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, 10:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 14601 |
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 | |
| 14602 |
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 | 1.1x faster | |
| 14603 |
📖 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 | |
| 14604 |
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 | |
| 14605 |
DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is designed for both human users and AI agent scenarios. |
3,940 | +1 | +72 | +735 | 0 | 84 | 1.0x, steady | |
| 14606 |
⚡ 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 | |
| 14607 |
微信Clawbot接入任意Agent |
1,316 | 0 | +3 | +26 | 0 | 16 | 1.1x faster | |
| 14608 |
Connect to any agents with WeChat ClawBot. |
1,691 | 0 | +3 | +23 | 0 | 0 | 0.9x, slowing | |
| 14609 |
No description |
825 | 0 | +5 | +48 | 0 | 0 | 1.0x, steady | |
| 14610 |
Curated list of the best truly open-source AI projects, models, tools, and infrastructure. Daily updated. |
4,992 | 0 | +33 | +156 | 0 | 15 | 1.0x, steady | |
| 14611 |
No description |
524 | 0 | 0 | +4 | 0 | 0 | No data | |
| 14612 |
Shob – an AI agent that delivers high-quality coding & automation work |
575 | 0 | 0 | +2 | 0 | 0 | No data | |
| 14613 |
Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation. |
1,564 | 0 | +10 | +57 | 0 | 24 | 1.0x, steady | |
| 14614 |
大麦网抢票自动化 — Mobile(U2) / Desktop(Tauri+Rust) 方案 |
549 | 0 | +10 | +80 | 0 | 16 | 1.0x, steady | |
| 14615 |
Cloud-native agent-as-a-service framework with one-click IaC deployment. |
579 | 0 | +17 | +79 | 0 | 8 | 1.0x, steady | |
| 14616 |
MrKraken's string replacements QoL. Always check for update after an SC patch!!! |
604 | 0 | +5 | +41 | 0 | 0 | 1.0x, steady | |
| 14617 |
A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work. |
882 | 0 | +2 | +7 | 0 | 0 | 1.1x faster | |
| 14618 |
🔥 A Survey on AI Auto-Research |
573 | 0 | +4 | +32 | 0 | 8 | 0.9x, slowing | |
| 14619 |
The new model of Jarvis, Mark XXXV, builds upon the previous Mark XXX. With each iteration, new features and integrations are added, making every model a refined and improved version of the one before it. |
628 | 0 | +9 | +43 | 0 | 10 | 1.0x, steady | |
| 14620 |
An infinite zoomable canvas for coding. Editor, terminal, and browser panels in a spatial workspace. |
2,227 | 0 | +10 | +54 | 0 | 8 | 1.0x, steady | |
| 14621 |
[ECCV 2026] 🔥 Official impl. of "DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing". |
794 | 0 | +3 | +15 | 0 | 0 | 0.9x, slowing | |
| 14622 |
夙愿反复打磨的精品 Skill |
471 | 0 | +24 | +195 | 0 | 0 | 1.0x, steady | |
| 14623 |
Structure-aware skeleton loader. One Web Component, every framework. |
816 | 0 | +3 | +16 | 0 | 0 | 0.9x, slowing | |
| 14624 |
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES. |
574 | 0 | +6 | +42 | 0 | 0 | 1.0x, steady | |
| 14625 |
Native macOS and iOS App for the Hermes AI agent — multi-window, multi-server (local + remote over SSH). Chat, dashboard, sessions, memory, cron, MCP, and more. |
907 | 0 | +6 | +25 | 0 | 0 | 1.0x, steady | |
| 14626 |
本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。(精校) |
582 | 0 | +9 | +41 | 0 | 8 | 1.0x, steady | |
| 14627 |
Research archive of Claude Code source and runtime artifacts reconstructed from published npm source maps. |
979 | 0 | +3 | +22 | 0 | 0 | 1.1x faster | |
| 14628 |
OmniVoice TTS nodes for ComfyUI - Zero-shot multilingual text-to-speech with voice cloning, voice design, and multi-speaker dialogue |
565 | 0 | +2 | +8 | 0 | 0 | 1.1x faster | |
| 14629 |
Multi-Agent Collaboration for Team and Friends |
1,489 | 0 | +17 | +296 | 0 | 0 | 1.0x, steady | |
| 14630 |
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself. |
1,807 | 0 | +16 | +92 | 0 | 18 | 1.0x, steady | |
| 14631 |
为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos. |
660 | 0 | +7 | +34 | 0 | 0 | 1.0x, steady | |
| 14632 |
马斯克.skill — Elon Musk的认知操作系统。由女娲.skill生成。 |
562 | 0 | +4 | +28 | 0 | 8 | 0.9x, slowing | |
| 14633 |
A fast, native terminal for Windows. Formerly winghostty. 🌙 |
517 | 0 | +26 | +97 | 0 | 0 | 1.0x, steady | |
| 14634 |
Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message |
1,316 | 0 | +14 | +64 | 0 | 0 | 1.0x, steady | |
| 14635 |
Predictive inline suggestions for zsh |
931 | 0 | +8 | +44 | 0 | 8 | 1.0x, steady | |
| 14636 |
WorldEngine: Towards the Era of Post-Training for Autonomous Driving |
532 | 0 | +3 | +18 | 0 | 0 | 0.9x, slowing | |
| 14637 |
No description |
570 | 0 | 0 | 0 | 0 | 0 | No data | |
| 14638 |
Seedance 2.0 × Higgsfield 技能集 | 15 Claude prompt skills for AI video generation — cinematic, 3D CGI, anime, e-commerce ads, music videos & more. Each skill: 2-second hook framework, camera encyclopedia, 5+ production prompts. 含2秒钩子框架、摄像机百科、行业最佳实践提示词工程 |
1,026 | 0 | +19 | +98 | 0 | 8 | 1.0x, steady | |
| 14639 |
Orchard-Agentic is a collection of open-source work on agentic modeling |
556 | 0 | +1 | +20 | 0 | 0 | 1.1x faster | |
| 14640 |
ParseBench - A Document Parsing Benchmark for AI Agents |
626 | 0 | +6 | +32 | 0 | 0 | 1.0x, steady | |
| 14641 |
See exactly what’s using your ports — and kill it in one click. |
528 | 0 | +1 | +6 | 0 | 0 | 1.1x faster | |
| 14642 |
Lossless DFlash speculative decoding for MLX on Apple Silicon |
793 | 0 | +2 | +7 | 0 | 0 | 1.1x faster | |
| 14643 |
Fantasy Inspired Idle Skilling Game |
535 | 0 | +3 | +25 | 0 | 0 | 0.9x, slowing | |
| 14644 |
A GitHub TUI |
1,135 | 0 | +4 | +15 | 0 | 0 | 0.9x, slowing | |
| 14645 |
An autonomous research colleague — from a question to a compiled manuscript, while you sleep. |
1,169 | 0 | 0 | +1 | 0 | 0 | No data | |
| 14646 |
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta. |
5,531 | 0 | +14 | +100 | 0 | 8 | 1.0x, steady | |
| 14647 |
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale |
670 | 0 | +7 | +31 | 0 | 0 | 1.0x, steady | |
| 14648 |
Plugin for Butterbase.ai |
535 | 0 | 0 | +1 | 0 | 0 | No data | |
| 14649 |
super expressive prompting model based on ltx2.3 |
517 | 0 | +2 | +22 | 0 | 0 | 1.1x faster | |
| 14650 |
Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python. |
927 | 0 | +3 | +26 | 0 | 0 | 0.9x, 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.