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 2 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 modeled on trendshift.io: 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.
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 7451 |
Ant Design for Vue |
975 | 0 | +3 | +25 | -5 | 0 | 0.4x, slowing | |
| 7452 |
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning. |
1,068 | 0 | +6 | +42 | -5 | 8 | 0.6x, slowing | |
| 7453 |
[CVPR2026]🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YOLO = You Only Look Once)* 🔥🔥🔥 |
774 | 0 | +1 | +34 | -5 | 0 | 0.2x, slowing | |
| 7454 |
Terminal UI for WireGuard and OpenVPN with multi-tunnel control, real-time telemetry, and leak guarding. |
726 | 0 | 0 | +22 | -5 | 0 | 0.0x, slowing | |
| 7455 |
Dr. Zero Self-Evolving Search Agents without Training Data |
611 | 0 | +38 | +90 | -5 | 15 | 0.9x, slowing | |
| 7456 |
Agent Skills used by the Sentry team for development. |
1,109 | 0 | +18 | +83 | -5 | 16 | 0.8x, slowing | |
| 7457 |
Remove AI features, telemetry data reporting, sponsored content, product integrations, and other annoyances from web browsers. |
3,077 | 0 | +8 | +49 | -5 | 24 | 0.6x, slowing | |
| 7458 |
An unofficial desktop client for Jellyfin |
1,874 | 0 | +1 | +33 | -5 | 0 | 0.2x, slowing | |
| 7459 |
LX Music 数据同步服务端，同时支持了部分lx-music-desktop的网页端实现。 |
1,025 | 0 | +20 | +142 | -5 | 9 | 0.8x, slowing | |
| 7460 |
Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation. |
880 | 0 | +1 | +16 | -5 | 0 | 0.2x, slowing | |
| 7461 |
The best open source courseware to learn cloud engineering |
1,075 | 0 | +20 | +144 | -5 | 24 | 0.8x, slowing | |
| 7462 |
No description |
571 | 0 | +173 | +570 | -5 | 62 | 1.0x, steady | |
| 7463 |
A complete browser-based reverse engineering platform built on Rizin, running entirely client-side via WebAssembly. |
770 | 0 | +1 | +12 | -5 | 0 | 0.2x, slowing | |
| 7464 |
A collection of Agent Skills Standard and Best Practice for Programming Languages, Frameworks that help our AI Agent follow best practies on frameworks and programming laguages |
582 | 0 | -1 | +15 | -5 | 0 | -0.3x, slowing | |
| 7465 |
🎯 精选 RSSHub 实用路由推荐，让你的 RSS 阅读更高效！ |
920 | 0 | +4 | +45 | -5 | 0 | 0.5x, slowing | |
| 7466 |
Type-Safe keyboard shortcuts library with awesome devtools |
757 | 0 | +3 | +25 | -5 | 8 | 0.4x, slowing | |
| 7467 |
Comark is an open-source Markdown parser and renderer with components, attributes and plugins. It streams AI output to React, Vue, Svelte, Angular, HTML and the terminal. |
1,085 | 0 | +7 | +37 | -5 | 0 | 0.6x, slowing | |
| 7468 |
数学建模技能 - 面向 CUMCM、MCM/ICM 等数学建模竞赛的三阶段工作流：建模分析、Python/MATLAB 编程与 DOCX 论文生成。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本 |
1,893 | 0 | +6 | +60 | -5 | 8 | 0.6x, slowing | |
| 7469 |
一个 Linux.do 第三方客户端 |
2,544 | 0 | +15 | +111 | -5 | 32 | 0.7x, slowing | |
| 7470 |
Izuko TV：安卓电视（Android TV）番剧应用，基于 Animeko，直连 Bangumi（最低支持 Android 7.1） |
660 | 0 | +30 | +194 | -5 | 0 | 0.9x, slowing | |
| 7471 |
QuantaAlpha transforms how you discover quantitative alpha factors by combining LLM intelligence with evolutionary strategies. Just describe your research direction, and watch as factors are automatically mined, evolved, and validated through self-evolving trajectories. |
1,641 | 0 | +13 | +72 | -5 | 0 | 0.7x, slowing | |
| 7472 |
Anthony Fu's curated collection of agent skills. |
6,032 | 0 | +19 | +105 | -5 | 0 | 0.8x, slowing | |
| 7473 |
Sets of tools to help bypass DPI |
890 | 0 | +6 | +49 | -5 | 0 | 0.6x, slowing | |
| 7474 |
Virtual Gaming PC v5 – Free Cloud Gaming with GPU (No Lag, Instant Access) |
2,453 | 0 | +50 | +259 | -5 | 12 | 0.9x, slowing | |
| 7475 |
Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI), parallel runners, autonomous loops, and agent infrastructure. |
1,437 | 0 | +22 | +133 | -5 | 0 | 0.8x, slowing | |
