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 16 Nov 2026, 17:20 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 it belongs to a personal account with no followers and either is under 3 days old with no watchers and at least 5 forks, or is under 30 days old with at least half as many forks as stars and 128 KB or less of files while that account is under a year old; it stays out while that account has no followers. Any repository with at least 50 stars that is under 30 days old is also left out for good when at least 2 other repositories of the same name were created within an hour of it, all owned by personal accounts with 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 |
|---|---|---|---|---|---|---|---|---|---|
| 38801 |
a digital safe with multiple keys, held by people you trust |
1,510 | 0 | +10 | +48 | +3 | 0 | 1.4x faster | |
| 38802 |
基于 Cloudflare 的 Serverless 聚合云盘。以 Telegram 为核心(支持 Webhook 直传与 2GB 扩展),并全面兼容 R2、S3、Discord 及 HuggingFace 等多存储后端。零成本构建你的全能私有数据金库。 |
807 | 0 | +4 | +13 | +3 | 0 | 4.4x faster | |
| 38803 |
A Python framework for AI-driven character animation using neural networks. |
2,138 | +1 | +8 | +25 | +3 | 8 | 1.8x faster | |
| 38804 |
A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond |
1,065 | 0 | +3 | +20 | +3 | 8 | Up from 0 | |
| 38805 |
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. |
2,889 | +1 | +36 | +134 | +3 | 56 | 1.1x faster | |
| 38806 |
AI-Human symbiotic browser — browse the web as one entity |
633 | 0 | +4 | +11 | +3 | 0 | 4.4x faster | |
| 38807 |
一套为研究生和学术研究者设计的完整AI Prompt库 📖 包含内容: ✨ 40+ 精心设计的AI Prompt ✨ 论文选题系统方法(生成、评估、论证) ✨ 论文查找快速方案(8个不同方案) ✨ 文献综述框架和工具 ✨ Excel自动评估表格 ✨ 3个完整的论证模板 🚀 核心优势: ⚡ 节省时间 50-70%(选题3-5天而不是2-3周) 🎯 科学方法(基于系统的5维度评估体系) 💡 即插即用(所有Prompt直接复制可用) 📚 全流程覆盖(从选题到出版的完整方案) 🎓 适用人群: 👨🎓 硕士研究生 | 博士研究生 | 本科毕业设计 | 学术研究者 | 内容创作者 |
2,378 | +2 | +48 | +241 | +3 | 40 | 1.1x faster | |
| 38808 |
Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram. |
6,192 | +1 | +16 | +86 | +3 | 26 | 1.3x faster | |
| 38809 |
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes. |
6,504 | +2 | +36 | +148 | +3 | 34 | 1.1x faster | |
| 38810 |
MLOps for DevOps Engineers - A hands-on, project-based guide to Machine Learning Operations |
559 | 0 | +4 | +15 | +3 | 0 | 4.4x faster | |
| 38811 |
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer. |
3,344 | 0 | +11 | +61 | +3 | 8 | 1.3x faster | |
| 38812 |
OpenTelemetry observability platform |
1,965 | 0 | +13 | +123 | +3 | 8 | 1.3x faster | |
| 38813 |
No description |
976 | +2 | +23 | +123 | +3 | 32 | 1.1x faster | |
| 38814 |
用于写NSFC本子的Agent Skills |
794 | 0 | +29 | +112 | +3 | 7 | 1.1x faster | |
| 38815 |
A request monitoring system for Claude Code that captures and visualizes all API requests and responses in real time. Helps developers monitor their Context for reviewing and debugging during Vibe Coding. |
1,093 | 0 | +3 | +10 | +3 | 0 | Up from 0 | |
| 38816 |
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative. |
712 | 0 | +6 | +23 | +3 | 0 | 2.2x faster | |
| 38817 |
Utilities for Android emulators, iOS simulators and real devices: launch, stream, control, record and automate them from a desktop app, TUI and CLI |
1,222 | 0 | +8 | +33 | +3 | 0 | 1.5x faster | |
| 38818 |
基於OpenVino-int8權重,精簡的QwenASR小工具,用於即時辨識以及字幕轉換使用 |
581 | 0 | +3 | +8 | +3 | 0 | Up from 0 | |
| 38819 |
Self-hosted Docker Compose management platform. For single or multi-host compose-first workflow. |
502 | 0 | +2 | +10 | +3 | 0 | No data | |
| 38820 |
A curated list of AI tools, agent skills, libraries, and resources for economics research, teaching, and policy analysis. Maintained by the OpenEcon team. |
716 | 0 | +9 | +45 | +3 | 10 | 1.4x faster | |
| 38821 |
Slap your MacBook, it yells back. Uses Apple Silicon accelerometer via IOKit HID. |
5,029 | 0 | +4 | +24 | +3 | 0 | 4.4x faster | |
| 38822 |
200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns. |
545 | 0 | +2 | +2 | +3 | 0 | No data | |
| 38823 |
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI |
4,449 | 0 | 0 | +6 | +3 | 0 | No data | |
| 38824 |
A lightweight, open-source, fully local alternative to Logitech Options+ for remapping Logitech HID++ mice. |
5,378 | -1 | +19 | +91 | +3 | 0 | 1.2x faster | |
| 38825 |
