GitHub repositories taking off today
Ranked by how many more stars each repo got today so far (since midnight US Pacific) than yesterday's pace would predict. Star counts come from GitHub. Last updated 15 Nov 2026, 09:20 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 it belongs to a personal account with no followers and either is under 3 days old with no watchers and at least 5 forks, or is under 30 days old with at least half as many forks as stars and 128 KB or less of files while that account is under a year old; 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 |
|---|---|---|---|---|---|---|---|---|---|
| 40101 |
An Android Auto alternative built for everyone |
362 | 0 | +33 | +238 | 0 | 0 | No data | |
| 40102 |
The official repo of GameHorizon, a unified data and evaluation suite that measures AAA gameplay capabilities at different temporal horizons for diverse model families. |
602 | 0 | +1 | +33 | 0 | 0 | No data | |
| 40103 |
Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open. |
3,234 | 0 | -28 | +1,403 | 0 | 0 | No data | |
| 40104 |
Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fabric. |
211 | 0 | +55 | +196 | 0 | 39 | No data | |
| 40105 |
No description |
79 | 0 | +15 | +68 | 0 | 8 | No data | |
| 40106 |
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU. |
712 | 0 | +34 | +282 | 0 | 0 | No data | |
| 40107 |
Jade Engine implementation for Prince of Persia trilogy games |
152 | 0 | +9 | +132 | 0 | 8 | No data | |
| 40108 |
Bold control panel for your server, one-click deploy on Railway |
592 | 0 | +7 | +21 | 0 | 0 | No data | |
| 40109 |
Open Source virtual tabletop for Obsidian: battle maps, tokens, fog of war, dice, initiative and a separate player view. |
683 | 0 | +11 | +81 | 0 | 0 | No data | |
| 40110 |
面向开发者与 AI Agent 的开源流量调试工作台,让业务异常可筛选、调试修改可追溯、排查现场可分享。 |
310 | 0 | +23 | +307 | 0 | 0 | No data | |
| 40111 |
A git hook that won't let you push code you can't explain. Quizzes you on your own diff. Works with Claude Code, Codex, Cursor. |
219 | 0 | 0 | -9 | 0 | 0 | No data | |
| 40112 |
The first, live, hinge-driven opening animation for the Galaxy Z Fold8. Features smooth windowed glass, modular settings, and 120hz live preview (even iPhone doesn't have this) → 90% complete. Need to discover method of preventing display shut-off during changeover. |
171 | 0 | +1 | +42 | 0 | 0 | No data | |
| 40113 |
Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API |
547 | 0 | +4 | +29 | 0 | 0 | No data | |
| 40114 |
非自回归System 1决策引擎,专为结构化类型决策场景设计 DeepOpen Multilingual, non-autoregressive System 1 decision engine. |
3,075 | 0 | 0 | +1,054 | 0 | 0 | No data | |
| 40115 |
Drive Google Flow from Claude, Codex or a local control panel, on Mac or Windows — using your Google AI subscription credits instead of the pay-per-use video API. No browser extension. |
631 | 0 | +80 | +448 | 0 | 0 | No data | |
| 40116 |
对话式 AI 助手 · All in Chat - 把 Agent 能力装进对话里,无需复杂配置,像聊天一样使用 Agent。已内置破甲角色「小码酱」,支持国模破甲。 |
1,364 | +2 | +370 | +1,306 | 0 | 85 | No data | |
| 40117 |
project on fine-tuning qwen to generate text w/o letter 'e' |
186 | 0 | +16 | +183 | 0 | 0 | No data | |
| 40118 |
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework |
760 | 0 | +9 | +45 | 0 | 0 | No data | |
| 40119 |
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request) |
1,609 | 0 | +13 | +267 | 0 | 0 | No data | |
| 40120 |
✅ Acceptance is open-source e2e testing for Agents. Your coding agent turns a prompt into observable checks, runs the real product, and publishes a report with screenshots, recordings, and logs attached to each check. You can accept the work, or send individual checks back. |
98 | 0 | +5 | +63 | 0 | 0 | No data | |
| 40121 |
AI 工程面试题(按公司分类)中文版 —— 顶级 AI 公司 AI 工程面试速查手册,附答案链接 |
308 | 0 | +11 | +305 | 0 | 8 | No data | |
| 40122 |
Plugins and mods that make Claude Code better: work with the local Codex CLI, watch the prompt cache, preview pasted images. |
203 | 0 | 0 | +200 | 0 | 0 | No data | |
| 40123 |
The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具:先看懂对方再回复,发不发由你。 |
