81 AI and ML repos matching this view, measured from our own daily snapshots.
| # | Repo | 7-day gain | 30-day gain | Trend | Tracked | Stars |
|---|---|---|---|---|---|---|
| 1 | apache/hertzbeatAn AI-powered next-generation open source real-time observability system. | −1 | +37 | Declining | 104 d | 7.5k |
| 2 | InternLM/MindSearch🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT) | −1 | −4 | Declining | 104 d | 6.9k |
| 3 | PySpur-Dev/pyspurA visual playground for agentic workflows: Iterate over your agents 10x faster | −1 | +15 | Declining | 104 d | 5.8k |
| 4 | OpenBMB/AgentVerse🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various… | −1 | +5 | Declining | 104 d | 5.2k |
| 5 | mock-server/mockserver-monorepoMockServer is an HTTP(S) mock server and proxy for testing that lets you mock APIs, inspect and… | −1 | +14 | Declining | 104 d | 5.0k |
| 6 | u14app/deep-researchUse any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server. | −1 | −8 | Declining | 104 d | 4.7k |
| 7 | i-am-bee/beeai-frameworkBuild production-ready AI agents in both Python and Typescript. | −1 | +20 | Declining | 104 d | 3.5k |
| 8 | Sumanth077/ai-engineering-toolkitA curated list of 100+ libraries and frameworks for AI engineers building with LLMs | −1 | +3 | Declining | 104 d | 3.4k |
| 9 | FasterDecoding/MedusaMedusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads | −1 | −1 | Declining | 104 d | 2.8k |
| 10 | DEEP-PolyU/Awesome-GraphRAGAwesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource… | −1 | +8 | Declining | 104 d | 2.7k |
| 11 | coleam00/mcp-crawl4ai-ragWeb Crawling and RAG Capabilities for AI Agents and AI Coding Assistants | −1 | −1 | Declining | 104 d | 2.3k |
| 12 | TommyLemon/APIAuto☔ 敏捷开发最强大易用的接口工具,机器学习零代码测试与 AI 问答、生成代码与静态检查、生成文档与光标悬浮注释,腾讯、华为、SHEIN、传音、工行等使用 ☔ The most advanced… | −1 | −1 | Declining | 104 d | 2.2k |
| 13 | greggh/claude-code.nvimSeamless integration between Claude Code AI assistant and Neovim | −1 | +1 | Declining | 104 d | 2.1k |
| 14 | sourcegraph/awesome-code-aiA list of AI coding tools (assistants, completions, refactoring, etc.) | −1 | +0 | Declining | 104 d | 1.7k |
| 15 | madox2/vim-aiAI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim and Neovim. | −1 | +4 | Declining | 104 d | 1.2k |
| 16 | Raudaschl/rag-fusionRAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented… | −1 | +1 | Declining | 104 d | 960 |
| 17 | Azure-Samples/serverless-chat-langchainjsBuild your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js… | −1 | +5 | Declining | 104 d | 869 |
| 18 | marckohlbrugge/37signals-skillsUnofficial agent skills + reference guide that teach AI coding assistants to write Rails the… | −1 | +4 | Declining | 155 d | 731 |
| 19 | Bessouat40/RAGLightRAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug… | −1 | −1 | Declining | 104 d | 672 |
| 20 | gridaco/assistant🤖 Bring your Figma design & development pipeline to the next level - with design to code… | −1 | +2 | Declining | 104 d | 619 |
| 21 | tonykipkemboi/ollama_pdf_ragA full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with… | −1 | +1 | Declining | 104 d | 550 |
| 22 | liunian-Jay/Awesome-RAG💡 Awesome RAG: A resource of Retrieval-Augmented Generation (RAG) for LLMs, focusing on the… | −1 | +0 | Declining | 104 d | 520 |
| 23 | NisaarAgharia/Advanced_RAGAdvanced Retrieval-Augmented Generation (RAG) through practical notebooks, using the power of the… | −1 | −1 | Declining | 104 d | 501 |
| 24 | neuml/rag🚀 Retrieval Augmented Generation (RAG) with txtai. Combine search and LLMs to find insights with… | −1 | +1 | Declining | 104 d | 466 |
| 25 | LightningRAG/LightningRAGLightningRAG is a full-stack Vue + Gin starter with a decoupled frontend and backend, plus… | −1 | +1 | Declining | 104 d | 455 |
| 26 | unit-mesh/autodev-vscodeAutoDev - 🧙the AI-powered coding wizard . Put the most loved AutoDev AI assistant into your… | −1 | +0 | Declining | 104 d | 453 |
| 27 | umbertogriffo/rag-chatbotRAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information… | −1 | −2 | Declining | 104 d | 442 |
| 28 | Palm1r/QodeAssistQodeAssist is an AI-powered coding assistant plugin for Qt Creator | −1 | −1 | Declining | 104 d | 438 |