| 7476 |
Recompilation of Blue Dragon |
883 | 0 | +27 | +149 | -5 | 0 | 0.9x, slowing | |
| 7477 |
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. |
1,023 | 0 | +9 | +57 | -5 | 8 | 0.6x, slowing | |
| 7478 |
A Graph-Centric Framework for Orchestrating Multi-Agent Systems with Vibe Graphing. |
566 | 0 | +2 | +31 | -5 | 0 | 0.3x, slowing | |
| 7479 |
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. |
3,319 | 0 | +8 | +67 | -5 | 0 | 0.6x, slowing | |
| 7480 |
High-performance icon rendering for React Native & Expo |
637 | 0 | +1 | +40 | -5 | 0 | 0.2x, slowing | |
| 7481 |
pi coding agent in a technicolor web trenchcoat |
885 | 0 | +1 | +18 | -5 | 0 | 0.2x, slowing | |
| 7482 |
vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm |
906 | 0 | +1 | +25 | -5 | 0 | 0.2x, slowing | |
| 7483 |
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree |
1,072 | 0 | +6 | +45 | -5 | 0 | 0.6x, slowing | |
| 7484 |
异环/Neverness to Everness脚本 |
619 | 0 | -2 | +8 | -5 | 0 | -0.8x, slowing | |
| 7485 |
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev. |
1,903 | 0 | +1 | +19 | -5 | 0 | 0.2x, slowing | |
| 7486 |
Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context; get tailored, production-ready output. Cursor, Claude Code, OpenClaw — no lock-in. |
1,071 | 0 | +6 | +64 | -5 | 0 | 0.5x, slowing | |
| 7487 |
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows. |
32,560 | +4 | +141 | +728 | -5 | 128 | 1.0x, steady | |
| 7488 |
Official agent plugin providing skills and MCP server configurations for Azure scenarios. |
1,609 | 0 | +10 | +79 | -5 | 0 | 0.7x, slowing | |
| 7489 |
WordPress MCP server with 234 Free tools and 547 total with Pro for building pages, managing content, and operating your site. Availability depends on installed integrations and enabled tools. |
759 | 0 | +2 | +33 | -5 | 0 | 0.3x, slowing | |
| 7490 |
Oracle3: open-source trading engine and MCP server for prediction markets. Finds fee-adjusted no-arbitrage violations across related event contracts and trades them live on Kalshi, Polymarket and Solana, or on paper, under pre-trade risk limits. 13 MCP tools, JSON CLI, agent skills, 600+ tests. |
560 | 0 | +36 | +267 | -5 | 0 | 0.9x, slowing | |
| 7491 |
A self-organizing Obsidian vault that gives AI coding agents persistent memory. |
5,472 | +1 | +41 | +604 | -5 | 5 | 0.9x, slowing | |
| 7492 |
JARVIS: a real-time agentic intelligence-gathering platform powered by autonomous web scraping & OSINT, streamed via Meta Ray-Ban smart glasses |
562 | 0 | +19 | +94 | -5 | 0 | 0.8x, slowing | |
| 7493 |
Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models. |
1,570 | 0 | 0 | +12 | -5 | 0 | 0.0x, slowing | |
| 7494 |
AI frontend |
752 | 0 | +11 | +61 | -5 | 0 | 0.7x, slowing | |
| 7495 |
EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance. |
1,276 | 0 | +5 | +42 | -5 | 0 | 0.5x, slowing | |
| 7496 |
The open SVG brand library: 7,600+ brand logos and cloud icons (AWS, Azure, GCP) as official SVG. Search, copy, ship via npm, CDN, CLI, React, Vue, Svelte, Figma, VS Code, Raycast and MCP. Free, MIT, no gatekeeping. |
2,935 | 0 | +29 | +150 | -5 | 8 | 0.8x, slowing | |
| 7497 |
Orchestrate thousands of agents and harnesses as a graph programatically |
1,421 | 0 | 0 | +14 | -5 | 0 | 0.0x, slowing | |
| 7498 |
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent. |
3,612 | 0 | +13 | +69 | -5 | 0 | 0.7x, slowing | |
| 7499 |
A clean, self-hosted web UI for managing your Traefik reverse proxy. |
1,657 | 0 | +4 | +37 | -5 | 0 | 0.5x, slowing | |
| 7500 |
Free AI PPT Templates — 4,000+ AI-generated presentation templates for any deck. Works with PowerPoint, Google Slides, Keynote, LibreOffice Impress, WPS Office, and more. |
787 | 0 | +4 | +29 | -5 | 8 | 0.5x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.