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 14 Nov 2026, 05:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 33501 |
An agent skill for building premium, immersive, scroll-driven websites. Works with Codex, Claude Code, and other coding agents. Also available as a Claude Code plugin. |
5,049 | +43 | +381 | +1,612 | 0 | 36 | 1.0x, steady | |
| 33502 |
多市场智能量化工作台（A股/港股/美股）— 基于 shy3130/tickflow-stock-panel 二次开发，新增港美股多市场支持。自托管选股+监控+回测。MIT。 |
335 | +2 | +45 | +186 | 0 | 0 | 1.1x faster | |
| 33503 |
A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse. |
901 | +2 | +8 | +134 | 0 | 0 | 1.1x faster | |
| 33504 |
Verify that the PowerPoint you are about to deliver is exactly the PPTX that passed QA—locally, offline, and with tamper-evident evidence. |
982 | 0 | 0 | +168 | 0 | 0 | No data | |
| 33505 |
Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success. |
983 | 0 | +1 | +131 | 0 | 0 | No data | |
| 33506 |
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 | 0 | -1 | +174 | 0 | 0 | No data | |
| 33507 |
StarPie 现代化 Windows 鼠标轮盘手势系统 |
1,363 | +2 | +25 | +217 | 0 | 0 | 1.1x faster | |
| 33508 |
Job board CLI for coding agents. Search and judge millions of worldwide postings from all white-collar sectors, refreshed hourly. |
570 | 0 | +2 | +15 | 0 | 0 | No data | |
| 33509 |
Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS |
3,560 | 0 | +5 | +35 | 0 | 0 | No data | |
| 33510 |
No description |
2,716 | +1 | +9 | +92 | 0 | 0 | 1.1x faster | |
| 33511 |
Agent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs. |
183 | 0 | +36 | +101 | 0 | 0 | No data | |
| 33512 |
pstack for Claude Code and Codex, tracking Cursor pstack upstream |
572 | +2 | +15 | +161 | 0 | 0 | 1.1x faster | |
| 33513 |
No description |
516 | +2 | +12 | +516 | 0 | 0 | 1.1x faster | |
| 33514 |
My AI learning system. |
4,205 | +12 | +99 | +644 | 0 | 3 | 1.0x, steady | |
| 33515 |
Agent skills for building with TypeSafe's System One API |
2,899 | +3 | +16 | +206 | 0 | 0 | 1.1x faster | |
| 33516 |
云取 YunGet：网盘分享解析与高速下载 Android 应用，基于 CYQawa/YunX 二次开发。支持夸克/UC/迅雷/百度/123/139/115/光鸭/蓝奏等平台，下载由 TurboDL 引擎承担。AGPL-3.0。 |
392 | +4 | +36 | +223 | 0 | 0 | 1.1x faster | |
| 33517 |
Claude Code plugin for writing triager-grade bug bounty reports |
375 | 0 | +6 | +119 | 0 | 0 | No data | |
| 33518 |
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. |
989 | 0 | +3 | +278 | 0 | 0 | No data | |
| 33519 |
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 | +29 | +169 | 0 | 0 | No data | |
| 33520 |
Monid - OpenRouter for agent tools. Join our community at https://discord.gg/rQzztcgJV8 |
6,191 | +7 | +52 | +2,489 | 0 | 0 | 1.0x, steady | |
| 33521 |
CraftStation Agent Runtime Composition System |
933 | 0 | 0 | +357 | 0 | 0 | No data | |
| 33522 |
我的电视 TV直播软件，极简页面支持收看国内电视直播 |
549 | +1 | +7 | +84 | 0 | 0 | 1.1x faster | |
| 33523 |
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. |
1,330 | +10 | +82 | +350 | 0 | 4 | 1.0x, steady | |
| 33524 |
Code for "Meta^n: Recursive Self-Improvement through Emergent Depth" |
87 | 0 | +2 | +51 | 0 | 0 | No data | |
| 33525 |
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語. |
2,528 | +6 | +63 | +469 | 0 | 0 | 1.0x, steady | |
| 33526 |
Move AI conversations between ChatGPT, Claude, Gemini, and DeepSeek with a local-first, open conversation format—no servers, no tracking. |
625 | 0 | 0 | +1 | 0 | 0 | No data | |
| 33527 |
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 | 0 | -1 | +81 | 0 | 0 | No data | |
| 33528 |
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU |
1,207 | +1 | +9 | +458 | 0 | 0 | 1.1x faster | |
