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, 00:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 27351 |
A Ruby gem implementation of a Model Context Protocol (MCP) server for Rails projects. This server allows LLMs (Large Language Models) to interact with Rails projects through the Model Context Protocol. |
573 | 0 | -1 | +2 | -1 | 0 | 0.7x, slowing | |
| 27352 |
No description |
1,111 | 0 | 0 | 0 | -1 | 0 | 0.0x, slowing | |
| 27353 |
Production-ready AI chat. Start here and make it your own. |
1,203 | -1 | +1 | +4 | -1 | 0 | 0.8x, slowing | |
| 27354 |
Self hosted ingress-as-a-service platform that allows you to expose applications and services running in private or local networks to the internet |
1,625 | 0 | 0 | +7 | -1 | 0 | 0.9x, slowing | |
| 27355 |
MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account. |
801 | 0 | +4 | +14 | -1 | 0 | 0.9x, slowing | |
| 27356 |
歌词获取器 | Super Lyric Getter |
550 | 0 | +3 | +19 | -1 | 0 | 1.0x, steady | |
| 27357 |
Formerly Better Chatbot. Navigator is an open-source AI workspace for agents, MCP and workflow automation. |
1,197 | 0 | +2 | +13 | -1 | 0 | 0.9x, slowing | |
| 27358 |
MCP server for TouchDesigner |
625 | 0 | +13 | +48 | -1 | 0 | 1.0x, steady | |
| 27359 |
No description |
11,331 | 0 | 0 | +1 | -1 | 0 | 0.5x, slowing | |
| 27360 |
Damn Vulnerable MCP Server |
1,367 | 0 | +2 | +13 | -1 | 0 | 0.9x, slowing | |
| 27361 |
Modern Video/Audio Downloader based on YT-DLP with Browser Integration (🦭 Seal for Desktop) |
589 | +1 | +2 | +14 | -1 | 0 | 0.9x, slowing | |
| 27362 |
The simplest, fastest repository for training/finetuning small-sized VLMs. |
5,073 | +1 | +7 | +30 | -1 | 0 | 1.0x, steady | |
| 27363 |
Inworld TTS |
766 | 0 | 0 | +5 | -1 | 0 | 0.8x, slowing | |
| 27364 |
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications. |
17,126 | +25 | +99 | +652 | -1 | 0 | 1.0x, steady | |
| 27365 |
Magicrew. The first open-source all-in-one AI productivity platform (Generalist AI Agent + Workflow Engine + IM + Online collaborative office system) |
5,083 | +1 | +13 | +39 | -1 | 0 | 1.0x, steady | |
| 27366 |
Multi-agent systems, memory, planning, reasoning loops |
2,948 | +1 | +4 | +28 | -1 | 0 | 1.0x, steady | |
| 27367 |
GHOST - Global Human Operations & Surveillance Tracking: Open-source investigation management platform for tracking people, connections, and intelligence data. Because Excel spreadsheets are for accountants, not investigators. Non-commercial license. |
933 | 0 | +6 | +29 | -1 | 0 | 1.0x, steady | |
| 27368 |
DocFlow is an AI-powered documentation platform built with Tiptap and Next.js, designed for real-time collaboration ⚡, smart writing assistance 🤖, and a flexible plugin system 🔌. |
1,334 | 0 | +3 | +12 | -1 | 0 | 0.9x, slowing | |
| 27369 |
Ruler — apply the same rules to all coding agents |
2,967 | 0 | +7 | +28 | -1 | 0 | 1.0x, steady | |
| 27370 |
An RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows. |
1,214 | 0 | +6 | +6 | -1 | 0 | 0.9x, slowing | |
| 27371 |
(Official) Repository. |
741 | 0 | +2 | +9 | -1 | 0 | 0.9x, slowing | |
| 27372 |
Инструмент для создания MCP-серверов в 1С:Предприятие путем разработки расширения конфигурации. Позволяет интегрировать данные и функциональность 1С с AI-ассистентами (Claude, Cursor и т.д.). Включает Python-прокси и пример расширения 1С с готовыми инструментами. |
573 | 0 | +4 | +38 | -1 | 0 | 1.0x, steady | |
| 27373 |
Build Container Images In Kubernetes |
981 | 0 | +3 | +9 | -1 | 0 | 0.9x, slowing | |
| 27374 |
Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing. |
