GitHub repositories taking off in the last 30 days
Ranked by how many more stars each repo got in the last 30 days than its pace over the 30 days before would predict. Star counts come from GitHub. Last updated 12 Nov 2026, 01:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 27601 |
Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video" |
768 | 0 | +2 | +8 | -1 | 0 | 0.9x, slowing | |
| 27602 |
No description |
875 | 0 | 0 | 0 | -1 | 0 | 0.0x, slowing | |
| 27603 |
Self-hosted Lovable/v0 alternative. Realtime database & storage included. |
529 | +1 | +2 | +6 | -1 | 0 | 0.9x, slowing | |
| 27604 |
Your workout logs visualized! |
528 | +1 | +4 | +10 | -1 | 0 | 0.9x, slowing | |
| 27605 |
WuMing's Claude Skills |
751 | 0 | 0 | +10 | -1 | 0 | 0.9x, slowing | |
| 27606 |
Lightweight & Fast Security Scanner for React Native & Expo |
503 | 0 | +1 | +2 | -1 | 0 | 0.7x, slowing | |
| 27607 |
Minimal self-hosted IPTV web interface with GPU transcoding, EPG, VOD, Chromecast, Xtream, and AI upscaling. |
517 | 0 | +2 | +5 | -1 | 0 | 0.8x, slowing | |
| 27608 |
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control |
2,532 | +4 | +36 | +196 | -1 | 0 | 1.0x, steady | |
| 27609 |
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation |
1,105 | 0 | +5 | +39 | -1 | 0 | 1.0x, steady | |
| 27610 |
Automatically reclaim space in your media library using customizable rules. Integrates with Jellyfin, Plex, and Emby (any or all of them) to analyze and manage your content. Functions similarly to Seerr (in reverse), providing efficient media cleanup |
577 | 0 | +4 | +10 | -1 | 0 | 0.9x, slowing | |
| 27611 |
Awesome list of add-ons, hooks, tools, skills, and resources for the pi coding agent (pi-mono). |
1,096 | +1 | 0 | +3 | -1 | 0 | 0.8x, slowing | |
| 27612 |
TUI and CLI for browsing models.dev, benchmarks, coding agents, and statuses for AI providers. |
519 | 0 | +1 | +7 | -1 | 0 | 0.9x, slowing | |
| 27613 |
KISS Sorcar: Keep it Simple, Stupid AI General Purpose Agent Framework for Long Horizon Tasks and AI Discovery |
561 | 0 | -2 | +6 | -1 | 0 | 0.9x, slowing | |
| 27614 |
Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore. |
603 | 0 | +2 | +7 | -1 | 0 | 0.9x, slowing | |
| 27615 |
源内Web（AIインターフェース） |
576 | 0 | +3 | +9 | -1 | 0 | 0.9x, slowing | |
| 27616 |
A Simple Implementation of Qwen3-TTS's ComfyUI |
1,973 | 0 | +5 | +38 | -1 | 0 | 1.0x, steady | |
| 27617 |
Turn your Android into a GPU-accelerated Linux hacking lab with one command! XFCE Desktop + Nmap, SQLMap, Hydra, Wine & more. No root required. |
866 | 0 | +8 | +46 | -1 | 0 | 1.0x, steady | |
| 27618 |
A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query. |
2,275 | +1 | +4 | +11 | -1 | 0 | 0.9x, slowing | |
| 27619 |
Sets of tools to help bypass DPI |
890 | +1 | 0 | +31 | -1 | 0 | 1.0x, steady | |
| 27620 |
Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw |
2,620 | +3 | +8 | +39 | -1 | 0 | 1.0x, steady | |
| 27621 |
🦀An agentic AI assistant that lives in your chats, inspired by nanoclaw and incorporating some of its design ideas. Built with Rust 🦀 |
756 | 0 | +3 | +13 | -1 | 0 | 0.9x, slowing | |
| 27622 |
Free, Micro AI Code Reviews That Run on Git Commit |
1,490 | 0 | +9 | +21 | -1 | 0 | 1.0x, steady | |
| 27623 |
Open Cowork - Opensource Claude Cowork for Windows & macOS & Linux. |
643 | 0 | 0 | +6 | -1 | 0 | 0.9x, slowing | |
| 27624 |
OCR in the Era of Large Language Models |
