Score 11.4 Total 546
  19. 19
    chatvia/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… PHP PHP · 112 total
    Gained in 7 d +112 Score 11.2 Total 112
  20. 20
    peterpoal134/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。 JavaScript JavaScript · 110 total New
    Gained in 7 d +110 Score 11.0 Total 110
  21. 21
    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 · 288 total
    Gained in 7 d +124 Score 9.7 Total 288
  22. 22
    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 7 d +1.1k Score 9.7 Total 14.9k
  23. 23
    YOLOW92/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. Rust Rust · 185 total
    Gained in 7 d +84 Score 8.4 Total 185
  24. 24
    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 · 373 total
    Gained in 7 d +124 Score 7.9 Total 373
  25. 25
    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 · 765 total Healthy
    Gained in 7 d +188 Score 7.8 Total 765
  26. 26
    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 7 d +214 Score 7.2 Total 1.1k
  27. 27
    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 · 496 total
    Gained in 7 d +134 Score 7.0 Total 496
  28. 28
    EvannZhongg/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. Python Python · 117 total
    Gained in 7 d +70 Score 7.0 Total 117
  29. 29
    SuanmoSuanyangTechnology/MemoryBear MemoryBear Equip AI with human-like memory capability Python Python · 9.3k total Healthy
    Gained in 7 d +640 Score 6.9 Total 9.3k
  30. 30
    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 · 887 total Healthy
    Gained in 7 d +176 Score 6.6 Total 887
  31. 31
    LazyAGI/LazyMind An AI Skill Runtime for knowledge-intensive work which makes everything under your control. Go Go · 539 total Healthy
    Gained in 7 d +130 Score 6.4 Total 539
  32. 32
    Windsander/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. JavaScript JavaScript · 87 total Healthy
    Gained in 7 d +59 Score 5.9 Total 87
  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 7 d +130 Score 5.8 Total 639
  34. 34
    memvid/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. Rust Rust · 17.4k total Low activity
    Gained in 7 d +724 Score 5.6 Total 17.4k
  35. 35
    himovo/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. Python Python · 501 total Healthy
    Gained in 7 d +107 Score 5.4 Total 501
  36. 36
    xcosmosbox/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… Go Go · 83 total Mixed signals
    Gained in 7 d +53 Score 5.3 Total 83
  37. 37
    GroundedCoreAI/nexusdesk Open-source, self-hosted, extensible Agent platform built around ReAct and Harness engineering, with AI customer support as its first complete reference application. Python Python · 166 total
    Gained in 7 d +55 Score 5.2 Total 166
  38. 38
    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 · 83.5k total Low activity
    Gained in 7 d +1.4k Score 4.8 Total 83.5k
  39. 39
    EternalNight996/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. JavaScript JavaScript · 122 total Healthy
    Gained in 7 d +47 Score 4.7 Total 122
  40. 40
    axoviq-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. Python Python · 1.8k total Healthy
    Gained in 7 d +186 Score 4.7 Total 1.8k
  41. 41
    WenyuChiou/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。 Python Python · 8.4k total Healthy
    Gained in 7 d +413 Score 4.6 Total 8.4k
  42. 42
    omdsh-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. TypeScript TypeScript · 846 total Healthy
    Gained in 7 d +124 Score 4.6 Total 846
  43. 43
    Usmansayed/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. Python Python · 145 total Healthy
    Gained in 7 d +46 Score 4.6 Total 145
  44. 44
    BlueRingsLabs/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. Python Python · 170 total
    Gained in 7 d +49 Score 4.5 Total 170
  45. 45
    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 · 255 total Mixed signals
