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. Star counts come from GitHub. Last updated 6 Nov 2026, 09:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 14551 |
An open-source AI based digital marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analytics - grounded in brand context, human approval, and verifiable outputs. Best for Brands, Agencies and one person campanies. |
928 | 0 | +10 | +75 | 0 | 10 | 1.1x faster | |
| 14552 |
从 Andrej Karpathy 推荐的 90 顶级技术博客中抓取最新文章，AI 多维评分筛选，生成一份每日精选日报。更多可见公众号：懂点儿AI |
1,660 | 0 | +2 | +15 | 0 | 0 | 1.2x faster | |
| 14553 |
Astrid is a portable, capability-secure operating system for composable software. |
10,291 | 0 | +3 | +17 | 0 | 0 | 0.9x, slowing | |
| 14554 |
Claude Code template for Spring Boot and other staff (included in the tags) |
1,445 | 0 | +8 | +148 | 0 | 0 | 1.0x, steady | |
| 14555 |
High-performance icon rendering for React Native & Expo |
639 | 0 | +2 | +40 | 0 | 0 | 1.2x faster | |
| 14556 |
A cross platform Audiobookshelf client for Android and iOS |
814 | 0 | +21 | +92 | 0 | 0 | 1.0x, steady | |
| 14557 |
ESP32-DIV HaleHound Edition for Cheap Yellow Display - Multi-protocol offensive security toolkit |
1,890 | 0 | +24 | +103 | 0 | 0 | 1.0x, steady | |
| 14558 |
Low-level IDE |
602 | 0 | +3 | +7 | 0 | 0 | 1.2x faster | |
| 14559 |
Lightweight open-source AI Agent optimized for Chinese users | Native support for domestic large-model coding plans | Compatible with the OpenClaw Skills ecosystem | Integrated with WeChat ClawBot, Weibo Lobster, Feishu, DingTalk, QQ, Xiaozhi AI, Telegram and dsh. |
784 | 0 | +1 | +5 | 0 | 0 | 1.2x faster | |
| 14560 |
Extract Windows credentials directly from VM memory snapshots and virtual disks |
1,657 | 0 | +10 | +33 | 0 | 0 | 1.0x, steady | |
| 14561 |
self-improving agent |
758 | 0 | +1 | +5 | 0 | 0 | 1.2x faster | |
| 14562 |
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime. |
693 | 0 | +18 | +83 | 0 | 8 | 1.0x, steady | |
| 14563 |
无需软路由，让你的Wi-Fi科学上网，网络加速ps5、switch、手机等可连Wi-Fi的设备。仅需一台macmini或者mac电脑，暂不支持windows |
541 | 0 | +4 | +11 | 0 | 8 | 0.9x, slowing | |
| 14564 |
GitHub Quick Review: Evaluate your enterprise and organizations against GitHub best practices |
528 | 0 | 0 | +1 | 0 | 0 | No data | |
| 14565 |
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM. |
1,586 | 0 | 0 | +14 | 0 | 0 | No data | |
| 14566 |
No description |
597 | 0 | +3 | +19 | 0 | 0 | 0.9x, slowing | |
| 14567 |
The most comprehensive code intelligence MCP server for AI coding agents. 40+ tools, 30+ languages, 9 agent integrations. Pre-indexed semantic knowledge graphs for instant code understanding — fewer tokens, fewer tool calls, 100% local. |
691 | 0 | +7 | +36 | 0 | 0 | 1.0x, steady | |
| 14568 |
Free, local chat where AI coding agents can tag each other, talk, and coordinate with you. |
1,582 | 0 | +11 | +55 | 0 | 0 | 1.0x, steady | |
| 14569 |
Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tools, 10 warehouses, AI-powered. |
817 | 0 | +2 | +14 | 0 | 8 | 1.2x faster | |
| 14570 |
JARVIS: a real-time agentic intelligence-gathering platform powered by autonomous web scraping & OSINT, streamed via Meta Ray-Ban smart glasses |
580 | 0 | +23 | +100 | 0 | 0 | 1.0x, steady | |
| 14571 |
微信公众号文章抓取 & Markdown 转换工具 |
1,082 | 0 | +5 | +32 | 0 | 0 | 1.0x, steady | |
| 14572 |
Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting. |
823 | 0 | +3 | +14 | 0 | 10 | 1.2x faster | |
| 14573 |
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. |
2,866 | 0 | +34 | +152 | 0 | 6 | 1.0x, steady | |
| 14574 |
亚马逊选品 之 Listing全维度穿透分析报告 加上 全品类分析 ，关键词分析，差评分析 ，市场调研 等等。codex/claude code agent skill, amazon sorftime MCP/西柚mcp/sif mcp/卖家精灵sellersprite 智能体skill. 亚马逊跨境电商skill工具集。 |