| 29 | IAAR-Shanghai/CRUD_RAGCRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language… | −1 | +1 | Declining | 104 d | 419 |
| 30 | TonicAI/tonic_validateMetrics to evaluate the quality of responses of your Retrieval Augmented Generation (RAG)… | −1 | −1 | Declining | 104 d | 327 |
| 31 | dfinke/awesome-copilot-chatmodesCustom chatMode.md personas for GitHub Copilot — specialize your VS Code with AI assistants for… | −1 | +0 | Declining | 104 d | 318 |
| 32 | RManLuo/gfm-rag[NeurIPS'25, ICLR'26] Graph Foundation Model for Retrieval Augmented Generation | −1 | +7 | Declining | 104 d | 314 |
| 33 | Ahren09/SARAOfficial Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented… | −1 | −8 | Declining | 104 d | 257 |
| 34 | TIGER-AI-Lab/LongRAGOfficial repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs". | −1 | −1 | Declining | 104 d | 248 |
| 35 | XMUDeepLIT/MemGraphRAG[KDD 2026] MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation | −1 | +3 | Declining | 94 d | 234 |
| 36 | IdolLab/RAGTrack[CVPR 2026] RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation | −1 | −1 | Declining | 104 d | 232 |
| 37 | Renumics/renumics-ragVisualization for a Retrieval-Augmented Generation (RAG) Assistant 🤖❤️📚 | −1 | −2 | Declining | 104 d | 210 |
| 38 | lroy-stack/admin-osOpen-source management dashboard template for small businesses: four languages, liquid-glass… | −1 | — | Declining | 19 d | 34 |
| 39 | HKUDS/AutoAgent"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework" | −2 | +17 | Declining | 104 d | 9.8k |
| 40 | Minidoracat/mcp-feedback-enhancedEnhanced MCP server for interactive user feedback and command execution in AI-assisted development… | −2 | −9 | Declining | 104 d | 3.7k |
| 41 | towhee-io/towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast. | −2 | +1 | Declining | 104 d | 3.5k |
| 42 | Meirtz/Awesome-Context-Engineering🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI… | −2 | +12 | Declining | 104 d | 3.3k |
| 43 | run-llama/LlamaIndexTSData framework for your LLM applications. Focus on server side solution | −2 | −3 | Declining | 104 d | 3.1k |
| 44 | approximatelabs/sketchAI code-writing assistant that understands data content | −2 | +0 | Declining | 104 d | 2.3k |
| 45 | hymie122/RAG-SurveyCollecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements… | −2 | −3 | Declining | 104 d | 1.8k |
| 46 | jxzhangjhu/Awesome-LLM-RAGAwesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language… | −2 | +3 | Declining | 104 d | 1.4k |
| 47 | jonfairbanks/local-ragIngest files for retrieval augmented generation (RAG) with open-source Large Language Models… | −2 | +1 | Declining | 104 d | 766 |
| 48 | MoMoM101/RAG-ReActAgentRAG ReAct Agent - A Retrieval-Augmented Generation system with ReAct (Reasoning+Acting) agent loop… | −2 | −2 | Declining | 104 d | 206 |
| 49 | datastax/ragstack-aiRAGStack is an out of the box solution simplifying Retrieval Augmented Generation (RAG) in AI apps. | −2 | −1 | Declining | 104 d | 194 |
| 50 | apidrifter/apidrifterBreaking-change detection and monitoring for the APIs you depend on. One engine for OpenAPI… | −2 | — | Declining | 17 d | 24 |
| 51 | weaviate/VerbaRetrieval Augmented Generation (RAG) chatbot powered by Weaviate | −3 | −5 | Declining | 104 d | 7.7k |
| 52 | truefoundry/cognitaRAG (Retrieval Augmented Generation) Framework for building modular, open source applications for… | −3 | −5 | Declining | 104 d | 4.4k |
| 53 | mongodb-developer/GenAI-ShowcaseMongoDB's Generative AI Showcase: an exhaustive collection of examples and sample applications… | −3 | −4 | Declining | 93 d | 4.3k |
| 54 | sourcegraph/cody-public-snapshotType less, code more: Cody is an AI code assistant that uses advanced search and codebase context… | −3 | −5 | Declining | 104 d | 3.8k |
| 55 | pinecone-io/canopyRetrieval Augmented Generation (RAG) framework and context engine powered by Pinecone | −3 | −4 | Declining | 104 d | 1.0k |
| 56 | mrhlaingbwardev/agentic-hacking-skillsAI-Powered Web Security & Automation - Official bonus skills, agents & MCP configs for the 'Agentic… | −3 | — | Declining | 15 d | 327 |
