GitHub repositories taking off in the last 7 days
Ranked by how many more stars each repo got in the last 7 days than its pace over the 7 days before would predict. Star counts come from GitHub. Last updated 12 Nov 2026, 07:20 UTC.
?
- 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: 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.
- Suspected
- Repositories with at least 50 stars are left out as likely bought stars when they have no detected programming language and got those stars within a day of being created; or got them within 14 days while having no watchers, at most 1 fork, no detected language or under 1 KB of code other than HTML and CSS, and either 5 KB or less of files or an owner that is a personal account with at most 1 follower. Repositories with no detected language are also left out when, at any age, they have 5 KB or less of files and got at least 90% of their stars on a single day that ended more than a day ago; or have 5 KB or less of files and belong to a personal account with no followers that was created at most an hour before the repository. Any repository with at least 50 stars is also left out when, under 3 days old, it has no watchers and at least 5 forks and belongs to a personal account with no followers; it stays out while that account has no followers. Some repositories are also left out, or kept in, by hand after a review of the daily lists, whatever the rules above say. See them.
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 27101 |
The AI Org-OS — a collaborative platform for humans and agents. Explore: https://spaces.xyne.ai |
826 | 0 | 0 | +25 | -1 | 0 | 0.0x, slowing | |
| 27102 |
🔥🔥🔥AI skills大全 mcp ai知识库 Agent 全维度 AI 资源百科，DSH插件 收录大模型、智能 Agent、RAG 检索增强、多模态、MLOps、AI 应用工具、AI面试集、Vibe coding 大全、零基础学习路线，持续更新前沿 AI 开源项目，开发者一站式 AI 导航库 |
690 | +6 | +91 | +232 | -1 | 14 | 1.0x, steady | |
| 27103 |
GrokFree注册机 - 支持生成CPA、grok2api、sub2api格式的json鉴权文件 |
534 | +2 | +6 | +42 | -1 | 0 | 0.9x, slowing | |
| 27104 |
Self-contained malware research hub: curated catalog of 80 families (1971-2024) + 2,764 real encrypted samples, indexed and searchable. Local Flask app, bilingual. |
676 | +3 | +5 | +22 | -1 | 24 | 0.8x, slowing | |
| 27105 |
WeType Tool 模块发布仓库 |
253 | +3 | +25 | +136 | -1 | 0 | 1.0x, steady | |
| 27106 |
Any version of any nixpkgs package, from one flake input |
517 | +2 | +6 | +30 | -1 | 0 | 0.9x, slowing | |
| 27107 |
Annotate terminal text, review documents and agent replies in Herdr, and send the feedback straight back to the agent. |
748 | +7 | +19 | +92 | -1 | 24 | 1.0x, steady | |
| 27108 |
DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF） |
966 | +1 | +23 | +111 | -1 | 0 | 1.0x, steady | |
| 27109 |
DeepSeek Harness plugin store, marketplace and hub — 11,000+ dsh plugins with search, rankings, install commands and a free public API. DeepSeek Harness 插件市场 / 插件商店：自动收集与格式校验，免费搜索 API。deepseek1024.com |
389 | +4 | +28 | +109 | -1 | 0 | 1.0x, steady | |
| 27110 |
No description |
148 | +1 | +10 | +53 | -1 | 8 | 0.9x, slowing | |
| 27111 |
No description |
324 | +15 | +51 | +259 | -1 | 120 | 1.0x, steady | |
| 27112 |
AuK: An Open-Source Foundational Model for Speech Generation and Editing |
1,593 | +1 | +16 | +95 | -1 | 0 | 0.9x, slowing | |
| 27113 |
🌌 Mebular 忆云 · 智能体共享记忆与任务协作 | One shared memory and task graph for all your AI agents and devices: automatic or on-demand, secure, controllable, and decentralized! |
174 | +9 | +61 | +173 | -1 | 12 | 1.0x, steady | |
| 27114 |
让 Codex 根据最终结果生成标题、注释、commit 和 PR，减少被否决方案在交付中的残留。 |
970 | +3 | +10 | +63 | -1 | 0 | 0.9x, slowing | |
| 27115 |
Reference implementation of FINESSE: self-reflective multi-agent financial reasoning with dynamic expert routing and ethical verification. |
390 | +8 | +60 | +241 | -1 | 5 | 1.0x, steady | |
| 27116 |
An automated benchmark platform for AI-generated apps — built-in evaluation rules, standard sample sets, and layered test cases across a multi-dimensional metric system. One pipeline runs build, install, E2E tests, and scoring into a shareable report. |
429 | 0 | +50 | +189 | -1 | 0 | 1.0x, steady | |
| 27117 |
Lecture and lab slides for EECS 498 AASE (Applied Agentic Software Engineering), UMich Fall 2026 |
336 | 0 | +3 | +322 | -1 | 0 | 0.8x, slowing | |
| 27118 |
养成类游戏英语学习 |
799 | 0 | +2 | +142 | -1 | 0 | 0.7x, slowing | |
| 27119 |
Qwen3.8-Flash-Next on ONE DGX Spark (TP=1) |
634 | +2 | +8 | +45 | -1 | 0 | 0.9x, slowing | |
| 27120 |
No description |
635 | +2 | +22 | +154 | -1 | 0 | 1.0x, steady | |
| 27121 |
