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, lowest first. Star counts come from GitHub. Last updated 9 Nov 2026, 02:20 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. 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 |
|---|---|---|---|---|---|---|---|---|---|
| 11801 |
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back. |
572 | +1 | +17 | +113 | -1 | 0 | 0.7x, slowing | |
| 11802 |
A builder, not just a researcher. Agent skills that turn top-grossing app patterns into native-quality mobile screens. |
4,971 | +9 | +1,038 | +2,452 | -1 | 3 | 0.9x, slowing | |
| 11803 |
Telegram trading bot for tokens: signals, limits and stop-loss in one chat. |
290 | 0 | +181 | +282 | -1 | 0 | 0.0x, slowing | |
| 11804 |
TuraIDC - Next-generation IDC cloud service management & billing system 图拉云业务/财务系统 —— 新一代的IDC云服务经营系统 |
292 | +4 | +194 | +202 | -1 | 0 | 0.7x, slowing | |
| 11805 |
EverRoom - A workspace that remembers your projects, decisions, and sources. |
2,976 | 0 | -4 | +11 | -1 | 0 | 0.0x, slowing | |
| 11806 |
让 QQ Bot 接入 DeepSeek Harness（dsh）的官方插件 |
567 | +6 | +72 | +441 | -1 | 0 | 0.9x, slowing | |
| 11807 |
A collection of jailbreak prompts and exploit techniques for local and frontier AI models, with modern methods for Qwen3.5, Gemma 4, Llama 4, Kimi K3, GPT-OSS, GPT-5.x, Gemini 3.x and Grok 4.x. For red-teaming and AI safety research only. |
580 | +2 | +28 | +168 | -1 | 0 | 0.7x, slowing | |
| 11808 |
Paxeer X is a Distributed HyperState Machine for payments, code execution and intent routing. Designed for Machines and the Users operating them. |
540 | -1 | -5 | -3 | -1 | 0 | No data | |
| 11809 |
No description |
1,632 | +1 | +19 | +165 | -1 | 0 | 0.4x, slowing | |
| 11810 |
Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration. |
698 | +7 | +44 | +208 | -1 | 6 | 0.9x, slowing | |
| 11811 |
DSH皮肤市场Skin Market 已收录五百+皮肤、桌宠、开屏动画等；有便捷的社区收录入口，并且已有多位开发者提交皮肤；有在线页面方便在线浏；有方便安装管理本地皮肤的插件 |
315 | +1 | +22 | +134 | -1 | 0 | 0.7x, slowing | |
| 11812 |
DeepSeek Harness的Windows电脑操控插件 / Windows computer use for DeepSeek Harness |
594 | +12 | +164 | +563 | -1 | 6 | 0.9x, slowing | |
| 11813 |
Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains. |
4,141 | +1 | +51 | +202 | -1 | 0 | 0.7x, slowing | |
| 11814 |
DeepSeek Harness Mobile 是一个面向 DeepSeek Harness 的原生移动端客户端。它通过 dsh-plugin-mobile-gateway 与 Harness 建立 WebSocket 连接，将工作区、会话、实时回复和 Agent 执行轨迹带到 iPhone，同时延续 DeepSeek WebUI 克制、清晰的视觉语言 |
749 | +2 | +39 | +274 | -1 | 0 | 0.7x, slowing | |
| 11815 |
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks. |
1,217 | +1 | -11 | +38 | -1 | 0 | 0.7x, slowing | |
| 11816 |
Zetta is an efficient closed-loop embodied harness for self-evolving physical intelligence. It evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Project Page: https://air-embodied-brain.github.io/zetta/ |
1,321 | 0 | +6 | +39 | -1 | 0 | 0.0x, slowing | |
| 11817 |
https://github.com/ifixai-ai/iFixAi |
316 | 0 | -5 | +85 | -1 | 0 | 0.0x, slowing | |
| 11818 |
Deterministic guardrails that don't break agents |
1,622 | +1 | +4 | +103 | -1 | 0 | 0.7x, slowing | |
| 11819 |
AI Chat with powerful models for free |
1,527 | -1 | +8 | +41 | -1 | 0 | No data | |
| 11820 |
No description |
584 | +7 | +77 | +218 | -1 | 0 | 0.8x, slowing | |
| 11821 |
Hand-picked ESP32 projects worth building, copying, or watching run |
717 | +1 | +30 | +189 | -1 | 0 | 0.7x, slowing | |
| 11822 |
mutual layer for multiple agents from different environment or providers to work on same interface or device, toward the same final goal |
202 | -1 | +83 | +199 | -1 | 0 | No data | |
| 11823 |
DeepSeek Harness 故事创作插件：一站式集成网文连载、短剧漫剧、小说改游戏与视频解说四大工作台 ｜ Community DeepSeek Harness plugin for web novels, short dramas, games & video recaps |
712 | +3 | +46 | +231 | -1 | 0 | 0.8x, slowing | |
| 11824 |