    Gained in 7 d +59 Score 4.2 Total 255
  46. 46
    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 · 57k total Healthy
    Gained in 7 d +979 Score 4.1 Total 57k
  47. 47
    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 7 d +1.2k Score 4.1 Total 80.6k
  48. 48
    FengZhenfei/carrel Ontology-Augmented Generation for AI agents. Python Python · 701 total
    Gained in 7 d +100 Score 4.1 Total 701
  49. 49
    StarTrail-org/PixelRAG https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/ Python Python · 10.8k total Healthy
    Gained in 7 d +416 Score 4.1 Total 10.8k
  50. 50
    ombharatiya/ai-system-design-guide AI system design guide for engineers building production AI systems and evals. 4.1k total Low activity
    Gained in 7 d +252 Score 4.0 Total 4.1k
  51. 51
    MemTensor/MemT-1.0 Official repository for MemT-1.0 Python Python · 501 total
    Gained in 7 d +82 Score 4.0 Total 501
  52. 52
    FuRongJun-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。 Python Python · 574 total Healthy
    Gained in 7 d +87 Score 3.9 Total 574
  53. 53
    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 · 36.3k total Healthy
    Gained in 7 d +729 Score 3.9 Total 36.3k
  54. 54
    StarTrail-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. Python Python · 13.8k total Healthy
    Gained in 7 d +440 Score 3.8 Total 13.8k
  55. 55
    lfnovo/open-notebook An Open Source implementation of Notebook LM with more flexibility and features TypeScript TypeScript · 41.4k total Mixed signals
    Gained in 7 d +767 Score 3.8 Total 41.4k
  56. 56
    electricsheephq/lcm-x LCM-X — Lossless Context Memory eXtension Python Python · 144 total Healthy
    Gained in 7 d +39 Score 3.8 Total 144
  57. 57
    datawhalechina/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 Python Python · 85.8k total Mixed signals
    Gained in 7 d +1k Score 3.6 Total 85.8k
  58. 58
    vstorm-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. Python Python · 160 total Healthy
    Gained in 7 d +39 Score 3.5 Total 160
  59. 59
    TencentCloud/Octop A smarter, self-hosted AI assistant — multi-user, multi-agent. Python Python · 11.5k total Healthy
    Gained in 7 d +368 Score 3.5 Total 11.5k
  60. 60
    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 7 d +55 Score 3.5 Total 306
  61. 61
    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 · 207 total
    Gained in 7 d +43 Score 3.4 Total 207
  62. 62
    dodo-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. Python Python · 33 total
    Gained in 7 d +33 Score 3.3 Total 33
  63. 63
    virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. Python Python · 36.8k total Healthy
    Gained in 7 d +589 Score 3.1 Total 36.8k
  64. 64
    youngyangyang04/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。 1.5k total
    Gained in 7 d +113 Score 3.0 Total 1.5k
  65. 65
    oceanbase/powercontext Agent memory: long-term memory & agent memory handoff. Claude Code & Codex. Python Python · 1.5k total Healthy
    Gained in 7 d +110 Score 3.0 Total 1.5k
  66. 66
    dheerajponnaganti/thenwise Thenwise: a local memory of your past Claude Code work, searchable by date and link. TypeScript TypeScript · 29 total New
    Gained in 7 d +29 Score 2.9 Total 29
  67. 67
    melgarafael/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. TypeScript TypeScript · 5.1k total Healthy
    Gained in 7 d +202 Score 2.9 Total 5.1k
  68. 68
    microsoft/ai-agents-for-beginners 18 Lessons to Get Started Building AI Agents Jupyter Notebook Jupyter Notebook · 78.7k total Healthy
    Gained in 7 d +795 Score 2.8 Total 78.7k
  69. 69
    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 7 d +150 Score 2.8 Total 3k
  70. 70
    cporter202/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. 51 total
    Gained in 7 d +27 Score 2.7 Total 51
  71. 71
