GitHub repositories taking off in the last 7 days
Ranked by how many more stars each repo got in the last 7 days than its pace over the 7 days before would predict, lowest first. Star counts come from GitHub. Last updated 10 Nov 2026, 08:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 22051 |
Automate the obvious and investigate the ambiguous. High-performance safety rules engine for real-time event processing at scale. |
500 | 0 | +2 | +11 | -1 | 0 | 0.8x, slowing | |
| 22052 |
大模型应用开发 -上下文工程与运行空间实践指南，上下文工程是设计原则，Agent Harness 是构建目标，本项目的目标，是为开发者和研究者提供一份大模型应用开发的骨架思路 |
852 | 0 | +2 | +20 | -1 | 0 | 0.8x, slowing | |
| 22053 |
The undetected self-hosted browser automation platform. Powered by Camoufox (Firefox) for 0% detection rates. Built for speed, privacy, and scalability. |
2,358 | 0 | +8 | +32 | -1 | 0 | 0.9x, slowing | |
| 22054 |
Integrate LLM models directly into Ghidra for AI-enhanced reverse engineering. |
841 | 0 | +2 | +19 | -1 | 0 | 0.6x, slowing | |
| 22055 |
experiments in goose |
521 | 0 | 0 | +3 | -1 | 0 | 0.0x, slowing | |
| 22056 |
menubarX for windows |
506 | 0 | -1 | +1 | -1 | 0 | No data | |
| 22057 |
File Converter, OCR, Transcription & TTS WebUI |
1,121 | 0 | 0 | +5 | -1 | 0 | 0.0x, slowing | |
| 22058 |
Python library for Agentic Document Extraction (ADE). |
1,038 | 0 | 0 | +4 | -1 | 0 | 0.0x, slowing | |
| 22059 |
MemoryBear Equip AI with human-like memory capability |
10,117 | +2 | +594 | +2,518 | -1 | 542 | 1.0x, steady | |
| 22060 |
DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。让安全不再昂贵，让审计不再复杂。 |
7,292 | 0 | +31 | +170 | -1 | 6 | 1.0x, steady | |
| 22061 |
A lightweight Model Context Protocol (MCP) server for safe Obsidian vault access |
1,721 | 0 | +8 | +42 | -1 | 0 | 0.9x, slowing | |
| 22062 |
API package for reading configuration. |
817 | 0 | 0 | +4 | -1 | 0 | 0.0x, slowing | |
| 22063 |
全自动优选CF的IP，包含美国US，日本JP，新加坡SG，德国DE，荷兰NL等cloudflare每天每小时自动优选IP，自动生成CF免费Vless节点。 |
684 | 0 | +4 | +37 | -1 | 0 | 0.8x, slowing | |
| 22064 |
my custom strudel scripts that haven't made it in to strudel for whatever reason |
530 | 0 | 0 | +6 | -1 | 0 | 0.0x, slowing | |
| 22065 |
Universal multi-language runner and smart REPL written in Rust. |
938 | 0 | 0 | +2 | -1 | 0 | 0.0x, slowing | |
| 22066 |
LLMs and VLMs with MLX Swift |
862 | 0 | +6 | +31 | -1 | 16 | 0.9x, slowing | |
| 22067 |
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing |
3,929 | 0 | +25 | +139 | -1 | 24 | 1.0x, steady | |
| 22068 |
Awesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code |
1,001 | 0 | +5 | +33 | -1 | 8 | 0.8x, slowing | |
| 22069 |
Official implementation of Falcon-TST |
654 | 0 | 0 | +132 | -1 | 0 | 0.0x, slowing | |
| 22070 |
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data. |
2,403 | 0 | +11 | +81 | -1 | 0 | 0.9x, slowing | |
| 22071 |
Intelligent prompt improver hook for Claude Code. Type vibes, ship precision. |
1,968 | 0 | +2 | +22 | -1 | 0 | 0.8x, slowing | |
| 22072 |
Open source Inbox for the official WhatsApp Cloud API. |
804 | 0 | +2 | +22 | -1 | 0 | 0.8x, slowing | |
| 22073 |
一个现代化的 Claude Code & Codex API 代理服务，提供智能负载均衡、用户管理和使用统计功能。 |
3,401 | 0 | +3 | +19 | -1 | 0 | 0.7x, slowing | |
| 22074 |
Deprecated: superseded by mcp_agent_mail_rust, the maintained Rust rewrite. Original Python FastMCP coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite. |
2,234 | 0 | +4 | +38 | -1 | 0 | 0.8x, slowing | |
| 22075 |
