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 15 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: 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. 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 |
|---|---|---|---|---|---|---|---|---|---|
| 34551 |
全球最可爱的鸣潮角色菲比表情包收集站-存放数据的 |
529 | 0 | +6 | +32 | -2 | 8 | 0.8x, slowing | |
| 34552 |
A git-aware, read-only file viewer for herdr. Mouse friendly, keyboard-driven TUI: tree + content pane with diffs, rendered markdown, and syntax highlighting. |
706 | 0 | +4 | +49 | -2 | 0 | 0.7x, slowing | |
| 34553 |
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline. |
769 | 0 | +1 | +12 | -2 | 0 | 0.4x, slowing | |
| 34554 |
ProxyPin script for authorized iOS Apple WLOC response rewriting tests |
542 | 0 | +7 | +93 | -2 | 0 | 0.8x, slowing | |
| 34555 |
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models. |
586 | 0 | +2 | +23 | -2 | 0 | 0.6x, slowing | |
| 34556 |
A Telegram client, but déjà vu |
699 | 0 | +3 | +27 | -2 | 8 | 0.6x, slowing | |
| 34557 |
Scaling the Horizon, Not the Parameters |
607 | 0 | 0 | +39 | -2 | 0 | 0.0x, slowing | |
| 34558 |
No description |
931 | 0 | +2 | +16 | -2 | 0 | 0.5x, slowing | |
| 34559 |
A flight-compliant WebAssembly interpreter. |
1,627 | 0 | +2 | +18 | -2 | 8 | 0.6x, slowing | |
| 34560 |
QuantSkills组织的全景导航 ：面向 AI Agent 的开源量化 Skill & Agent 生态，从数据、因子研究、回测验证到风险监控与交易自动化。｜Open-source Quant Skills & Agents for AI-driven research, backtesting, risk and trading automation.——Panoramic navigator for the QuantSkills organization |
2,753 | +1 | +137 | +671 | -2 | 109 | 1.0x, steady | |
| 34561 |
AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark. |
811 | 0 | +2 | +248 | -2 | 0 | 0.6x, slowing | |
| 34562 |
No description |
1,577 | 0 | +7 | +22 | -2 | 8 | 0.8x, slowing | |
| 34563 |
Ackem — 本地优先 AI 桌面陪伴 · Local-first AI desktop companion. 隐私数据不上传，支持记忆/情绪/扩展/ 。AGPL-3.0 |
554 | 0 | 0 | +4 | -2 | 0 | 0.0x, slowing | |
| 34564 |
A native macOS UI for Apple's platform |
1,635 | 0 | +5 | +85 | -2 | 8 | 0.7x, slowing | |
| 34565 |
Live USB device tree in your terminal. Rust TUI, no root, no libusb. Full activity metrics on Linux; device tree on macOS/Windows. |
713 | 0 | +1 | +16 | -2 | 0 | 0.4x, slowing | |
| 34566 |
From Foundation to Application |
1,113 | 0 | +10 | +65 | -2 | 0 | 0.8x, slowing | |
| 34567 |
Morluto profile README |
193 | +1 | +14 | +121 | -2 | 16 | 0.9x, slowing | |
| 34568 |
A V2Ray client for Android, support Xray core and v2fly core |
1,540 | 0 | +38 | +287 | -2 | 15 | 0.9x, slowing | |
| 34569 |
Claude Code가 명확한 한국어를 구사하게 만드는 output-style 플러그인 | Claude Code output-style for clear, fluent Korean |
1,505 | 0 | +15 | +79 | -2 | 8 | 0.9x, slowing | |
| 34570 |
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill. |
2,852 | +7 | +130 | +556 | -2 | 108 | 1.0x, steady | |
| 34571 |
Grok 自动注册机 — 注册成功后自动入库 CLIProxyAPI (CPA)：支持本地 auth 目录与远程 Management API 上传 |
584 | 0 | +1 | +9 | -2 | 0 | 0.4x, slowing | |
| 34572 |
sanoTTS (सानो = 'small' in Nepali): 294k–2.27M-parameter neural TTS that runs on a $3 chip, in the browser, or in Python with low-latency streaming. |
844 | 0 | +8 | +50 | -2 | 16 | 0.8x, slowing | |
| 34573 |
UI Sound Effects for your interfaces |
940 | 0 | +11 | +79 | -2 | 0 | 0.8x, slowing | |
| 34574 |
Think with AI beyond the chat box. A shared canvas for handwriting, equations, diagrams, and spatial reasoning. |
2,519 | 0 | +2 | +40 | -2 | 0 | 0.6x, slowing | |
| 34575 |
Home Assistant integration for smooth IKEA BILRESA scroll wheel dimming over Matter (real-time MultiPressOngoing events) |
100 | 0 | +8 | +86 | -2 | 8 | 0.8x, slowing | |
| 34576 |
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent. |
1,446 | 0 | +2 | +12 | -2 | 0 | 0.5x, slowing | |
| 34577 |
深度专门用于写作的Harness智能体 |
738 | 0 | +14 | +87 | -2 | 8 | 0.9x, slowing | |