| 57 | boyuchengz/canvas-mcpRead-only MCP server that connects Claude, ChatGPT and other AI assistants to Canvas LMS. | −3 | — | Declining | 26 d | 116 |
| 58 | TabbyML/tabbySelf-hosted AI coding assistant | −4 | +8 | Declining | 104 d | 33.9k |
| 59 | sweepai/sweepSweep: AI coding assistant for JetBrains | −4 | −2 | Declining | 104 d | 7.7k |
| 60 | airweave-ai/airweaveOpen-source context retrieval layer for AI agents | −4 | −15 | Declining | 104 d | 6.5k |
| 61 | cheshire-cat-ai/coreAI agent microservice | −4 | −1 | Declining | 104 d | 3.1k |
| 62 | ElysiumForge-Labs/elysium-chain-mcpMCP server for AI agents to read and interact with Elysium, Kinetiq’s Arbitrum Orbit L2 on… | −4 | — | Declining | 18 d | 151 |
| 63 | microsoft/TaskWeaverThe first "code-first" agent framework for seamlessly planning and executing data analytics tasks. | −5 | −8 | Declining | 104 d | 6.2k |
| 64 | PawanOsman/OpenCursorOpen-source Cursor-like AI coding agent for VS Code - agentic chat, multi-provider LLMs (OpenAI… | −5 | +8 | Declining | 104 d | 6.0k |
| 65 | BIT-DataLab/Edit-BananaEdit Banana: A framework for converting statistical formats into editable. | −6 | +13 | Declining | 104 d | 5.5k |
| 66 | Pimzino/spec-workflow-mcpA Model Context Protocol (MCP) server that provides structured spec-driven development workflow… | −6 | −3 | Declining | 104 d | 4.3k |
| 67 | oobabooga/textgenOpen-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible… | −8 | +0 | Declining | 104 d | 47.7k |
| 68 | nomic-ai/gpt4allGPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. | −14 | −19 | Declining | 104 d | 77.3k |
| 69 | pathwaycom/pathwayPython ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG. | −17 | −107 | Declining | 104 d | 62.0k |
| 70 | mrwogu/promptscriptPrompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any AI coding… | −20 | −63 | Declining | 104 d | 324 |
| 71 | AlexSergey/rockpackZero-config React with built-in SSR, automated quality gates, and AI-ready project structure - ship… | −22 | +36 | Declining | 104 d | 1.1k |
| 72 | Cattmonkey/ChaosIntelligence把智能体当函数,把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI… | −22 | — | Declining | 26 d | 406 |
| 73 | gravityellestone/resp-polishSelf-hosted UI review for code, copy, and rendered screens. Get weighted 0-100 findings for… | −27 | — | Declining | 16 d | 32 |
| 74 | Glen-Web-App/best-agent-memory-mcpBest Agent Memory MCP servers, ranked and compared: long-term memory for Claude Code, Codex, Cursor… | −29 | — | Declining | 16 d | 210 |
| 75 | RainedFeral/mcp-typography-server-resocketMCP-сервер для книжной типографики (алгоритм Кнута — Пласса) и визуального аудита вёрстки для… | −29 | — | Declining | 16 d | 36 |
| 76 | MonkumRanger/MAX2-AI-Content-Automation-resocketOpen-source human-in-the-loop AI content automation with n8n, Notion, Telegram, AI generation, and… | −29 | — | Declining | 16 d | 35 |
| 77 | rocketride-org/rocketride-serverRocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++… | −37 | +2,287 | Declining | 104 d | 20.0k |
| 78 | cutetailbud/ff-ruyijsThis is a lightweight, headless browser purpose-built for AI agents (such as Codex or Claude Code)… | −72 | — | Declining | 15 d | 1.2k |
| 79 | holaboss-ai/holaOSOpen-source agentic workspace enterprises can make their own. Connect the systems you already run —… | −77 | −101 | Declining | 104 d | 11.4k |
| 80 | beenuar/AiSOCOpen-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK… | −227 | — | Declining | 28 d | 7.1k |
| 81 | andrew-babo/muse4aiMuse4AI — let your AI agent make the pictures and the videos. Local Windows bridge for Muse via… | −434 | — | Declining | 17 d | 328 |
whatstrending.ai stores its own daily star count for every repo it tracks (89,063 snapshots on 156 days since 2026-06-19). 7-day gain = stars on 2026-11-21 minus stars on 2026-11-14, and 30-day gain = stars on 2026-11-21 minus stars on 2026-10-22: the same two dates for every repo, and no value when we did not snapshot the repo on both days. Trend compares a repo's 7-day pace with its own longer-run pace. Tracked = days since our first snapshot. Stars = our newest snapshot. Nothing is estimated.
The full table from our 2026-11-21 snapshot as CSV or JSON, or live from the repos API.