    headroomlabs-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. Python Python · 78.6k total Healthy
    Gained in 7 d +750 Score 2.7 Total 78.6k
  72. 72
    pwnedlabs/ai-security-labs AI security training: hands-on labs, tools and courses for LLM, RAG and agent security. Maintained by Pwned Labs. 26 total New
    Gained in 7 d +26 Score 2.6 Total 26
  73. 73
    weir36/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% Python Python · 26 total New
    Gained in 7 d +26 Score 2.6 Total 26
  74. 74
    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 · 374 total Healthy
    Gained in 7 d +47 Score 2.6 Total 374
  75. 75
    adongwanai/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 MDX MDX · 11.6k total Mixed signals
    Gained in 7 d +273 Score 2.6 Total 11.6k
  76. 76
    volcengine/OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. Python Python · 41.4k total Healthy
    Gained in 7 d +514 Score 2.5 Total 41.4k
  77. 77
    dgesteves/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. TypeScript TypeScript · 39 total
    Gained in 7 d +25 Score 2.5 Total 39
  78. 78
    harrytted/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。 Python Python · 25 total New
    Gained in 7 d +25 Score 2.5 Total 25
  79. 79
    Phantomduke375846-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. HTML HTML · 25 total New
    Gained in 7 d +25 Score 2.5 Total 25
  80. 80
    SorcererEarl/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. HTML HTML · 25 total New
    Gained in 7 d +25 Score 2.5 Total 25
  81. 81
    WUnicorn67526/memochka-rpocket-team-bot 😼 AI-участница Telegram-чата с памятью, локальными мемами, реакциями и собственным характером 25 total New
    Gained in 7 d +25 Score 2.5 Total 25
  82. 82
    PeaceOfElf37336/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. HTML HTML · 25 total New
    Gained in 7 d +25 Score 2.5 Total 25
  83. 83
    AidaShika/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. Python Python · 24 total New
    Gained in 7 d +24 Score 2.4 Total 24
  84. 84
    TencentCloud/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. TypeScript TypeScript · 30.4k total Healthy
    Gained in 7 d +402 Score 2.3 Total 30.4k
  85. 85
    aliengiraffe/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. Go Go · 48 total
    Gained in 7 d +23 Score 2.3 Total 48
  86. 86
    nashsu/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。 TypeScript TypeScript · 21.3k total Mixed signals
    Gained in 7 d +333 Score 2.3 Total 21.3k
  87. 87
    didilili/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 Python Python · 5.8k total Low activity
    Gained in 7 d +172 Score 2.3 Total 5.8k
  88. 88
    Gentleman-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). TypeScript TypeScript · 1.5k total Healthy
    Gained in 7 d +87 Score 2.3 Total 1.5k
  89. 89
    liliu-z/stashbase An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work. TypeScript TypeScript · 1.2k total Healthy
    Gained in 7 d +78 Score 2.3 Total 1.2k
  90. 90
    xzf-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. Python Python · 2.8k total Mixed signals
    Gained in 7 d +119 Score 2.3 Total 2.8k
  91. 91
    eugeniughelbur/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. Python Python · 5.1k total Healthy
    Gained in 7 d +157 Score 2.2 Total 5.1k
  92. 92
    MiaoWuNYA/rikkahub-sillytavern-android 安卓AI聊天端:开箱即聊，无损导入酒馆卡，缓存强省用量，Jev 决策，专属RP模式，防空回，主动信息，前端卡支持，高定制主题，QQbot，AI群聊，插件系统，强兼容中转站。手机移动端原生支持，求 Star 收藏⭐Android AI Chatbox: lossless SillyTavern card import, aggressive cache optimization, Jev decisions, multi-dimensional memory, anti-blank-reply, proactive messages, AI group chat, SillyTavern… Kotlin Kotlin · 163 total
    Gained in 7 d +26 Score 2.2 Total 163
  93. 93
    max-ramas/rms-memory-mcp Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency Rust Rust · 63 total Healthy
    Gained in 7 d +22 Score 2.2 Total 63
  94. 94