8,384 | 0 | +79 | +574 | 0 | 33 | No data | |
| 40124 |
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K. |
1,517 | 0 | +4 | +1,040 | 0 | 0 | No data | |
| 40125 |
聊天悬浮窗助手(macOS):屏幕感知 + 本地小模型判断意图与风险,按话术生成回复候选。纯只读。 |
529 | 0 | +4 | +33 | 0 | 0 | No data | |
| 40126 |
Launch any app or trigger quick actions from the status bar or anywhere on your screen. |
305 | 0 | +20 | +126 | 0 | 16 | No data | |
| 40127 |
🐋 DSH 鱼的记忆:给会话一份会淡忘的长期记忆,每条都带时间。名字里的「鱼」来自 DeepSeek 的鲸鱼。 |
520 | 0 | +16 | +517 | 0 | 0 | No data | |
| 40128 |
ProphetLab's Texas Hold'em benchmark and playground for decision models: cash and SNG leaderboards, live replays, and bring-your-own-agent tables. |
45 | 0 | +1 | +32 | 0 | 0 | No data | |
| 40129 |
JevChat-Windows:聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入,发送永远手动 |
890 | 0 | +12 | +81 | 0 | 8 | No data | |
| 40130 |
The agentic CLI for the entire Cloudflare API |
1,045 | 0 | +31 | +159 | 0 | 0 | No data | |
| 40131 |
No description |
1,194 | 0 | +7 | +68 | 0 | 0 | No data | |
| 40132 |
Async-first agent harness |
2,232 | 0 | +12 | +32 | 0 | 0 | No data | |
| 40133 |
Self-hosted, non-custodial stablecoin payment gateway with x402 and invoice checkout. Accepts USDC, USDT, PYUSD and DAI across 8 networks with QR payments, payment links, settlement tracking and signed webhooks. REST API, micropayments, exports, zero platform fees and no KYC. Python, cross-platform. |
334 | 0 | +2 | +138 | 0 | 0 | No data | |
| 40134 |
Multi-chain crypto wallet risk scanner for AML/KYT screening. Scores addresses 0–100 using sanctions, risky contracts and fund tracing. Integrates 6 intelligence providers with failover, detects scams, hacks, mixers and phishing, supports 15+ chains, batch screening and TXT/JSON/CSV/HTML/PDF reports. Python, cross-platform. |
914 | 0 | +667 | +669 | 0 | 0 | No data | |
| 40135 |
Control your Android phone with natural language. No computer required. Powered by Midscene, with Skills and a Codex plugin. |
136 | 0 | +1 | +135 | 0 | 0 | No data | |
| 40136 |
No description |
79 | 0 | +12 | +74 | 0 | 16 | No data | |
| 40137 |
Launch what you built on Jev, TypeSafe AI's System One decision model: a weekly board where makers launch and people vote, over an index of public Jev examples by decision pattern, with source citations, dated link checks and call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema, platform matrix. |
602 | 0 | 0 | +13 | 0 | 0 | No data | |
| 40138 |
DeepSeek Harness 的启动界面与启动动画插件 |
842 | 0 | +37 | +642 | 0 | 24 | No data | |
| 40139 |
An intuitive, color-accurate, professional RAW photo editor. |
160 | 0 | +38 | +142 | 0 | 6 | No data | |
| 40140 |
No description |
51 | 0 | 0 | +51 | 0 | 0 | No data | |
| 40141 |
A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection. |
562 | 0 | +19 | +274 | 0 | 0 | No data | |
| 40142 |
Archive of Google Summer of Code (GSoC) accepted proposals across years for community reference and inspiration. |
398 | 0 | +6 | +145 | 0 | 0 | No data | |
| 40143 |
mu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi. |
605 | 0 | +19 | +89 | 0 | 8 | No data | |
| 40144 |
The Open EDG C & C++ Compiler Project |
1,040 | 0 | +15 | +105 | 0 | 0 | No data | |
| 40145 |
Codex computer use, decoupled from the app, for usage inside any harness. |
2,426 | 0 | +28 | +1,280 | 0 | 0 | No data | |
| 40146 |
ARTEX 二次开发版:外网突破→内网纵深全流程自主渗透平台(上游 Autumn-27/ARTEX,AGPL-3.0) |
89 | 0 | +11 | +89 | 0 | 24 | No data | |
| 40147 |
GDScript Compiler for Godot. |
315 | 0 | +265 | +274 | 0 | 0 | No data | |
| 40148 |
降低Deepseek v4.1flash的Token消耗/Raising Token efficiency without lossing performance(Works for v4.1flash) |
202 | 0 | +56 | +192 | 0 | 5 | No data | |
| 40149 |
Agnes Harness: A pluggable agent harness for Forward Deployed Engineering (FDE). Built for trust. Made for the real world. |
2,082 | 0 | +67 | +1,401 | 0 | 0 | No data | |
| 40150 |
A sensible Zulip client |
675 | 0 | 0 | -177 | 0 | 0 | No data |
Today counts stars since midnight US Pacific time, so it is a partial day.