| 34578 |
A smooth, customizable Wayland compositor with glass effects, three window layouts, and settings you can actually click. We got a little carried away. |
1,454 | 0 | +27 | +296 | -2 | 0 | 0.9x, slowing | |
| 34579 |
Latest docs: https://q-ant-gmbh.github.io/qant_native_computing_toolkit/ |
96 | 0 | +3 | +39 | -2 | 0 | 0.6x, slowing | |
| 34580 |
An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews results to improve the next round of growth. 从代码到市场的开源端到端增长工具。理解产品、接入信息渠道、研究市场、执行增长行动，并基于真实数据自我改进。 |
1,972 | 0 | +1 | +17 | -2 | 0 | 0.4x, slowing | |
| 34581 |
Preview-first Grok Build instruction deployment with compat and hook isolation, durable recovery, and layered uninstall. |
507 | 0 | 0 | +16 | -2 | 8 | 0.0x, slowing | |
| 34582 |
The open registry and delivery platform for agent skills. |
608 | +2 | +130 | +576 | -2 | 39 | 1.0x, steady | |
| 34583 |
A World of Tanks-style armored combat simulator built directly with Three.js and Vite: 220 vehicles, 33 destructible battlefields, and 13 modes, with plate-level armor, ballistics, modules, spotting, and physics. Play in your browser on desktop or mobile. Built end-to-end by a multi-agent Claude/Codex pipeline. |
539 | 0 | +6 | +58 | -2 | 0 | 0.8x, slowing | |
| 34584 |
FDE（前沿部署工程师）从零入门指南（基于范冰《增长黑客》原书框架） |
5,562 | 0 | +71 | +483 | -2 | 4 | 1.0x, steady | |
| 34585 |
Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling, sampler-aware support for Euler, ER-SDE, RES, SEEDS and SA-Solver, CPU/VRAM history storage, and fail-closed native fallbacks. |
719 | 0 | +2 | +29 | -2 | 0 | 0.5x, slowing | |
| 34586 |
No description |
301 | 0 | +23 | +105 | -2 | 8 | 0.9x, slowing | |
| 34587 |
Agents Office v3 (Beta) — a headless office where AI agents do real work |
815 | 0 | +33 | +180 | -2 | 0 | 0.9x, slowing | |
| 34588 |
Unity plugin for third-party agent platforms |
640 | 0 | +20 | +219 | -2 | 16 | 0.9x, slowing | |
| 34589 |
No description |
96 | 0 | 0 | +86 | -2 | 0 | 0.0x, slowing | |
| 34590 |
Figma like visual editor built for Claude Code, Codex and OpenCode |
738 | 0 | +2 | +18 | -2 | 0 | 0.6x, slowing | |
| 34591 |
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included. |
703 | 0 | +3 | +18 | -2 | 0 | 0.6x, slowing | |
| 34592 |
Open Source Steam Unlocker |
263 | 0 | +24 | +85 | -2 | 26 | 0.9x, slowing | |
| 34593 |
Pre-1.0. An omarchy-style desktop environment for macOS: tiling with a real Super key, dwindle layout, a themed status bar written for it, focus-follows-mouse, trackpad workspace swipes and a live workspace overview — ~157MB, six self-built Swift binaries, one repo. Built and tested on macOS 26 / Apple Silicon. |
715 | 0 | +3 | +28 | -2 | 0 | 0.6x, slowing | |
| 34594 |
a desktop app for getting work done with any model |
1,054 | 0 | +10 | +71 | -2 | 8 | 0.8x, slowing | |
| 34595 |
DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF） |
975 | 0 | +20 | +104 | -2 | 8 | 0.9x, slowing | |
| 34596 |
🚧 Under construction — no-training RefMod reference adapters for MiniMax H3 (compress reference images/videos into tiny latents, no training needed). |
629 | 0 | +11 | +192 | -2 | 0 | 0.8x, slowing | |
| 34597 |
The self-improving context engine for coding agents. |
514 | 0 | +10 | +55 | -2 | 0 | 0.8x, slowing | |
| 34598 |
Zetta is an efficient closed-loop embodied harness for self-evolving physical intelligence. It evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Project Page: https://air-embodied-brain.github.io/zetta/ |
1,326 | 0 | +4 | +32 | -2 | 0 | 0.7x, slowing | |
| 34599 |
将参考声音和中文文案自动生成白板动画视频的本地 AI 工具。 |
802 | 0 | +2 | +30 | -2 | 0 | 0.5x, slowing | |
| 34600 |
DeepSeek Harness 提示词破限插件：通过系统提示词解除模型回答限制，深度适配 Web 与桌面端多模式及工具调用 |
1,184 | +2 | +152 | +901 | -2 | 60 | 1.0x, steady |
Today counts stars since midnight US Pacific time, so it is a partial day.