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, lowest first. Star counts come from GitHub. Last updated 8 Nov 2026, 11:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 13501 |
Claude Code skills for Obsidian | Claude Code x Obsidian Lab, 4 weeks live, starts Nov 10 |
548 | 0 | +3 | +8 | -3 | 0 | 0.7x, slowing | |
| 13502 |
一款追求极致流畅的开源鼠标手势扩展。指尖滑动，进入心流。支持手势导航、超级拖拽、滚轮手势、特殊手势，并可自定义所有手势及更多功能。 / An open-source mouse gesture extension designed for ultimate smoothness. Swipe your fingertips, enter the Flow. Supports gesture navigation, super drag, wheel and rocker gestures, and the ability to customize all gestures and more. |
697 | 0 | +5 | +34 | -3 | 0 | 0.9x, slowing | |
| 13503 |
Universal IPTV in your Browser & Efficient Transcoding on your Server |
515 | 0 | 0 | +4 | -3 | 0 | 0.6x, slowing | |
| 13504 |
Radiance is rebuilt of Minecraft renderer on a Vulkan C++ backend, featuring native Hardware Ray Tracing on Windows & Linux. Break free from OpenGL limits for Minecraft. |
1,176 | 0 | +7 | +42 | -3 | 0 | 0.9x, slowing | |
| 13505 |
Awesome list of add-ons, hooks, tools, skills, and resources for the pi coding agent (pi-mono). |
1,095 | 0 | -1 | +2 | -3 | 0 | 0.4x, slowing | |
| 13506 |
Automated, hardened Clawdbot installation with Tailscale VPN, UFW firewall, and Docker isolation |
605 | 0 | 0 | +4 | -3 | 0 | 0.6x, slowing | |
| 13507 |
TUI and CLI for browsing models.dev, benchmarks, coding agents, and statuses for AI providers. |
518 | 0 | +1 | +6 | -3 | 0 | 0.7x, slowing | |
| 13508 |
Spirit-v1.5: A Robotic Foundation Model by Spirit AI |
672 | 0 | +2 | +7 | -3 | 0 | 0.7x, slowing | |
| 13509 |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models |
4,815 | 0 | +14 | +88 | -3 | 0 | 1.0x, steady | |
| 13510 |
Some commonly used research experiences and processes are encapsulated into Agent skills. |
881 | 0 | +4 | +21 | -3 | 0 | 0.9x, slowing | |
| 13511 |
Claude Agents Library |
758 | 0 | +1 | +2 | -3 | 0 | 0.4x, slowing | |
| 13512 |
Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore. |
602 | 0 | +2 | +6 | -3 | 0 | 0.7x, slowing | |
| 13513 |
Fast, scriptable CLI for the App Store Connect API. Automate TestFlight, builds, submissions, signing, analytics, screenshots, subscriptions, and more |
8,270 | 0 | +69 | +560 | -3 | 4 | 1.0x, steady | |
| 13514 |
No description |
989 | 0 | +4 | +7 | -3 | 0 | 0.7x, slowing | |
| 13515 |
Dingtalk channel plugin for OpenClaw |
1,663 | 0 | +2 | +3 | -3 | 0 | 0.5x, slowing | |
| 13516 |
giffgaff keeper - a tiny web |
549 | 0 | -2 | +1 | -3 | 0 | 0.3x, slowing | |
| 13517 |
Experimental Linux microvm setup with a TypeScript Control Plane as Agent Sandbox |
2,399 | 0 | +33 | +135 | -3 | 0 | 1.0x, steady | |
| 13518 |
🤖 AI social-media automation skill | Self-evolution workflows | AI 社交媒体自动化 skill | 自我进化工作流 |
547 | 0 | +2 | +14 | -3 | 0 | 0.8x, slowing | |
| 13519 |
A GitHub action that detects and automatically closes low-quality and AI slop PRs. |
855 | 0 | +3 | +16 | -3 | 0 | 0.8x, slowing | |
| 13520 |
Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent. Stop babysitting your terminal. Employ a Peon today. |
5,111 | 0 | +10 | +54 | -3 | 0 | 0.9x, slowing | |
| 13521 |
Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman. |
662 | 0 | +1 | +6 | -3 | 0 | 0.7x, slowing | |
| 13522 |
No description |
585 | 0 | 0 | -1 | -3 | 0 | -0.5x, slowing | |
| 13523 |
Fetch X/Twitter tweets, replies, timelines, and articles without login or API keys — field tool for AI agents. |
1,001 | 0 | +3 | +20 | -3 | 0 | 0.9x, slowing | |
| 13524 |
self-improving agent |
758 | 0 | -1 | +4 | -3 | 0 | 0.6x, slowing | |
| 13525 |