561 | +1 | +2 | +7 | -1 | 0 | 0.9x, slowing | |
| 27375 |
No description |
803 | +2 | +11 | +36 | -1 | 0 | 1.0x, steady | |
| 27376 |
A Cloudflare alternative for local and cloud use, can be used ontop of cloudflare for cloudflares paid features, but for free! |
906 | +1 | +1 | +9 | -1 | 0 | 0.9x, slowing | |
| 27377 |
A Claude.ai reverse proxy |
786 | 0 | +3 | +9 | -1 | 0 | 0.9x, slowing | |
| 27378 |
Liquid RuntimeShader effects for Compose Multiplatform |
578 | 0 | -1 | +6 | -1 | 0 | 0.9x, slowing | |
| 27379 |
AutoClip: AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具 |
1,232 | +8 | +50 | +87 | -1 | 0 | 1.0x, steady | |
| 27380 |
Steam EncryptedAppTicket generator |
563 | -1 | -2 | +5 | -1 | 0 | 0.8x, slowing | |
| 27381 |
[ACL 2026] OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction https://arxiv.org/abs/2604.25602 |
2,075 | 0 | +1 | +5 | -1 | 0 | 0.8x, slowing | |
| 27382 |
Mocking library with the perfect balance of Performance and Intuitive API |
650 | -1 | 0 | +1 | -1 | 0 | 0.5x, slowing | |
| 27383 |
The honest edge layer for Kalshi prediction markets - an agent-native toolkit (CLI, MCP server, Claude skill) that measures whether you actually beat the book instead of claiming it. |
656 | +2 | +11 | +40 | -1 | 0 | 1.0x, steady | |
| 27384 |
Provider-agnostic, open-source evaluation infrastructure for language models |
831 | 0 | 0 | +9 | -1 | 0 | 0.9x, slowing | |
| 27385 |
Helium Browser for Windows |
1,487 | +3 | +9 | +70 | -1 | 0 | 1.0x, steady | |
| 27386 |
The world's most powerful open-source financial AI assistant - Access institutional-grade financial data, run complex analyses, and create stunning visualizations, all through natural conversation. |
911 | 0 | +2 | +10 | -1 | 0 | 0.9x, slowing | |
| 27387 |
Modern Billing & Monetization UI Components Library |
512 | 0 | +1 | +6 | -1 | 0 | 0.9x, slowing | |
| 27388 |
政治資金の流れを透明性を持って公開するプラットフォームです |
707 | 0 | +1 | +5 | -1 | 0 | 0.8x, slowing | |
| 27389 |
Odin 2D game library. Beginner friendly and easy to modify. |
726 | 0 | +5 | +28 | -1 | 0 | 1.0x, steady | |
| 27390 |
An alignment auditing agent capable of quickly exploring alignment hypothesis |
1,408 | 0 | +6 | +39 | -1 | 0 | 1.0x, steady | |
| 27391 |
HTTP(s) request filter for processes |
962 | 0 | +2 | +2 | -1 | 0 | 0.7x, slowing | |
| 27392 |
No description |
11,173 | 0 | 0 | +1 | -1 | 0 | 0.5x, slowing | |
| 27393 |
PasarGuard | Unified GUI Censorship Resistant Solution |
2,831 | +4 | +34 | +144 | -1 | 0 | 1.0x, steady | |
| 27394 |
Easy Tailscale to WireGuard bridge in a container |
611 | 0 | +1 | +4 | -1 | 0 | 0.8x, slowing | |
| 27395 |
Simple Rust VPN Client / Server |
740 | 0 | 0 | +5 | -1 | 0 | 0.8x, slowing | |
| 27396 |
A list of OSINT tools & resources for (fraud-)investigators, CTI-analysts, KYC, AML and more. |
1,808 | +1 | +10 | +45 | -1 | 0 | 1.0x, steady | |
| 27397 |
WHartTest 是一款AI驱动的测试自动化平台，实现从需求到可执行测试用例的自动化生成与管理，帮助测试团队提升效率与覆盖率。 (WHartTest is an AI-driven test automation platform that automates the generation and management of executable test cases from requirements, helping testing teams improve efficiency and coverage.) |
1,081 | +1 | +11 | +34 | -1 | 0 | 1.0x, steady | |
| 27398 |
menubarX for windows |
506 | 0 | -1 | +1 | -1 | 0 | 0.5x, slowing | |
| 27399 |
Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps. |
1,255 | 0 | +4 | +25 | -1 | 0 | 1.0x, steady | |
| 27400 |
MiMo-Audio: Audio Language Models are Few-Shot Learners |
1,093 | 0 | +3 | +8 | -1 | 0 | 0.9x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.