    rasidi3112/pondok-ai Turn one machine into a private ChatGPT for a whole room. One command sets up Ollama, Open WebUI, RAG and an OpenAI-compatible API sized to your hardware, and pondok-ai share lets a classroom or office chat from their own phones. TypeScript TypeScript · 59 total
    Gained in 7 d +22 Score 2.2 Total 59
  95. 95
    MemPalace/mempalace The best-benchmarked open-source AI memory system. And it's free. Python Python · 60.2k total Healthy
    Gained in 7 d +524 Score 2.1 Total 60.2k
  96. 96
    datawhalechina/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/ Python Python · 12.8k total Low activity
    Gained in 7 d +240 Score 2.1 Total 12.8k
  97. 97
    repowise-dev/repowise Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP. Python Python · 8.1k total Healthy
    Gained in 7 d +189 Score 2.1 Total 8.1k
  98. 98
    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 7 d +88 Score 2.1 Total 1.8k
  99. 99
    w8123/EnterpriseAgentFramework ReachAI企业级智能体开发平台：快速、安全完成已有业务系统智能化改造，让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise systems, enabling AI to query data, fill out forms, and execute business tasks directly within OA, ERP, CRM, and other business applications. Java Java · 1k total Healthy
    Gained in 7 d +63 Score 2.0 Total 1k
  100. 100
    open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...) Python Python · 158k total Healthy
    Gained in 7 d +779 Score 2.0 Total 158k
  101. 101
    langchain-ai/langgraph Build resilient agents. Python Python · 44.3k total Healthy
    Gained in 7 d +412 Score 2.0 Total 44.3k
  102. 102
    chrisryugj/kordoc 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 TypeScript TypeScript · 2.9k total Healthy
    Gained in 7 d +103 Score 2.0 Total 2.9k
  103. 103
    yuezhiai/jonex All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine Python Python · 1.6k total Mixed signals
    Gained in 7 d +75 Score 1.9 Total 1.6k
  104. 104
    410979729/scope-recall-hermes Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct or delete what is remembered. Python Python · 521 total Healthy
    Gained in 7 d +41 Score 1.9 Total 521
  105. 105
    slow-stack/mneme 🧠 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. JavaScript JavaScript · 206 total Healthy
    Gained in 7 d +25 Score 1.9 Total 206
  106. 106
    promptfoo/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. TypeScript TypeScript · 26.7k total Healthy
    Gained in 7 d +293 Score 1.8 Total 26.7k
  107. 107
    ConardLi/garden-skills ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more. JavaScript JavaScript · 13.5k total Mixed signals
    Gained in 7 d +205 Score 1.8 Total 13.5k
  108. 108
    Shubhamsaboo/awesome-llm-apps 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source. Python Python · 144k total Healthy
    Gained in 7 d +659 Score 1.7 Total 144k
  109. 109
    DasterProkio/awesome-ai-companion Open-source AI companions, desktop pets, long-term memory & proactive chat. 人机恋开源项目大全。让你的家机能够脱离官端自主存在，拥有记忆和主动性。 HTML HTML · 1.1k total Healthy
    Gained in 7 d +57 Score 1.7 Total 1.1k
  110. 110
    langgenius/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. Python Python · 160k total Healthy
    Gained in 7 d +684 Score 1.7 Total 160k
  111. 111
    mem0ai/mem0 The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. Python Python · 68.3k total Healthy
    Gained in 7 d +445 Score 1.7 Total 68.3k
  112. 112
    Gentleman-Programming/gentle-ai Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in. Go Go · 8.2k total Healthy
    Gained in 7 d +153 Score 1.7 Total 8.2k
  113. 113
    VictorTaelin/uniichat TypeScript TypeScript · 638 total
    Gained in 7 d +41 Score 1.7 Total 638
  114. 114
    ZeKaiNie/universal-examprep-skill Exam Cram Coach · 跨会话记忆与讲义溯源防幻觉的极速备考教练 | AI exam-prep tutor for Claude Code, Cursor, Codex, Antigravity: teaches from slides with page citations, crops figures, quizzes with real homework, runs smoothly on small cheap models. 期末复习·考前突击·刷题·错题本·小抄 Python Python · 364 total Healthy