| 33529 |
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. |
699 | 0 | +7 | +95 | 0 | 0 | No data | |
| 33530 |
A DeepSeek Harness (dsh) dynamic plugin that cuts token cost without cutting model intelligence |
82 | +1 | +10 | +58 | 0 | 0 | 1.1x faster | |
| 33531 |
recipe for running Qwen3.8-Flash-Next on a single DGX Spark |
520 | +1 | +12 | +80 | 0 | 0 | 1.1x faster | |
| 33532 |
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin. |
629 | 0 | 0 | +44 | 0 | 0 | No data | |
| 33533 |
Curso de SDD (Spec-Driven Development) desde cero |
803 | +2 | +13 | +100 | 0 | 0 | 1.1x faster | |
| 33534 |
Learn AI agents from first principles to production. Zero mandatory dependencies, pure standard Python 3.11+, and no magic frameworks. |
91 | +1 | +3 | +70 | 0 | 0 | 1.1x faster | |
| 33535 |
Cross-Platform Micro-VM Sandbox for Agentic Workloads |
838 | +1 | +12 | +441 | 0 | 0 | 1.1x faster | |
| 33536 |
解决bilibili海外用户卡顿的终极插件 |
1,690 | +4 | +71 | +362 | 0 | 0 | 1.1x faster | |
| 33537 |
Connect locally signed-in WorkBuddy models to DeepSeek Harness with a read-only credits overview and model management. |
1,563 | +39 | +296 | +1,427 | 0 | 46 | 1.0x, steady | |
| 33538 |
A tiny, self-hosted notification inbox for developers. Something happened in one of your apps; Boop tells you on your phone. |
1,278 | +2 | +11 | +277 | 0 | 0 | 1.1x faster | |
| 33539 |
Free SEO MCP server + open-source SEO and GEO skills for Claude: keyword research, rank tracking, audits, backlinks, AI visibility on your real GSC/GA4/ads data. claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp |
9,523 | +82 | +635 | +4,015 | 0 | 89 | 1.0x, steady | |
| 33540 |
A self-hosted AI platform with a Go server, multi-provider routing, usage tracking and an admin console, with chat and agentic work modes. |
714 | 0 | +19 | +227 | 0 | 0 | No data | |
| 33541 |
SABER enables identity-resolved quantification of multi-animal social behavior |
222 | 0 | 0 | +215 | 0 | 0 | No data | |
| 33542 |
Fix text typed in the wrong keyboard layout (Thai ↔ English) on Windows. Fast, tiny, no network code. |
31 | 0 | 0 | +31 | 0 | 0 | No data | |
| 33543 |
Web UI for Pi Coding Agent that keeps sessions alive in real workspaces. |
122 | 0 | +7 | +108 | 0 | 0 | No data | |
| 33544 |
Lecture and lab slides for EECS 498 AASE (Applied Agentic Software Engineering), UMich Fall 2026 |
336 | 0 | +3 | +318 | 0 | 0 | No data | |
| 33545 |
Puts DLSS 5 neural rendering into games that never shipped it, and brings the game's own DLSS up to date - super resolution, ray reconstruction, frame generation. Scans your library, picks one of eight routes, fetches every part from its publisher at run time, then says what happened. One exe, no admin; uninstall puts the game back. |
1,000 | +1 | +19 | +124 | 0 | 0 | 1.1x faster | |
| 33546 |
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi. |
797 | +1 | +27 | +161 | 0 | 0 | 1.1x faster | |
| 33547 |
One code, and you're in the same room. Remote multiplayer between Android emulators: 3DS, Switch, PSP, PS2, DS and WII. |
894 | +1 | +13 | +272 | 0 | 0 | 1.1x faster | |
| 33548 |
Neurwerk Kubernetes platform charts, release contracts, namespaces, defaults, and validation. |
119 | 0 | -2 | +46 | 0 | 0 | No data | |
| 33549 |
No description |
498 | 0 | 0 | +225 | 0 | 0 | No data | |
| 33550 |
Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents. |
647 | 0 | +15 | +60 | 0 | 0 | No data |
Today counts stars since midnight US Pacific time, so it is a partial day. 32 more tracked repositories are still loading their star history and will join the ranking once it is complete.