Repositories taking off
?
- Stars gained
- New stars in the window. "all" means the repo is younger than the window, so the number is every star it has.
- Today
- Stars since midnight US Pacific time, so a partial day.
- Above pace
- How many more stars the repo got than its pace in the window before would predict. +500 means 500 more than usual.
- Momentum
- A daily score modeled on trendshift.io: 8 points per star and 2 per fork since midnight UTC, reduced for repos that are this busy every day.
- Speed-up
- Stars per day in the window divided by stars per day in the window before. "New" means the repo is younger than the window. "Under 14 days" (twice the window; "Under 2 years" for 1 year) means it is older than the window but too young for a full window before it to compare with.
- Bars
- Stars per day (per week for 90 days and 1 year). Bright bars are the selected window. Heights use a square-root scale, so quieter days stay visible next to a spike.
| # | Repository | Stars | Today | 7d | 30d | 90d | Above pace ↓ | Momentum | Speed-up | Weekly stars |
|---|---|---|---|---|---|---|---|---|---|---|
| 851 |
AIにまじなPPTXを作らせる Claude Code / Codex スキル |
1,431 | +1 | +127 | +630 | +1,430all | +1,430 | 0 | New | |
| 852 |
No description |
1,430 | -4 | +916 | +1,426 | +1,426 | +1,426 | 74 | Under 180 days | |
| 853 |
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物 |
82,124 | +159 | +1,453 | +7,516 | +13,174 | +1,425 | 1,127 | 1.1x faster | |
| 854 |
基于 REA 深度拆解并高保真还原 Claude 官方桌面端 UI。还原 30 个独立 React 组件与 8 项硬核交互物理算法，附带 3000+ 行逆向分析手册。 |
1,427 | +16 | +165 | +1,425all | +1,425all | +1,425 | 165 | New | |
| 855 |
LLM Inference Engine for Metal, CUDA and Vulkan. |
1,490 | +5 | +87 | +1,177 | +1,454 | +1,419 | 63 | Under 180 days | |
| 856 |
Curated list of project-based tutorials |
288,097 | +93 | +828 | +3,990 | +13,996 | +1,418 | 663 | 1.1x faster | |
| 857 |
You don't write AGENTS.md. You train it with gradient descent. |
1,419 | +1 | +19 | +335 | +1,418all | +1,418 | 16 | New | |
| 858 |
No description |
1,418 | +8 | +124 | +1,418all | +1,418all | +1,418 | 99 | New | |
| 859 |
A decompilation of Super Smash Bros Melee brought to you by a bunch of clever folks. |
2,443 | +1 | +9 | +163 | +1,501 | +1,417 | 16 | 17.9x faster | |
| 860 |
洛雪音乐源 |
10,282 | +32 | +280 | +1,092 | +2,955 | +1,417 | 338 | 1.9x faster | |
| 861 |
YunX（云析）的官方 windows 桌面端 |
1,417 | +76 | +469 | +1,401 | +1,416all | +1,416 | 704 | New | |
| 862 |
麦麦预算餐：基于麦当劳 MCP 的真实核价、预算比较与餐品替换 Skill |
1,504 | +52 | +804 | +1,416all | +1,416all | +1,416 | 328 | New | |
| 863 |
One-click installer for Big Walk VR and Titanfall 2 VR |
1,414 | +3 | +48 | +1,310 | +1,414all | +1,414 | 56 | New | |
| 864 |
No description |
1,421 | +16 | +1,414all | +1,414all | +1,414all | +1,414 | 61 | New | |
| 865 |
Open-source alternative to Higgsfield AI — Free AI image generation & cinema studio with 20+ models (Flux, SDXL, Midjourney, Ideogram). Self-hosted, customizable, MIT licensed. |
1,481 | +32 | +354 | +839 | +1,446 | +1,413 | 346 | 44.0x faster | |
| 866 |
Local-first desktop widget for tracking token usage, costs, limits, and session activity across 47+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync. |
3,379 | +19 | +176 | +1,003 | +2,393 | +1,412 | 228 | Under 180 days | |
| 867 |
Official Hex-Rays IDA MCP Server. |
1,411 | +8 | +115 | +1,200 | +1,411all | +1,411 | 112 | New | |
| 868 |
雪解けのように、半角/全角の壁を溶かす日本語入力。 |
1,410 | +5 | +226 | +1,409all | +1,409all | +1,409 | 60 | New | |
| 869 |
Automatically builds GenP executables from source |
4,462 | +14 | +136 | +830 | +2,838 | +1,406 | 202 | 2.0x faster | |
| 870 |
🌸 The Cutest Music Player With Support Local File and Youtube Music for Android! |
7,653 | +28 | +290 | +1,198 | +3,766 | +1,403 | 300 | 1.6x faster | |
| 871 |
a fast, GPU-accelerated, full-featured IDE and terminal multiplexer, suitable both for automatic and manual programming. |
1,401 | +51 | +134 | +230 | +1,399all | +1,399 | 540 | New | |
| 872 |
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench. |
1,399 | +2 | +40 | +918 | +1,399all | +1,399 | 23 | New | |
| 873 |
Gr8r Studio: a calm, structured project management workspace. Vite + plain ES modules. |
1,399 | +89 | +546 | +1,398all | +1,398all | +1,398 | 706 | New | |