1,083 | 0 | +32 | +140 | 0 | 18 | 1.0x, steady | |
| 14575 |
Servizio API per l'estrazione automatizzata di dati catastali dal portale SISTER |
677 | 0 | 0 | +3 | 0 | 0 | No data | |
| 14576 |
A collection of open-source Agent Skills for content creation — images, audio, and video. |
820 | 0 | +3 | +26 | 0 | 0 | 1.2x faster | |
| 14577 |
An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently. |
1,296 | 0 | +5 | +18 | 0 | 0 | 1.0x, steady | |
| 14578 |
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever. |
788 | 0 | +3 | +24 | 0 | 0 | 1.2x faster | |
| 14579 |
A complete list of SAP MCP Servers and SAP AI Skills |
566 | 0 | +13 | +56 | 0 | 8 | 1.0x, steady | |
| 14580 |
把网页AI转api，如claude2api |
659 | 0 | +2 | +11 | 0 | 0 | 1.2x faster | |
| 14581 |
Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views |
931 | 0 | +3 | +29 | 0 | 0 | 1.2x faster | |
| 14582 |
Orchestrate thousands of agents and harnesses as a graph programatically |
1,422 | 0 | +1 | +13 | 0 | 0 | 1.2x faster | |
| 14583 |
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent. |
3,625 | 0 | +17 | +71 | 0 | 0 | 1.0x, steady | |
| 14584 |
TieZ 是一款基于 Tauri 的跨平台剪贴板管理器 / A cross-platform clipboard manager with history, tags, sync, privacy protection, and fast daily workflows. |
3,085 | 0 | +21 | +158 | 0 | 16 | 1.0x, steady | |
| 14585 |
Real time video translation / dubbing skill |
812 | 0 | 0 | 0 | 0 | 0 | No data | |
| 14586 |
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions. |
1,025 | 0 | +3 | +106 | 0 | 0 | 0.9x, slowing | |
| 14587 |
The universal skill manager for AI coding agents. |
966 | 0 | +3 | +15 | 0 | 0 | 0.9x, slowing | |
| 14588 |
Collection of AI agent skills for Claude Code |
769 | 0 | +1 | +8 | 0 | 0 | 1.2x faster | |
| 14589 |
gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶ |
832 | 0 | +1 | +5 | 0 | 0 | 1.2x faster | |
| 14590 |
Multi-subscription extension for pi -- use multiple OAuth accounts per provider (Anthropic, Codex, Copilot, Gemini, Antigravity) |
538 | 0 | +6 | +24 | 0 | 0 | 1.0x, steady | |
| 14591 |
A floating desktop reader with transparent text-only mode for low-distraction reading. |
674 | 0 | +4 | +20 | 0 | 8 | 0.9x, slowing | |
| 14592 |
Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time. |
790 | 0 | +3 | +19 | 0 | 0 | 1.2x faster | |
| 14593 |
⚡ LFK is a lightning-fast, keyboard-focused, yazi-inspired terminal user interface for navigating and managing Kubernetes clusters. Built for speed and efficiency, it brings a three-column Miller columns layout with an owner-based resource hierarchy to your terminal. |
926 | 0 | +3 | +14 | 0 | 0 | 0.9x, slowing | |
| 14594 |
Mac app to review the code written by you or your agent with Claude in the loop. |
900 | 0 | +3 | +55 | 0 | 0 | 0.9x, slowing | |
| 14595 |
Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more |
574 | 0 | +3 | +13 | 0 | 0 | 1.2x faster | |
| 14596 |
📖 开箱即用的 PDF 学术翻译神器 | Win + Mac 双平台 | 公式排版完美保留 · Zotero 深度联动 · 35 种语言 · 20+ AI 翻译引擎 · 表格/OCR/术语库 · 批量翻译 | 基于 PDFMathTranslate (EMNLP 2025) |
524 | 0 | +9 | +47 | 0 | 24 | 1.0x, steady | |
| 14597 |
A lightweight, offline Android Text-to-Speech (TTS) engine enabling seamless system-wide voice cloning and high-fidelity text reading. / 运行在安卓本地的轻量级文字转语音 (TTS) 引擎，支持离线发音人提取、零门槛音色克隆与双擎系统级全局听书。 |
873 | 0 | +8 | +46 | 0 | 0 | 1.0x, steady | |
| 14598 |
⚡ 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. |
796 | 0 | +4 | +20 | 0 | 0 | 0.9x, slowing | |
| 14599 |
No TrickyStore on Canoe |
1,206 | 0 | +16 | +97 | 0 | 26 | 1.0x, steady | |
| 14600 |
微信Clawbot接入任意Agent |
1,316 | 0 | +3 | +26 | 0 | 16 | 1.2x faster |
Today counts stars since midnight US Pacific time, so it is a partial day.