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 13 Nov 2026, 13:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 34251 |
See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views, and session-level usage insight. |
775 | 0 | +6 | +49 | 0 | 0 | No data | |
| 34252 |
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams. |
1,257 | 0 | +4 | +22 | 0 | 0 | No data | |
| 34253 |
An alternative logical projection of React with 100% API compliancy but simpler implementation resulting in smaller bundle size and better performance. |
579 | 0 | +14 | +230 | 0 | 0 | 0.0x, slowing | |
| 34254 |
Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python. |
927 | 0 | 0 | +20 | 0 | 0 | No data | |
| 34255 |
Let Pi control your apps on MacOS & Windows |
2,141 | 0 | +6 | +100 | 0 | 0 | No data | |
| 34256 |
talkie is a vintage language model from 1930 |
1,038 | 0 | +4 | +20 | 0 | 0 | No data | |
| 34257 |
A self-hosted, unified webmail client. |
686 | +1 | +30 | +140 | 0 | 16 | 0.9x, slowing | |
| 34258 |
FlashKDA: high-performance Kimi Delta Attention kernels |
1,297 | 0 | +1 | +18 | 0 | 0 | No data | |
| 34259 |
启智平台的 Agent 驾驶舱：Skill + CLI，一条命令直达。Agent cockpit for the Inspire ML platform: one command, every operation, straight from chat. |
563 | 0 | +8 | +26 | 0 | 0 | 0.0x, slowing | |
| 34260 |
A GPU-rendered terminal emulator with inline 3D graphics 🐀🧀 |
3,329 | 0 | +5 | +57 | 0 | 0 | No data | |
| 34261 |
Open-source drop-in replacement for Bambu Studio's proprietary `bambu_networking` plugin. |
605 | 0 | +9 | +43 | 0 | 0 | 0.0x, slowing | |
| 34262 |
The browser-native agent framework |
791 | 0 | +3 | +17 | 0 | 0 | 0.0x, slowing | |
| 34263 |
An image-to-world skillset for Claude. |
12,516 | +3 | +143 | +1,210 | 0 | 37 | 1.0x, steady | |
| 34264 |
No description |
55 | 0 | +1 | +53 | 0 | 0 | No data | |
| 34265 |
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode. |
794 | 0 | +3 | +12 | 0 | 0 | 0.0x, slowing | |
| 34266 |
Personal deep learning study notes and tutorial-style notebooks |
719 | 0 | +2 | +15 | 0 | 8 | 0.0x, slowing | |
| 34267 |
MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。 |
1,061 | 0 | 0 | +317 | 0 | 0 | No data | |
| 34268 |
GEO research library for papers, datasets, white papers, experiments, and high-quality articles. |
796 | 0 | +15 | +101 | 0 | 0 | No data | |
| 34269 |
No description |
345 | 0 | +92 | +333 | 0 | 0 | No data | |
| 34270 |
Multimodal RL training framework for diffusion & omni models |
1,501 | +1 | +31 | +235 | 0 | 22 | 1.1x faster | |
| 34271 |
TODOforAI Bridge — native C edge agent (PTY relay over Noise-encrypted WebSocket) |
77 | 0 | +10 | +59 | 0 | 0 | 0.0x, slowing | |
| 34272 |
A native iOS client for tmux and herdr, designed to feel natural on iPhone. |
533 | 0 | +5 | +19 | 0 | 0 | No data | |
| 34273 |
A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 80K reach / 448 likes / 500 comments on first post. Includes Day 2 flop postmortem. |
857 | 0 | +107 | +122 | 0 | 5 | 0.0x, slowing | |
| 34274 |
闲鱼 CLI · 原生支持 MCP · 为 AI Agent 而生 | Goofish (Xianyu) automation CLI · MCP-ready · Built for AI Agents |
475 | +1 | +38 | +151 | 0 | 15 | 0.9x, slowing | |
| 34275 |
Rust port of @masterking32's MasterHttpRelayVPN — all credit to @masterking32 for the original idea and Python implementation. Free DPI bypass via a Google Apps Script relay with TLS SNI concealment. CLI + cross-platform desktop UI, HTTP + SOCKS5 proxy, no runtime deps. |