The Coordination Layer for Multi-Agent AI |
674 | 0 | +8 | +16 | -3 | 0 | 0.8x, slowing | |
| 13526 |
Free, open-source ASO keyword research tool for macOS. No API keys, no accounts, and your research stays on your Mac. |
540 | 0 | +2 | +23 | -3 | 0 | 0.9x, slowing | |
| 13527 |
LLM inference engine written in .NET |
528 | 0 | +1 | +7 | -3 | 0 | 0.7x, slowing | |
| 13528 |
Agent skills for daily paper discovery, critical reviews, and connected research notes. Supports English and Chinese. |
1,341 | 0 | +11 | +63 | -3 | 0 | 1.0x, steady | |
| 13529 |
A collection of open-source Agent Skills for content creation — images, audio, and video. |
822 | 0 | +5 | +25 | -3 | 0 | 0.9x, slowing | |
| 13530 |
Real-Time Open-source command center for MikroTik RouterOS v7. Streams live CPU, traffic, wireless clients, DHCP, WireGuard, firewall and geo connection data straight from the router API to your browser over a WebSocket. Alerts, reports, config management and zero-touch provisioning. One static Go binary, self-hosted, Docker-ready |
645 | 0 | +7 | +34 | -3 | 0 | 0.9x, slowing | |
| 13531 |
Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context |
624 | 0 | +3 | +14 | -3 | 0 | 0.8x, slowing | |
| 13532 |
Lightweight scheduled task management panel, similar to Qinglong Panel. 轻量级定时任务管理面板 |
649 | 0 | +18 | +79 | -3 | 0 | 1.0x, steady | |
| 13533 |
One Query. All Search Skill. 聚合 Gemini、Grok、豆包、元宝等平台原生 AI 搜索能力，免费获取科技趋势、行业舆情、热点追踪、旅行规划、日常问题统一接进自己的 Agent 与工作流，指定链接免费爬取 |
1,316 | 0 | +8 | +33 | -3 | 0 | 0.9x, slowing | |
| 13534 |
一个持续进化的面试训练系统。在线体验地址：https://techspar.cn |
1,141 | 0 | +8 | +38 | -3 | 8 | 0.9x, slowing | |
| 13535 |
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets. |
927 | 0 | -1 | +5 | -3 | 0 | 0.6x, slowing | |
| 13536 |
100% private on-device voice models for speech-to-text and meeting transcription on macOS |
3,241 | 0 | +1 | +48 | -3 | 8 | 0.9x, slowing | |
| 13537 |
Native ARM64 port of OpenEmu for Apple Silicon MacBooks |
570 | 0 | +14 | +83 | -3 | 0 | 1.0x, steady | |
| 13538 |
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app. |
797 | 0 | +5 | +19 | -3 | 0 | 0.9x, slowing | |
| 13539 |
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。 |
3,853 | 0 | +5 | +48 | -3 | 0 | 0.9x, slowing | |
| 13540 |
[ECCV 2026] 🔥 Official impl. of "DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing". |
794 | 0 | +2 | +14 | -3 | 0 | 0.8x, slowing | |
| 13541 |
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands. All original source code is the property of Anthropic. |
2,363 | 0 | +12 | +67 | -3 | 8 | 1.0x, steady | |
| 13542 |
CheetahClaws: Scaling the Harness in Agentic AI |
796 | 0 | +2 | +12 | -3 | 0 | 0.8x, slowing | |
| 13543 |
No description |
533 | 0 | -1 | +1 | -3 | 0 | 0.3x, slowing | |
| 13544 |
Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions. |
555 | 0 | +2 | +10 | -3 | 0 | 0.8x, slowing | |
| 13545 |
No description |
1,333 | 0 | +4 | +35 | -3 | 0 | 0.9x, slowing | |
| 13546 |
Open-source benchmark for browser AI agents on daily tasks. |
1,229 | 0 | +48 | +266 | -3 | 5 | 1.0x, steady | |
| 13547 |
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf. |
511 | 0 | +1 | +23 | -3 | 0 | 0.9x, slowing | |
| 13548 |
No description |
726 | 0 | +3 | +20 | -3 | 8 | 0.9x, slowing | |
| 13549 |
Dinky makes files smaller. |
536 | 0 | +3 | +13 | -3 | 0 | 0.8x, slowing | |
| 13550 |
Genblaze is an open source Python SDK for orchestrating generative AI media pipelines across video, audio, and image providers with built in provenance for every output. |
548 | 0 | -3 | -1 | -3 | 0 | -0.5x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.