    Gained in 7 d +30 Score 1.6 Total 364
  115. 115
    infiniflow/ragflow RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure. Go Go · 93.4k total Healthy
    Gained in 7 d +488 Score 1.6 Total 93.4k
  116. 116
    unclecode/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/VuxzM8mtf Python Python · 86.8k total Healthy
    Gained in 7 d +466 Score 1.6 Total 86.8k
  117. 117
    jzjzzzzzzz/agent-me Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin. Python Python · 632 total Healthy
    Gained in 7 d +38 Score 1.6 Total 632
  118. 118
    vshulcz/deja-vu Coding agent memory for Claude Code, Codex, Cursor and 40 more, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary. Go Go · 1.4k total Healthy
    Gained in 7 d +56 Score 1.5 Total 1.4k
  119. 119
    HKUDS/RAG-Anything "RAG-Anything: All-in-One RAG Framework" Python Python · 24.4k total Healthy
    Gained in 7 d +237 Score 1.5 Total 24.4k
  120. 120
    PaddlePaddle/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. Python Python · 92.1k total Low activity
    Gained in 7 d +437 Score 1.4 Total 92.1k
  121. 121
    DocAILab/XRAG XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation Python Python · 611 total Mixed signals
    Gained in 7 d +34 Score 1.4 Total 611
  122. 122
    shuxiachai/academic-commercialization-agent AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark. Python Python · 806 total Healthy
    Gained in 7 d +39 Score 1.4 Total 806
  123. 123
    Gentleman-Programming/engram Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI. Go Go · 7.7k total Healthy
    Gained in 7 d +122 Score 1.4 Total 7.7k
  124. 124
    HKUDS/VideoRAG [KDD'2026] "VideoRAG: Chat with Your Videos" Python Python · 3.5k total Low activity
    Gained in 7 d +81 Score 1.4 Total 3.5k
  125. 125
    Ontos-AI/knowhere Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG. Python Python · 3.9k total Healthy
    Gained in 7 d +85 Score 1.4 Total 3.9k
  126. 126
    cortexkit/magic-context Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit. TypeScript TypeScript · 2.5k total Healthy
    Gained in 7 d +67 Score 1.4 Total 2.5k
  127. 127
    topoteretes/cognee Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free Python Python · 33k total Healthy
    Gained in 7 d +243 Score 1.3 Total 33k
  128. 128
    langbot-app/LangBot Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama… Python Python · 18.7k total Healthy
    Gained in 7 d +180 Score 1.3 Total 18.7k
  129. 129
    yaojingang/GEOFlow Open-source GEO content engineering and multi-site distribution platform with AI quality inspection, illustrated admin help, hosted sites, browser-assisted publishing, and signed updates. PHP PHP · 4k total Healthy
    Gained in 7 d +82 Score 1.3 Total 4k
  130. 130
    deeplethe/utopia World's first open-source enterprise world model. Rust Rust · 8.7k total Healthy
    Gained in 7 d +121 Score 1.3 Total 8.7k
  131. 131
    plastic-labs/honcho Memory library for building stateful agents Python Python · 7.9k total Healthy
    Gained in 7 d +115 Score 1.3 Total 7.9k
  132. 132
    liyupi/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… JavaScript JavaScript · 21.8k total Mixed signals
    Gained in 7 d +189 Score 1.3 Total 21.8k
  133. 133
    garrytan/gbrain Garry's Opinionated OpenClaw/Hermes Agent Brain TypeScript TypeScript · 31.5k total Healthy
    Gained in 7 d +227 Score 1.3 Total 31.5k
  134. 134
    MemoriLabs/Memori Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed… Python Python · 17.3k total Mixed signals
    Gained in 7 d +166 Score 1.3 Total 17.3k
  135. 135
    comet-ml/opik Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. Python Python · 23.1k total Healthy
    Gained in 7 d +182 Score 1.2 Total 23.1k
  136. 136
    semantica-agi/semantica Graph-Native Infrastructure for Context and Accountable AI Systems Python Python · 14.4k total Healthy