国家反诈AI API 转 OpenAI 兼容格式反向代理服务 || 仅学习用途 |
631 | 0 | +4 | +31 | -1 | 0 | 0.8x, slowing | |
| 27122 |
Cross-platform Cloudflare Turnstile solver (macOS, Windows, Linux) |
517 | +2 | +4 | +21 | -1 | 0 | 0.8x, slowing | |
| 27123 |
The official codebase of Unified Motion Retargeting |
526 | 0 | +6 | +51 | -1 | 0 | 0.9x, slowing | |
| 27124 |
Stop letting AI code blind. Map the architecture before every change with Birdview. |
686 | 0 | +11 | +49 | -1 | 0 | 0.9x, slowing | |
| 27125 |
Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report. |
517 | 0 | +1 | +11 | -1 | 0 | 0.5x, slowing | |
| 27126 |
把直播、课程、演讲、口播等长视频自动切成精彩片段｜本地语音识别，音频不出本机；LLM 挑高光，批量导出 |
535 | 0 | 0 | +145 | -1 | 0 | 0.0x, slowing | |
| 27127 |
Android-only Nintendo Switch emulator for Adreno GPUs: new interface, Lemon Cheater memory editor, savestates and NSZ/XCZ support. Mirror of git.lemon-emu.org/lemon/Lemon-Project |
303 | +2 | +16 | +166 | -1 | 8 | 0.9x, slowing | |
| 27128 |
CSAPP 中文文档与学习资料：《深入理解计算机系统》第三版全章节 Markdown，含练习题答案、八大实验中文翻译及官方自学实验包，方便在线阅读与离线学习。 |
1,157 | +2 | +29 | +230 | -1 | 0 | 1.0x, steady | |
| 27129 |
PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstream behavior is the contract, and Go is the implementation language. |
847 | +6 | +37 | +263 | -1 | 0 | 1.0x, steady | |
| 27130 |
An awesome collection of Jev use cases, workflows, and agent skills. |
668 | 0 | +4 | +59 | -1 | 0 | 0.8x, slowing | |
| 27131 |
Open, lightweight multimodal decision models for text, images, and video. Train and run them yourself. |
911 | +3 | +11 | +146 | -1 | 16 | 0.9x, slowing | |
| 27132 |
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. |
1,458 | +1 | +21 | +163 | -1 | 0 | 1.0x, steady | |
| 27133 |
HAEnv — synthetic longitudinal patients with code-derived gold, for evaluating health agents over time |
221 | +4 | +47 | +218 | -1 | 0 | 1.0x, steady | |
| 27134 |
MacOS Tahoe-like shell for Hyprland |
385 | +14 | +37 | +378 | -1 | 7 | 1.0x, steady | |
| 27135 |
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable |
1,185 | +4 | +25 | +208 | -1 | 0 | 1.0x, steady | |
| 27136 |
Fast, memory-safe camera RAW decoder in Rust: ~40 formats, SIMD, GPU, WebAssembly, ICC colour management. CLI, C, C++, Python and JavaScript bindings. |
122 | 0 | +4 | +122 | -1 | 0 | 0.8x, slowing | |
| 27137 |
Self-healing Docker CI: BuildKit failure taxonomy, Claude Code fixes, rebuild verification, capped retries. |
111 | 0 | -1 | +109 | -1 | 0 | No data | |
| 27138 |
A motion design studio on your own machine: Claude makes the video step by step, you approve every stage. Bring your own Claude Code or API key. |
696 | 0 | +14 | +105 | -1 | 0 | 0.9x, slowing | |
| 27139 |
Liquid Glass and Apple Music touches for the Spotify iOS app. A GPL-3.0 fork of spoti.pw 0.21.1. |
305 | +5 | +19 | +242 | -1 | 0 | 1.0x, steady | |
| 27140 |
ReStreet: FIFA Street (2012) recompiled for Windows PC, with online play, a launcher with friends, chat and rooms. Bring your own game. |
510 | +1 | +26 | +437 | -1 | 0 | 1.0x, steady | |
| 27141 |
Read-only, local-first cloud security scanner for AWS, Azure and GCP. Your scan data stays on your machine. |
210 | 0 | -1 | +209 | -1 | 0 | No data | |
| 27142 |
No description |
1,780 | +12 | +77 | +867 | -1 | 18 | 1.0x, steady | |
| 27143 |
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and GPT-6 Astra Ultra. |
479 | +14 | +103 | +448 | -1 | 10 | 1.0x, steady | |
| 27144 |
🍟 麦当劳中国官方 MCP 智能助手技能：把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算，下单必二次确认。｜McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill splitting. |
379 | 0 | 0 | +372 | -1 | 0 | 0.0x, slowing | |
| 27145 |
A native macOS file browser with fast fuzzy filename search, powered by fsearch. |
699 | +1 | +3 | +52 | -1 | 0 | 0.8x, slowing | |
| 27146 |
麦当当的宇宙，一个能够理解预算、心情、用餐场景的 AI 助手，通过麦当劳 MCP 获取真实可用的信息，再生成个性化推荐、挑战任务和可分享的结果卡片。 |
137 | 0 | -1 | +129 | -1 | 0 | No data | |
| 27147 |
A free desktop encyclopedia for Windows, Mac, and Linux, inspired by the CD-ROM reference software of the early 2000s and powered by Wikipedia, online or offline. Public beta. |
54 | 0 | +7 | +49 | -1 | 0 | 0.9x, slowing | |
| 27148 |
A Japanese font that shows furigana by itself. |
432 | 0 | +7 | +431 | -1 | 0 | 0.9x, slowing | |
| 27149 |
A fun McDonald's personality test powered by MBTI logic. |
135 | 0 | -1 | +134all | -1 | 0 | No data | |
| 27150 |
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory |
461 | +10 | +76 | +459all | -1 | 38 | 1.0x, steady |
Today counts stars since midnight US Pacific time, so it is a partial day.