Parametric cad modeling with Javascript |
706 | +1 | +9 | +48 | +3 | 16 | 1.4x faster | |
| 38826 |
🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free. |
1,183 | 0 | +7 | +26 | +3 | 0 | 1.9x faster | |
| 38827 |
handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (around 1k by default), support for exclusive llamacpp features, strong security, strict zero-trust-in-the-ai policy (the code hard limits the ai, no amount of prompt engineering will bypass it) |
541 | 0 | +8 | +26 | +3 | 0 | 1.8x faster | |
| 38828 |
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, and more. |
604 | 0 | +4 | +10 | +3 | 0 | 4.4x faster | |
| 38829 |
AI Marketing Suite for Claude Code. 15 marketing skills with parallel subagents — audit any website, generate copy, email sequences, ad campaigns, content calendars, competitive intelligence, and client-ready PDF reports. |
2,920 | +3 | +34 | +154 | +3 | 48 | 1.1x faster | |
| 38830 |
dsh-Openwrite:OpenWrite 的 DeepSeek Harness 小说创作插件,含统一创作 Agent、56 个小说工具、原生工作台与标准审稿 DAG |
967 | +4 | +29 | +136 | +3 | 56 | 1.1x faster | |
| 38831 |
The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps. |
2,564 | -1 | -1 | +54 | +3 | 0 | No data | |
| 38832 |
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. |
523 | 0 | 0 | 0 | +3 | 0 | No data | |
| 38833 |
A modern cross-platform GUI for yt-dlp. Download videos from YouTube, Bilibili, TikTok and 1000+ sites. Built with Tauri + Vue. |
713 | 0 | +37 | +160 | +3 | 24 | 1.1x faster | |
| 38834 |
SwiftUI agent skill for Claude Code, Codex, and other AI tools. |
6,568 | +1 | +61 | +374 | +3 | 4 | 1.1x faster | |
| 38835 |
Voice input for Fcitx5 — local and cloud ASR, LLM rewriting, cross-distro packages |
650 | 0 | +13 | +73 | +3 | 0 | 1.3x faster | |
| 38836 |
AI-powered Cisco Packet Tracer automation over MCP. Describe a network in natural language and it generates, validates and deploys full topologies (OSPF, EIGRP, RIP, DHCP). |
386 | 0 | +27 | +119 | +3 | 7 | 1.1x faster | |
| 38837 |
Minimal Claude Code statusline setup I personally use |
1,403 | 0 | +3 | +9 | +3 | 0 | Up from 0 | |
| 38838 |
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. | Lead: Minwei Wang (https://www.minwei.wang · ORCID: 0009-0002-7976-4689 · DOI: 10.5281/zenodo.24156132) |
19,852 | +1 | +31 | +190 | +3 | 58 | 1.1x faster | |
| 38839 |
kubernetes, reimplemented in Rust |
805 | 0 | +14 | +32 | +3 | 0 | 1.3x faster | |
| 38840 |
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README) |
617 | 0 | 0 | -3 | +3 | 0 | No data | |
| 38841 |
Self-hosted, secure tunnel server in Rust. Expose local HTTP/HTTPS/TCP/UDP services to the public internet via TLS-encrypted WebSocket. Open-source, pay-as-you-go managed option, MCP server for AI agents. |
665 | 0 | +4 | +8 | +3 | 0 | 4.4x faster | |
| 38842 |
Web-based browser profile manager for CloakBrowser — create, launch, and manage isolated browser profiles with unique fingerprints. Free, self-hosted Multilogin alternative |
1,020 | 0 | +12 | +39 | +3 | 0 | 1.3x faster | |
| 38843 |
#1 open-source code reviewer on Code-Review-Bench |
666 | 0 | +2 | +16 | +3 | 0 | No data | |
| 38844 |
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows. |
3,005 | +1 | +6 | +45 | +3 | 16 | 2.2x faster | |
| 38845 |
Multi-subscription extension for pi -- use multiple OAuth accounts per provider (Anthropic, Codex, Copilot, Gemini, Antigravity) |
549 | 0 | +8 | +28 | +3 | 0 | 1.5x faster | |
| 38846 |
No description |
194 | +1 | +17 | +58 | +3 | 16 | 1.2x faster | |
| 38847 |
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run() |
9,112 | +12 | +153 | +622 | +3 | 113 | 1.0x, steady | |
| 38848 |
AVdb 更新及CSV仓库 |
300 | +1 | +15 | +69 | +3 | 12 | 1.3x faster | |
| 38849 |
Real-time OSINT command center for the Iran/Israel and Russia/Ukraine theaters — 50+ live open-source intelligence sources (news, Telegram, military aircraft & naval tracking, missile alerts, prediction & defense markets) in one dashboard. No API keys. Free. Next.js + TypeScript. |
682 | 0 | +6 | +18 | +3 | 0 | 2.2x faster | |
| 38850 |
The world's most sophisticated street level image geolocation software |
1,114 | 0 | +17 | +67 | +3 | 0 | 1.2x faster |
Today counts stars since midnight US Pacific time, so it is a partial day.