    Gained in 7 d +143 Score 1.2 Total 14.4k
  137. 137
    NVIDIA/skills Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. Python Python · 3.8k total Healthy
    Gained in 7 d +72 Score 1.2 Total 3.8k
  138. 138
    ItzCrazyKns/Vane Vane is an AI-powered answering engine. TypeScript TypeScript · 38k total Low activity
    Gained in 7 d +228 Score 1.2 Total 38k
  139. 139
    EverMind-AI/EverOS One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. Python Python · 13.8k total Healthy
    Gained in 7 d +137 Score 1.2 Total 13.8k
  140. 140
    langchain-ai/langchain The agent engineering platform. Python Python · 149k total Healthy
    Gained in 7 d +439 Score 1.1 Total 149k
  141. 141
    MemTensor/MemOS 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. TypeScript TypeScript · 12.2k total Healthy
    Gained in 7 d +125 Score 1.1 Total 12.2k
  142. 142
    getzep/graphiti Build Real-Time Knowledge Graphs for AI Agents Python Python · 32.4k total Healthy
    Gained in 7 d +203 Score 1.1 Total 32.4k
  143. 143
    tudoumashu/ai-memory-skillpack Bounded project-memory skills for Codex CLI and Claude Code. Python Python · 481 total
    Gained in 7 d +24 Score 1.1 Total 481
  144. 144
    rohitg00/agentmemory #1 Persistent memory for AI coding agents based on real-world benchmarks TypeScript TypeScript · 30.1k total Healthy
    Gained in 7 d +193 Score 1.1 Total 30.1k
  145. 145
    Mintplex-Labs/anything-llm Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience JavaScript JavaScript · 67.9k total Healthy
    Gained in 7 d +287 Score 1.1 Total 67.9k
  146. 146
    poco-ai/Agentero Unified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台；补齐 Zotero 时代的人机上下文断点。 TypeScript TypeScript · 1.1k total Healthy
    Gained in 7 d +35 Score 1.1 Total 1.1k
  147. 147
    ScrapeGraphAI/Scrapegraph-ai Python scraper based on AI Python Python · 32.4k total Mixed signals
    Gained in 7 d +193 Score 1.1 Total 32.4k
  148. 148
    yilewang/llm-for-zotero An open-source research agent system for your Zotero library. TypeScript TypeScript · 3.5k total Healthy
    Gained in 7 d +62 Score 1.1 Total 3.5k
  149. 149
    NirDiamant/RAG_Techniques This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial. Jupyter Notebook Jupyter Notebook · 30.2k total Healthy
    Gained in 7 d +183 Score 1.1 Total 30.2k
  150. 150
    tirth8205/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. Python Python · 32.6k total Healthy
    Gained in 7 d +178 Score 1.0 Total 32.6k
  151. 151
    onyx-dot-app/onyx Open Source AI Platform - AI Chat with advanced features that works with every LLM Python Python · 33.2k total Healthy
    Gained in 7 d +178 Score 1.0 Total 33.2k
  152. 152
    ModelEngine-Group/nexent Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes. Python Python · 6.1k total Healthy
    Gained in 7 d +75 Score 1.0 Total 6.1k
  153. 153
    ExplosiveCoderflome/AI-Novel-Writing-Assistant 面向长篇小说创作的 AI Native 开源系统，用 Agent、世界观、写法引擎、RAG 和整本生产工作流，帮助新手从一句灵感走到完整小说。AI-native engine for end-to-end novel creation — from idea to full chapters, with structured planning, worldbuilding, and agent-driven workflows. TypeScript TypeScript · 3.4k total Healthy
    Gained in 7 d +55 Score 1.0 Total 3.4k
  154. 154
    yfedoseev/pdf_oxide The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0. Rust Rust · 1.2k total Healthy
    Gained in 7 d +32 Score 1.0 Total 1.2k
  155. 155
    tobi/qmd mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local TypeScript TypeScript · 30.8k total Healthy
    Gained in 7 d +167 Score 1.0 Total 30.8k
  156. 156
    simular-ai/Agent-S Agent S: the state-of-the-art open source computer use agents Python Python · 12.9k total Mixed signals
    Gained in 7 d +107 Score 0.9 Total 12.9k
  157. 157
    dataease/SQLBot 🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG. JavaScript JavaScript · 7k total Healthy