| 874 |
The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill candidates for your review. Practical application of the Augmented Expertise methodology. Open source: CC BY 4.0. |
3,575 | +12 | +121 | +665 | +2,311 | +1,397 | 138 | 2.5x faster | |
| 875 |
Next Remote Protocol Framework. |
2,757 | +124 | +933 | +1,435 | +2,073 | +1,392 | 1,453 | 3.0x faster | |
| 876 |
hanime1的三方客户端，提高了一些播放体验 |
1,393 | +8 | +60 | +344 | +1,392 | +1,391 | 84 | 1,398x faster | |
| 877 |
Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry. |
1,391 | +5 | +49 | +1,391all | +1,391all | +1,391 | 60 | New | |
| 878 |
Agent skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one |
2,056 | +7 | +100 | +357 | +1,721 | +1,389 | 106 | Under 180 days | |
| 879 |
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration. |
1,385 | +369 | +716 | +1,145 | +1,383all | +1,383 | 3,344 | New | |
| 880 |
Microduck 复刻：飞特 HD-1910 整机已实机验证（站立、行走、前滚翻起身）。镜像、Studio 网页中控、CAD/BOM、装配教程、电路工程与训练平台 | Microduck robot replica with real hardware demos. |
1,384 | +21 | +162 | +365 | +1,381all | +1,381 | 288 | New | |
| 881 |
DeepSeek Harness橙皮书《从开机到拆开》：完整系统提示词、129行启动清单、三份原始会话日志——官方文档没有的一手实测。PDF/EPUB/HTML免费下载 |
1,381 | +4 | +34 | +82 | +1,380all | +1,380 | 32 | New | |
| 882 |
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation. |
2,104 | +5 | +110 | +504 | +1,729 | +1,379 | 61 | 4.9x faster | |
| 883 |
Local AI song generator with an editable score — YuE2 on your GPU: full songs with vocals, sheet music, covers, exact replay. Native Windows app, no Python, installer with auto-update. |
1,381 | +24 | +414 | +1,183 | +1,379all | +1,379 | 195 | New | |
| 884 |
基于Vue3 + WebRTC + Nodejs + Flutter搭建的远程桌面控制、游戏串流 |
8,886 | +50 | +273 | +775 | +1,898 | +1,377 | 674 | 3.6x faster | |
| 885 |
A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities. |
2,542 | +8 | +69 | +832 | +1,957 | +1,377 | 64 | Under 180 days | |
| 886 |
ComfyUI MiniMax H3 Director workflow |
1,378 | +6 | +35 | +273 | +1,377all | +1,377 | 76 | New | |
| 887 |
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company. |
4,991 | 0 | +12 | +120 | +1,581 | +1,376 | 0 | 7.7x faster | |
| 888 |
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed. |
5,444 | +6 | +74 | +636 | +2,139 | +1,376 | 80 | 2.8x faster | |
| 889 |
No description |
1,683 | +8 | +359 | +1,377 | +1,528 | +1,375 | 70 | Under 180 days | |
| 890 |
Overdrive, a PS5 homebrew game store with 2,000+ games. |
1,375 | +33 | +449 | +1,372all | +1,372all | +1,372 | 238 | New | |
| 891 |
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music. |
1,373 | +4 | +52 | +404 | +1,371all | +1,371 | 40 | New | |
| 892 |
This repository contains the Hugging Face Agents Course. |
34,058 | +25 | +286 | +1,209 | +3,719 | +1,368 | 346 | 1.6x faster | |
| 893 |
SwiftUI agent skill for Claude Code, Codex, and other AI tools. |
6,361 | +3 | +101 | +1,530 | +2,010 | +1,367 | 27 | 3.1x faster | |
| 894 |
书童 Pagekin（原名 AI 小说作家）：开源免费的 AI 长篇小说写作桌面软件，从设定、蓝图到正文、审稿、定稿；支持拆解仿写、续写、改写，可导入写作 Skill（如去 AI 味）。模型需自行配置，作品在本地。Pagekin (formerly AI Novel Writer): free, open-source AI novel writing app for long novels and web fiction. Imitate, continue, rewrite; import writing skills. Local-first, no model bundled. Windows & macOS. |
1,881 | +47 | +234 | +762 | +1,621 | +1,366 | 504 | Under 180 days | |
| 895 |
A V2Ray client for Android, support Xray core and v2fly core |
1,370 | +9 | +90 | +439 | +1,364 | +1,362 | 88 | Under 180 days | |
| 896 |
Build native apps in JS. Backend, frontend. ~5Mb. |
1,370 | +4 | +110 | +938 | +1,364 | +1,360 | 21 | Under 180 days | |
| 897 |
Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer. |
2,513 | +10 | +71 | +304 | +1,934 | +1,358 | 96 | Under 180 days | |
| 898 |
A general-purpose window upscaler for Windows 10/11. |
16,111 | +16 | +195 | +1,140 | +1,983 | +1,357 | 147 | 3.2x faster | |
| 899 |
Turn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls. |
1,856 | +80 | +300 | +412 | +1,455 | +1,357 | 664 | 14.9x faster | |
| 900 |
No description |
1,357 | +4 | +73 | +201 | +1,356all | +1,356 | 28 | New |
Today counts stars since midnight US Pacific time, so it is a partial day. 6 more tracked repositories are still loading their star history and will join the ranking once it is complete.