3,642 | 0 | +2 | +46 | 0 | 0 | No data | |
| 34276 |
Hierarchal Agent Loop Optimizer |
1,212 | 0 | +4 | +27 | 0 | 0 | No data | |
| 34277 |
Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers. |
900 | 0 | +3 | +35 | 0 | 8 | No data | |
| 34278 |
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp. |
3,649 | +6 | +296 | +380 | 0 | 75 | 1.0x, steady | |
| 34279 |
The open source Unity Dev Agent |
762 | 0 | +3 | +11 | 0 | 0 | No data | |
| 34280 |
Markdown filesystem for agents and teams. |
877 | 0 | +2 | +157 | 0 | 0 | No data | |
| 34281 |
GPT Image 2/2.5/2.6 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing |
6,092 | +2 | +71 | +357 | 0 | 56 | 1.1x faster | |
| 34282 |
Your personal web archiver. |
428 | 0 | +26 | +427 | 0 | 0 | 0.0x, slowing | |
| 34283 |
阅读Sigma是gedoor/legado的一个分支版本，在原有基础上增加更多功能，为书源带来更多可能性。 |
668 | 0 | +8 | +51 | 0 | 8 | No data | |
| 34284 |
No description |
508 | 0 | 0 | +12 | 0 | 0 | No data | |
| 34285 |
Beautiful README badges, inspired by shields.io and styled like shadcn/ui. |
945 | 0 | +4 | +24 | 0 | 8 | 0.0x, slowing | |
| 34286 |
A multi-round co-design skill for publication-ready paper framework diagrams and method overview figures. |
2,345 | 0 | +13 | +83 | 0 | 0 | 0.0x, slowing | |
| 34287 |
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified. |
969 | 0 | +8 | +52 | 0 | 0 | No data | |
| 34288 |
GPT Image 2 to Seedance 2.5 Early Access workflow guide. |
621 | 0 | +1 | +13 | 0 | 0 | 0.0x, slowing | |
| 34289 |
A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more. |
839 | 0 | +9 | +158 | 0 | 0 | 0.0x, slowing | |
| 34290 |
World2Agent(W2A) is an open protocol that standardizes how Al agents perceive the real world. |
1,125 | 0 | +2 | -2 | 0 | 0 | No data | |
| 34291 |
A 100% free AI pipeline that researches, scripts, narrates, and uploads faceless YouTube videos — one command |
256 | 0 | +28 | +128 | 0 | 0 | 0.0x, slowing | |
| 34292 |
面向小白用户的 CTF / 逆向 Skills 整合包：自动分流、头脑风暴、教学模式、比赛模式、只提示模式 |
849 | 0 | +4 | +16 | 0 | 0 | No data | |
| 34293 |
GTM agent for technical founders. Pay-per-result. Two surfaces: terminal CLI + local web dashboard. |
586 | 0 | -7 | -82 | 0 | 0 | 0.0x, slowing | |
| 34294 |
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week. |
2,006 | 0 | 0 | +11 | 0 | 0 | No data | |
| 34295 |
high-performance linear attention kernel library built on TileLang |
755 | 0 | +6 | +29 | 0 | 8 | 0.0x, slowing | |
| 34296 |
Exact convex collision geometry for MuJoCo assemblies: pegs and holes from any outline, threads, and gears. |
188 | 0 | +3 | +187 | 0 | 0 | No data | |
| 34297 |
Linux payload implementing HV exploits to run a custom bootloader |
577 | 0 | +31 | +346 | 0 | 16 | 0.0x, slowing | |
| 34298 |
Product Builder Second Brain - AI Product Heroes Edition 3 |
864 | +1 | +33 | +642 | 0 | 24 | 0.7x, slowing | |
| 34299 |
Algebrica is free and open a mathematical knowledge base dedicated to clarity, structure, and conceptual coherence. |
1,104 | +1 | +9 | +48 | 0 | 24 | 1.1x faster | |
| 34300 |
A simple 2D game engine for rapid prototyping with Lua, featuring live reload and cross-platform export; this repo is a mirror and development happens at: https://codeberg.org/brettchalupa/usagi |
880 | 0 | +1 | +17 | 0 | 0 | No data |
Today counts stars since midnight US Pacific time, so it is a partial day.