The verifiable coding agent runtime. Define your coding agent's process in natural language with stages, checks, and approval gates instead of hoping it follows your instructions. Primitives for verifiable software factories. |
882 | 0 | +5 | +29 | -1 | 0 | 0.8x, slowing | |
| 22076 |
A modern full-stack blog CMS driven by Cloudflare. | 基于 Cloudflare 生态的全栈现代化博客 CMS。 |
783 | 0 | +1 | +15 | -1 | 0 | 0.6x, slowing | |
| 22077 |
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents |
3,620 | 0 | +10 | +71 | -1 | 24 | 0.9x, slowing | |
| 22078 |
TensorIMS（原 Mystery00/TurboIMS）：由 Mystery00 维护的 Pixel Tensor IMS 配置工具，聚焦中国大陆的中国移动、中国联通、中国电信网络；其他运营商因缺少测试条件，不作为主要适配和维护对象。 |
697 | 0 | +8 | +51 | -1 | 8 | 0.9x, slowing | |
| 22079 |
CodeNomad: The command center that puts AI coding on steroids. |
2,663 | 0 | +5 | +55 | -1 | 0 | 0.8x, slowing | |
| 22080 |
Repo for "Adaptation of Agentic AI" |
688 | 0 | 0 | +4 | -1 | 0 | 0.0x, slowing | |
| 22081 |
一个跨平台、自动化、全兼容的 Sing-box 一键部署脚本 |
682 | 0 | +11 | +59 | -1 | 0 | 0.9x, slowing | |
| 22082 |
一款白噪音应用送给你，祝您牛掰，有的是钱 |
1,424 | 0 | +8 | +40 | -1 | 0 | 0.8x, slowing | |
| 22083 |
A curated list of Model Context Protocol (MCP) servers |
1,087 | 0 | +2 | +15 | -1 | 0 | 0.6x, slowing | |
| 22084 |
🚀 An awesome list of curated Nano Banana pro prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of the Nano banana pro(Nano banana 2) AI image model. |
10,385 | 0 | +9 | +60 | -1 | 0 | 0.9x, slowing | |
| 22085 |
Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP |
4,067 | 0 | +13 | +89 | -1 | 8 | 0.9x, slowing | |
| 22086 |
No description |
1,718 | 0 | +3 | +39 | -1 | 0 | 0.7x, slowing | |
| 22087 |
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control. |
1,162 | 0 | 0 | +8 | -1 | 0 | 0.0x, slowing | |
| 22088 |
an unhealthy amount of work has been put into this...star it? |
2,447 | 0 | +8 | +49 | -1 | 0 | 0.9x, slowing | |
| 22089 |
A modern, lightweight Markdown editor for macOS. |
509 | 0 | +5 | +21 | -1 | 8 | 0.8x, slowing | |
| 22090 |
No description |
814 | 0 | 0 | +6 | -1 | 0 | 0.0x, slowing | |
| 22091 |
企业级 LLM 中转服务可用性监控系统，实时追踪服务状态并提供可视化仪表板。 |
1,108 | 0 | -1 | +10 | -1 | 0 | No data | |
| 22092 |
Custom and repackaged Snapmaker U1 firmware |
1,136 | 0 | +21 | +96 | -1 | 0 | 0.9x, slowing | |
| 22093 |
🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source. |
13,766 | 0 | +35 | +227 | -1 | 24 | 1.0x, steady | |
| 22094 |
a project brain for your AI. Give LLMs instant architectural context without burning tokens |
711 | 0 | +3 | +10 | -1 | 0 | 0.7x, slowing | |
| 22095 |
Local folders, automatically synced to Proton Drive. (Unofficial Sync Client) |
692 | 0 | +2 | +10 | -1 | 0 | 0.8x, slowing | |
| 22096 |
Generate UI screens from text prompts and extract their HTML and screenshots programmatically. |
1,849 | 0 | +6 | +24 | -1 | 0 | 0.9x, slowing | |
| 22097 |
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support. |
1,651 | 0 | +5 | +35 | -1 | 0 | 0.8x, slowing | |
| 22098 |
No description |
1,205 | 0 | +5 | +44 | -1 | 0 | 0.8x, slowing | |
| 22099 |
CachyOS kernel for NixOS |
786 | 0 | +6 | +51 | -1 | 0 | 0.9x, slowing | |
| 22100 |
Self-hosted Lovable/v0 alternative. Realtime database & storage included. |
528 | 0 | +1 | +5 | -1 | 0 | 0.6x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 1 more tracked repositories are still loading their star history and will join the ranking once it is complete.