745 | 0 | 0 | +15 | -1 | 0 | 0.9x, slowing | |
| 27625 |
77 open-source marketing skills for Claude Code, Codex, and other AI coding agents. SEO, content, email, ads, analytics, and growth. |
737 | 0 | +7 | +26 | -1 | 0 | 1.0x, steady | |
| 27626 |
No description |
585 | 0 | 0 | +1 | -1 | 0 | 0.5x, slowing | |
| 27627 |
AI长篇小说创作系统 - 基于文件级长期记忆的Smart State模式，支持百万字级长篇小说持续创作 |
712 | +1 | +4 | +37 | -1 | 0 | 1.0x, steady | |
| 27628 |
PostgreSQL in-database durable execution |
2,849 | 0 | +1 | +25 | -1 | 0 | 1.0x, steady | |
| 27629 |
The all-in-one AI agent. Build mobile apps, frontend, backend, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry. |
1,029 | 0 | +4 | +50 | -1 | 0 | 1.0x, steady | |
| 27630 |
Open-source AI-powered offensive security harness for automated penetration testing. |
3,520 | +11 | +133 | +414 | -1 | 3 | 1.0x, steady | |
| 27631 |
High-performance icon rendering for React Native & Expo |
639 | 0 | 0 | +24 | -1 | 0 | 1.0x, steady | |
| 27632 |
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree |
1,086 | +1 | +9 | +44 | -1 | 0 | 1.0x, steady | |
| 27633 |
The Coordination Layer for Multi-Agent AI |
675 | 0 | +1 | +16 | -1 | 0 | 0.9x, slowing | |
| 27634 |
A WYSIWYG editor for TikZ that parses TikZ code |
508 | 0 | +3 | +24 | -1 | 0 | 1.0x, steady | |
| 27635 |
If you can read ~100 lines of Python, you understand agents. |
778 | 0 | +2 | +18 | -1 | 0 | 1.0x, steady | |
| 27636 |
Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark. |
2,904 | +1 | +2 | +20 | -1 | 0 | 1.0x, steady | |
| 27637 |
Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context |
626 | +1 | +2 | +15 | -1 | 0 | 0.9x, slowing | |
| 27638 |
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions. |
1,028 | 0 | +3 | +65 | -1 | 0 | 1.0x, steady | |
| 27639 |
Score and choose the best domain name for your startup — AI-powered generation, real-time availability, and multi-dimensional scoring (LEN, PRO, MEM, BRD, FIT). Free, no signup. |
631 | 0 | 0 | 0 | -1 | 0 | 0.0x, slowing | |
| 27640 |
Private Inference Network on Idle Macs |
575 | +1 | +3 | +29 | -1 | 0 | 1.0x, steady | |
| 27641 |
ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent |
1,475 | +2 | +5 | +17 | -1 | 0 | 1.0x, steady | |
| 27642 |
AI model safety scanner built on NVIDIA garak |
683 | 0 | +3 | +9 | -1 | 0 | 0.9x, slowing | |
| 27643 |
context-ware floating secretary |
582 | 0 | -1 | +4 | -1 | 0 | 0.8x, slowing | |
| 27644 |
🚀 An 800KB RAM ultra-lightweight Cloudflare WARP SOCKS5 proxy in Docker. 仅需 800KB 内存的纯内核态 Cloudflare WARP 代理 - Docker |
1,466 | +1 | +5 | +23 | -1 | 0 | 1.0x, steady | |
| 27645 |
☁️ 轻量级高性能跨平台AI对话 + AI Agent + AI网关桌面客户端 | Lightweight, high-performance cross-platform AI dialogue + AI Agent + AI gateway desktop client |
924 | 0 | +2 | +19 | -1 | 0 | 1.0x, steady | |
| 27646 |
Claude code environment for laywers |
701 | 0 | +3 | +11 | -1 | 0 | 0.9x, slowing | |
| 27647 |
基于Pengu loader的英雄联盟客户端增强插件；LOL助手；sona助手；LOL插件；A LOL plugin base on Pengu loader; sona plugin; |
1,083 | +2 | +17 | +88 | -1 | 0 | 1.0x, steady | |
| 27648 |
Bitterbot - a mesh of agents that turns shared experience into collective capability. |
2,486 | +1 | +5 | +18 | -1 | 0 | 1.0x, steady | |
| 27649 |
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES. |
580 | 0 | +6 | +41 | -1 | 0 | 1.0x, steady | |
| 27650 |
MathCode: A Frontier Mathematical Coding Agent |
752 | 0 | +1 | +6 | -1 | 0 | 0.9x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.