    Gained in 7 d +79 Score 0.9 Total 7k
  158. 158
    VectifyAI/PageIndex 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG Python Python · 40k total Healthy
    Gained in 7 d +184 Score 0.9 Total 40k
  159. 159
    screenpipe/screenpipe YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context Rust Rust · 22.2k total Healthy
    Gained in 7 d +136 Score 0.9 Total 22.2k
  160. 160
    MODSetter/SurfSense Air-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://discord.gg/ejRNvftDp9 Python Python · 16.7k total Healthy
    Gained in 7 d +116 Score 0.9 Total 16.7k
  161. 161
    ai-boost/awesome-harness-engineering Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. Python Python · 5k total Mixed signals
    Gained in 7 d +63 Score 0.9 Total 5k
  162. 162
    amitshekhariitbhu/ai-system-design AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step. Markdown Markdown · 820 total
    Gained in 7 d +25 Score 0.9 Total 820
  163. 163
    pipeshub-ai/pipeshub-ai 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. Python Python · 3.9k total Healthy
    Gained in 7 d +55 Score 0.9 Total 3.9k
  164. 164
    xerrors/Yuxi 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. Python Python · 7.6k total Healthy
    Gained in 7 d +75 Score 0.9 Total 7.6k
  165. 165
    MemTensor/memmy-agent 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc. TypeScript TypeScript · 2.2k total Healthy
    Gained in 7 d +38 Score 0.8 Total 2.2k
  166. 166
    Marker-Inc-Korea/AutoRAG Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files. TypeScript TypeScript · 5.3k total Healthy
    Gained in 7 d +59 Score 0.8 Total 5.3k
  167. 167
    datawhalechina/happy-llm 📚 从零开始构建大模型 Jupyter Notebook Jupyter Notebook · 34.7k total Low activity
    Gained in 7 d +152 Score 0.8 Total 34.7k
  168. 168
    agentscope-ai/ReMe ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. Python Python · 3.7k total Healthy
    Gained in 7 d +49 Score 0.8 Total 3.7k
  169. 169
    dair-ai/Prompt-Engineering-Guide 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. MDX MDX · 79.8k total Low activity
    Gained in 7 d +223 Score 0.8 Total 79.8k
  170. 170
    nageoffer/ragent 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。 Java Java · 4.4k total Mixed signals
    Gained in 7 d +52 Score 0.8 Total 4.4k
  171. 171
    AVIDS2/memorix Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae. TypeScript TypeScript · 893 total Healthy
    Gained in 7 d +23 Score 0.8 Total 893
  172. 172
    HKUDS/LightRAG [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation Python Python · 40.5k total Healthy
    Gained in 7 d +152 Score 0.8 Total 40.5k
  173. 173
    SenteLabsAI/OpenExecutive AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js). Python Python · 5.7k total Healthy
    Gained in 7 d +56 Score 0.7 Total 5.7k
  174. 174
    codedogQBY/ReadAny AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync. TypeScript TypeScript · 2.9k total Healthy
    Gained in 7 d +39 Score 0.7 Total 2.9k
  175. 175
    FB208/OpenBidKit_Yibiao 开箱即用的AI标书编写工具，标书AI生成工具，投标工具箱、知识库、标书查重、废标项检查，完全开源免费，欢迎使用 JavaScript JavaScript · 3.3k total Healthy
    Gained in 7 d +41 Score 0.7 Total 3.3k
  176. 176
    opendataloader-project/opendataloader-pdf PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. Java Java · 30.2k total Healthy
    Gained in 7 d +125 Score 0.7 Total 30.2k
  177. 177
    elizaOS/eliza Open source agentic operating system TypeScript TypeScript · 19.8k total Healthy
    Gained in 7 d +98 Score 0.7 Total 19.8k
  178. 178
    zzet/gortex High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord… Go Go · 1.9k total Healthy
    Gained in 7 d +30 Score 0.7 Total 1.9k
  179. 179
    modelscope/evalscope A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking. Python Python · 3.6k total Healthy
    Gained in 7 d +41 Score 0.7 Total 3.6k
  180. 180
