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 | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 2001 |
众多优秀广告规则的上游、开源社区中最棒的广告过滤器之一。适配AdGuard/Home/DNS、AdAway、hosts、Mosdns、ClashMeta、QuantumultX等主流广告拦截工具/代理工具。 |
6,702 | -2 | +23 | +167 | -17 | 0 | 0.6x, slowing | |
| 2002 |
A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize. |
10,712 | +6 | +35 | +173 | -17 | 56 | 0.7x, slowing | |
| 2003 |
The LLM Evaluation Framework |
19,144 | +14 | +143 | +694 | -17 | 198 | 0.9x, slowing | |
| 2004 |
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. |
14,962 | +6 | +71 | +262 | -17 | 43 | 0.8x, slowing | |
| 2005 |
🪓 An orchestration engine for background tasks, AI agents, and durable workflows |
8,191 | +5 | +33 | +189 | -17 | 48 | 0.7x, slowing | |
| 2006 |
A repository that helps users get affinity software working on GNU/Linux 🐧 |
3,241 | +2 | +10 | +110 | -17 | 24 | 0.4x, slowing | |
| 2007 |
coss.com/ui is the official design system of Cal.com |
10,757 | +6 | +28 | +154 | -17 | 48 | 0.6x, slowing | |
| 2008 |
🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling. |
16,384 | +8 | +73 | +314 | -17 | 72 | 0.8x, slowing | |
| 2009 |
A cross-platform private music playback service |
4,621 | +12 | +104 | +556 | -17 | 144 | 0.9x, slowing | |
| 2010 |
Real-time monitoring dashboard for Proxmox VE, PBS, Docker, Kubernetes, TrueNAS and vSphere. Self-hosted, with alerts for failed backups, full disks, unhealthy containers and offline nodes. |
6,959 | +11 | +57 | +217 | -17 | 120 | 0.8x, slowing | |
| 2011 |
openDAW is a next-generation web-based Digital Audio Workstation (DAW) |
2,383 | +2 | +25 | +228 | -17 | 24 | 0.6x, slowing | |
| 2012 |
Browser-based ground station suite for celestial body, mission and satellite tracking, SDR reception, hardware control, and telemetry decoding |
4,865 | 0 | +7 | +59 | -17 | 8 | 0.3x, slowing | |
| 2013 |
Incremental engine for long horizon agents 🌟 Star if you like it! |
11,767 | +6 | +36 | +187 | -17 | 88 | 0.7x, slowing | |
| 2014 |
周润发公益免费v2ray节点订阅、翻墙、免费翻墙、免费科学上网、免费节点、免费梯子、免费ss/v2ray/trojan节点、蓝灯、谷歌商店、翻墙梯子、v2ray节点、免费节点、免费v2ray节点、最新公益免费v2ray节点订阅地址、免费v2ray节点每日更新、免费v2ray/clash/singbox节点 |
1,293 | 0 | +25 | +133 | -17 | 6 | 0.6x, slowing | |
| 2015 |
YouTube and YouTube Music in a single app. No ads, plays in the background. |
1,456 | 0 | +24 | +147 | -17 | 12 | 0.6x, slowing | |
| 2016 |
Free, open-source Windows optimization tool for performance, privacy, and simplicity. |
10,663 | +9 | +119 | +1,004 | -17 | 118 | 0.9x, slowing | |
| 2017 |
Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement. |
13,166 | +18 | +196 | +990 | -17 | 204 | 0.9x, slowing | |
| 2018 |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models |
4,788 | 0 | +14 | +88 | -17 | 0 | 0.5x, slowing | |
| 2019 |
385 AI skills, 76 expert agents, and 906 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants. |
993 | +4 | +34 | +165 | -17 | 48 | 0.7x, slowing | |
| 2020 |
The Generative UI framework |
18,810 | +6 | +72 | +498 | -17 | 72 | 0.8x, slowing | |
| 2021 |
数学建模技能 - 面向 CUMCM、MCM/ICM 等数学建模竞赛的三阶段工作流：建模分析、Python/MATLAB 编程与 DOCX 论文生成。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本 |
1,889 | +2 | +8 | +64 | -17 | 26 | 0.3x, slowing | |
| 2022 |
Measuring and evolving with the frontier of agent work |
977 | +1 | +33 | +185 | -17 | 28 | 0.7x, slowing | |
| 2023 |
Talk to research papers like talking to authors - Python package with AI agent for arXiv papers |
841 | +2 | +8 | +48 | -17 | 16 | 0.3x, slowing | |
| 2024 |