Unofficial Claude Skill derived from the book Refactoring UI — a design rulebook and diagnostic layer for web UI. 151 tracked rules, design token generation, and Tailwind mappings. |
381 | +3 | +30 | +366 | -1 | 0 | 0.8x, slowing | |
| 11825 |
蓝色大肥鱼档案馆 |
323 | +2 | +30 | +136 | -1 | 0 | 0.7x, slowing | |
| 11826 |
No description |
720 | +3 | +61 | +237 | -1 | 0 | 0.8x, slowing | |
| 11827 |
A calm menu bar, done the native way. Hides the icons you don't need until you do. |
1,164 | +14 | +194 | +350 | -1 | 16 | 0.9x, slowing | |
| 11828 |
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。 |
961 | 0 | +3 | +65 | -1 | 0 | 0.0x, slowing | |
| 11829 |
Turn a private Telegram channel into your personal cloud drive. Android, Windows, Linux and macOS, auto backup, optional E2E encryption, built-in file manager and player. |
448 | +1 | +30 | +207 | -1 | 0 | 0.4x, slowing | |
| 11830 |
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency. |
5,436 | +1 | -2 | +374 | -1 | 0 | 0.7x, slowing | |
| 11831 |
1인 사업가 생산성 키트 — 직원 없이 58개를 자동화했고, 그중 바로 쓸 수 있는 AI 에이전트 스킬 38개(+실행 스크립트 19개)를 공개합니다 |
438 | 0 | +5 | +74 | -1 | 0 | 0.0x, slowing | |
| 11832 |
🩷 💘C × SDL3 × OpenGL — Three Mysterious Forces, United as One! Bong~ Bongocat!!!Don't be shy, Join Here🧸: https://discord.gg/vf8jqnattk |
4,054 | +7 | +78 | +485 | -1 | 3 | 0.8x, slowing | |
| 11833 |
Audit AI chat exports locally before sharing or migration. Find possible secrets, personal-data patterns, broken JSON/JSONL, SQLite issues, and scan gaps—without uploading the archive. |
986 | -1 | -2 | +253 | -1 | 0 | No data | |
| 11834 |
AI 时代的私人影库 |
1,303 | +8 | +98 | +610 | -1 | 0 | 0.9x, slowing | |
| 11835 |
DogSC — Smooth screen capture and lightweight editing for macOS. |
713 | +4 | +34 | +333 | -1 | 0 | 0.9x, slowing | |
| 11836 |
Run Omarchy on MacOS without any setup. |
2,930 | +10 | +87 | +388 | -1 | 9 | 0.9x, slowing | |
| 11837 |
No description |
2,711 | +1 | +8 | +96 | -1 | 0 | 0.4x, slowing | |
| 11838 |
✨ agentic app store previews and screenshots |
2,596 | +1 | +11 | +137 | -1 | 0 | 0.4x, slowing | |
| 11839 |
No description |
507 | +1 | +24 | +506 | -1 | 0 | 0.7x, slowing | |
| 11840 |
灵感源自 macOS 动态屏保体验，为 Windows 打造的轻量原生动态壁纸与屏保应用，支持多显示器、智能性能副本和低功耗播放。 |
321 | +2 | +116 | +296 | -1 | 0 | 0.7x, slowing | |
| 11841 |
SEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, deterministic. |
987 | 0 | +1 | +304 | -1 | 0 | 0.0x, slowing | |
| 11842 |
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port. |
1,265 | +7 | +78 | +351 | -1 | 9 | 0.9x, slowing | |
| 11843 |
Halo is an open-source framework built by White Circle for training large language and multimodal models |
851 | 0 | +12 | +34 | -1 | 0 | 0.0x, slowing | |
| 11844 |
Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun, MTProto) |
864 | -1 | +3 | +24 | -1 | 0 | No data | |
| 11845 |
Code for "Meta^n: Recursive Self-Improvement through Emergent Depth" |
86 | 0 | +3 | +51 | -1 | 0 | 0.0x, slowing | |
| 11846 |
Watch for bugs like a hawk! gohawk is a set of static analyzers for Go, focused on concurrency and resource-lifetime bugs. |
141 | +2 | +43 | +133 | -1 | 0 | 0.7x, slowing | |
| 11847 |
NORDEF Matrix Open Control: model-independent AI safety belt with 0/1/2 decisions, Ed25519 root gate, replay protection, evidence chain, and incident-pattern eval bank |
680 | -1 | -33 | +105 | -1 | 0 | No data | |
| 11848 |
A Claude Code skill that applies the concrete design rules from the book Refactoring UI (Wathan & Schoger) — constrained spacing/type/color/shadow scales, hierarchy through weight and color, and depth through emulated light — to building and fixing interfaces. |
695 | +1 | +15 | +104 | -1 | 0 | 0.7x, slowing | |
| 11849 |
Fire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다 |
997 | 0 | +10 | +295 | -1 | 0 | 0.0x, slowing | |
| 11850 |
A simple PoToken minter written in Java |
574 | +1 | +33 | +106 | -1 | 0 | 0.7x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.