    jegly/Box The most advanced, fully offline client-side AI suite on Android today. Kotlin Kotlin · 964 total Mixed signals
    Gained in 7 d +21 Score 0.7 Total 964
  181. 181
    xberg-io/xberg The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence. Rust Rust · 9.5k total Healthy
    Gained in 7 d +66 Score 0.7 Total 9.5k
  182. 182
    SocialAI-tianji/Tianji 制作懂人情世故的大语言模型 | 涵盖提示词工程、RAG、Agent、LLM微调教程 Python Python · 2k total Low activity
    Gained in 7 d +30 Score 0.7 Total 2k
  183. 183
    LearningCircuit/local-deep-research ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. Python Python · 9.5k total Healthy
    Gained in 7 d +64 Score 0.7 Total 9.5k
  184. 184
    amitshekhariitbhu/ai-engineering-interview-questions Your Cheat Sheet for AI Engineering Interview – Questions and Answers. Markdown Markdown · 3.6k total Mixed signals
    Gained in 7 d +39 Score 0.7 Total 3.6k
  185. 185
    Future-House/paper-qa High accuracy RAG for answering questions from scientific documents with citations Python Python · 9.5k total Mixed signals
    Gained in 7 d +63 Score 0.6 Total 9.5k
  186. 186
    Ar9av/obsidian-wiki Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents Python Python · 3.7k total Healthy
    Gained in 7 d +38 Score 0.6 Total 3.7k
  187. 187
    supermemoryai/supermemory Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era. TypeScript TypeScript · 31.5k total Healthy
    Gained in 7 d +107 Score 0.6 Total 31.5k
  188. 188
    khoj-ai/khoj Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. Python Python · 37.9k total Low activity
    Gained in 7 d +117 Score 0.6 Total 37.9k
  189. 189
    trustgraph-ai/trustgraph The Governance Platform for Agents, Knowledge, and Context Python Python · 2.9k total Healthy
    Gained in 7 d +32 Score 0.6 Total 2.9k
  190. 190
    breferrari/obsidian-mind A self-organizing Obsidian vault that gives AI coding agents persistent memory. TypeScript TypeScript · 5.5k total Healthy
    Gained in 7 d +44 Score 0.6 Total 5.5k
  191. 191
    oceanbase/seekdb The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable. C++ C++ · 3.2k total Healthy
    Gained in 7 d +33 Score 0.6 Total 3.2k
  192. 192
    Osmantic/ODS ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server. Python Python · 7.7k total Healthy
    Gained in 7 d +51 Score 0.6 Total 7.7k
  193. 193
    Snailclimb/interview-guide 基于 Spring Boot 4.1、Java 25、Spring AI 2.0、React、PostgreSQL/pgvector、Redis 和 RustFS 构建的开源 AI 面试平台，支持简历智能分析、模拟面试、语音面试和知识库 RAG。 Java Java · 3.5k total Mixed signals
    Gained in 7 d +33 Score 0.6 Total 3.5k
  194. 194
    AnalyseDeCircuit/oxideterm AI-native workspace for local shells and remote machines.Zero Webview, zero OpenSSL, zero telemetry, and no app subscription.Written in Rust+GPUI Rust Rust · 1.8k total Healthy
    Gained in 7 d +23 Score 0.6 Total 1.8k
  195. 195
    miurla/morphic An AI-powered search engine with a generative UI TypeScript TypeScript · 9.3k total Healthy
    Gained in 7 d +49 Score 0.5 Total 9.3k
  196. 196
    vibrantlabsai/ragas Supercharge Your LLM Application Evaluations 🚀 Python Python · 16.2k total Low activity
    Gained in 7 d +64 Score 0.5 Total 16.2k
  197. 197
    run-llama/llama_index LlamaIndex is the document processing platform for AI Python Python · 52.8k total Healthy
    Gained in 7 d +115 Score 0.5 Total 52.8k
  198. 198
    humanlayer/12-factor-agents What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? TypeScript TypeScript · 27k total Low activity
    Gained in 7 d +82 Score 0.5 Total 27k
  199. 199
    cocoindex-io/cocoindex Incremental engine for long horizon agents 🌟 Star if you like it! Rust Rust · 11.8k total Healthy
    Gained in 7 d +54 Score 0.5 Total 11.8k
  200. 200
    Canner/WrenAI GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more. Python Python · 18k total Healthy
    Gained in 7 d +66 Score 0.5 Total 18k
Show more

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