Daily Trends Rankings
Top GitHub Rankings
Today’s GitHub trending list is buzzing with tools that make AI more practical and accessible for everyday workflows. Leading the charge is Microsoft’s MarkItDown, a highly efficient utility that converts messy office documents into clean Markdown, perfect for feeding data into LLMs. Meanwhile, MoneyPrinterTurbo is seeing a massive surge in popularity, offering a one-click solution for developers to generate high-quality short videos using large language models, proving that AI-driven content creation remains a top priority for the community.
A clear theme today is the evolution of AI agents and "memory" infrastructure. Projects like Supermemory are positioning themselves as the essential data layer for the AI era, while oh-my-pi brings a sophisticated AI coding agent directly to the terminal with optimized tool harnesses. We are also seeing a strong push toward specialized developer utilities, from Scrapling’s adaptive web scraping framework to VoxCPM’s impressive tokenizer-free speech generation. Whether you are building multi-agent financial frameworks or mastering the fundamentals through the classic Build Your Own X repository, today’s trends show a community focused on moving beyond simple chat interfaces toward robust, automated systems.
| Rank | Repo | Description | Language | Stars | Fork | Stars today | Growth |
|---|---|---|---|---|---|---|---|
| 1 | microsoft /markitdown | Python tool for converting files and office documents to Markdown. | Python | 138,309 | 9,419 | 3,034 | 2.19% |
| 2 | nesquena /hermes-webui | Hermes WebUI: The best way to use Hermes Agent from the web or from your phone! | Python | 11,255 | 1,447 | 945 | 8.40% |
| 3 | supermemoryai /supermemory | Memory engine and app that is extremely fast, scalable. The Memory API for the AI era. | TypeScript | 23,955 | 2,141 | 647 | 2.70% |
| 4 | harry0703 /MoneyPrinterTurbo | 利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM. | Python | 76,798 | 10,898 | 3,375 | 4.39% |
| 5 | D4Vinci /Scrapling | 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! | Python | 57,992 | 5,630 | 1,486 | 2.56% |
| 6 | pbakaus /impeccable | The design language that makes your AI harness better at design. | JavaScript | 32,661 | 1,780 | 485 | 1.48% |
| 7 | p-e-w /heretic | Fully automatic censorship removal for language models | Python | 23,019 | 2,465 | 249 | 1.08% |
| 8 | EveryInc /compound-engineering-plugin | Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more | TypeScript | 19,087 | 1,428 | 417 | 2.18% |
| 9 | TauricResearch /TradingAgents | TradingAgents: Multi-Agents LLM Financial Trading Framework | Python | 81,745 | 15,889 | 299 | 0.37% |
| 10 | revfactory /harness | A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. | HTML | 5,129 | 689 | 524 | 10.22% |
| 11 | godotengine /godot | Godot Engine – Multi-platform 2D and 3D game engine | C++ | 111,623 | 25,509 | 77 | 0.07% |
| 12 | can1357 /oh-my-pi | ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more | TypeScript | 9,450 | 759 | 335 | 3.54% |
| 13 | OpenBMB /VoxCPM | VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning | Python | 24,209 | 2,788 | 888 | 3.67% |
| 14 | FareedKhan-dev /train-llm-from-scratch | A straightforward method for training your LLM, from downloading data to generating text. | Jupyter Notebook | 3,690 | 515 | 861 | 23.33% |
| 15 | stefan-jansen /machine-learning-for-trading | Code for Machine Learning for Algorithmic Trading, 2nd edition. | Jupyter Notebook | 17,836 | 5,183 | 93 | 0.52% |
| 16 | dmtrKovalenko /fff | The fastest and the most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS | Rust | 7,160 | 298 | 135 | 1.89% |
| 17 | codecrafters-io /build-your-own-x | Master programming by recreating your favorite technologies from scratch. | Markdown | 510,386 | 48,388 | 1,212 | 0.24% |