🎬 seedance2接入 开源本地 AI 短剧 & 漫剧生成工具 —— 从故事到成片一站式完成，数据不出本机，短剧工作流管理平台，高灵活度，AI真人剧，AI漫剧本地搞定。 Open-source local AI short drama maker: story → storyboard → video, fully offline, your data stays yours. 纳米流水线 |
2,248 | +3 | +89 | +388 | -17 | 86 | 0.8x, slowing | |
| 2025 |
Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context; get tailored, production-ready output. Cursor, Claude Code, OpenClaw — no lock-in. |
1,064 | -1 | +6 | +72 | -17 | 0 | 0.3x, slowing | |
| 2026 |
✨多agent实现全自动AI小说生成 |
2,244 | +4 | +34 | +194 | -17 | 40 | 0.7x, slowing | |
| 2027 |
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click |
41,640 | +50 | +488 | +2,466 | -17 | 586 | 1.0x, steady | |
| 2028 |
The best place to build with your AI sub |
2,141 | +5 | +14 | +257 | -17 | 32 | 0.5x, slowing | |
| 2029 |
FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B |
764 | +4 | +45 | +166 | -17 | 40 | 0.7x, slowing | |
| 2030 |
Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org |
543 | 0 | +1 | +34 | -17 | 0 | 0.1x, slowing | |
| 2031 |
No description |
777 | +2 | +25 | +172 | -17 | 24 | 0.6x, slowing | |
| 2032 |
better agentic engineering |
4,351 | 0 | +10 | +73 | -17 | 0 | 0.4x, slowing | |
| 2033 |
134+ free LLM APIs & AI API keys from 40+ providers. Google Gemini, NVIDIA NIM, Groq, OpenRouter & more. One-click setup for Claude Code, Cursor and Codex. |
4,795 | +20 | +296 | +1,422 | -17 | 233 | 0.9x, slowing | |
| 2034 |
Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration. |
1,282 | +1 | +15 | +171 | -17 | 24 | 0.5x, slowing | |
| 2035 |
Email for professionals and teams |
5,181 | +9 | +74 | +1,462 | -17 | 88 | 0.8x, slowing | |
| 2036 |
Give cloud AI agents a real development environment on your own machines. |
2,436 | +14 | +63 | +463 | -17 | 148 | 0.8x, slowing | |
| 2037 |
🐹 Cleanup, app management, maintenance, disk analysis, and live status in one free, open-source, native Mac app + extensive support for AI agents. |
1,603 | -1 | +11 | +161 | -17 | 0 | 0.4x, slowing | |
| 2038 |
access to david ondrej's personal agent skills |
4,173 | 0 | +14 | +105 | -17 | 8 | 0.5x, slowing | |
| 2039 |
指纹浏览器、纯协议全自动ChatGPT FREE注册机+Codex自动接码授权、对接提链服务器 |
1,712 | +6 | +41 | +231 | -17 | 54 | 0.7x, slowing | |
| 2040 |
Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard. |
886 | +35 | +180 | +473 | -17 | 392 | 0.9x, slowing | |
| 2041 |
Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime. |
3,970 | +184 | +1,769 | +3,817 | -17 | 1,142 | 1.0x, steady | |
| 2042 |
Make any agent harness multimodal-native. |
3,148 | -1 | +4 | +132 | -17 | 0 | 0.2x, slowing | |
| 2043 |
A股行情分析与AI智能投研智能体：股票分析、量化交易分析、盘后复盘桌面工作台——easy stock |
1,667 | +9 | +101 | +722 | -17 | 77 | 0.9x, slowing | |
| 2044 |
Wiicompiled |
1,292 | +5 | +69 | +291 | -17 | 59 | 0.8x, slowing | |
| 2045 |
Deterministic guardrails that don't break agents |
1,609 | +1 | +15 | +1,589 | -17 | 16 | 0.5x, slowing | |
| 2046 |
Install Command：npm install |
2,190 | +5 | +54 | +288 | -17 | 82 | 0.8x, slowing | |
| 2047 |
No description |
2,023 | +9 | +40 | +487 | -17 | 162 | 0.7x, slowing | |
| 2048 |
Automation for MS Rewards based on https://youtu.be/4qdPcMNaioA |
1,064 | 0 | +10 | +132 | -17 | 0 | 0.4x, slowing | |
| 2049 |
Grab your own cool 'runs-on.dev' subdomain to use for free forever. |
500 | +1 | +31 | +146 | -17 | 6 | 0.6x, slowing | |
| 2050 |
TypeLLM: LLMs with type-safe generation |
972 | 0 | +3 | +160 | -17 | 0 | 0.2x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 134 more tracked repositories are still loading their star history and will join the ranking once it is complete.