GitHub repositories taking off today
Ranked by how many more stars each repo got today so far (since midnight US Pacific) than yesterday's pace would predict. Star counts come from GitHub. Last updated 16 Nov 2026, 23:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 43901 |
白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。 |
698 | +5 | +52 | +296 | -2 | 66 | 0.7x, slowing | |
| 43902 |
通过扫码或机器人凭据把IM机器人接入DeepSeek Harness(支持飞书、微信、钉钉、企业微信、QQ、Slack、Telegram、Discord和WhatsApp)。 Connect IM bots to DeepSeek Harness via QR code or credentials (9 channels). |
3,651 | +17 | +215 | +1,547 | -2 | 211 | 0.9x, slowing | |
| 43903 |
dlss 5 cyberpunk |
82 | +23 | +72 | +82 | -2 | 184 | 0.9x, slowing | |
| 43904 |
DSH Agency Agents — 为 DeepSeek Harness 提供 321 名可召唤的专业智能体 · 321 summonable domain experts for DeepSeek Harness |
256 | +1 | +24 | +117 | -2 | 18 | 0.4x, slowing | |
| 43905 |
Independent native Design (including PPT) and Video plugins for DeepSeek Harness. |
1,854 | +13 | +57 | +387 | -2 | 200 | 0.9x, slowing | |
| 43906 |
SVG recreation of the x.ai bot avatar. One shape morphing through 14 states, measured off the reference video frame by frame. |
1,981 | +2 | +27 | +182 | -2 | 32 | 0.5x, slowing | |
| 43907 |
A local desktop app that turns videos and images into 3D Gaussian Splats in one click. |
2,529 | +4 | +104 | +500 | -2 | 69 | 0.7x, slowing | |
| 43908 |
【Project-IBⅡ】一个单文件PWA个人Agent应用,兼备多种工作技能与创意玩法,可同时对接多位自定义Agent助手,每一位Agent都具备与用户的长期独立记忆。用户数据与记忆支持完整的数据导入和导出,公开透明。支持导入其他官端的聊天记录,如ChatGPT/Claude等,不依赖任何网络服务器。 |
498 | +3 | +34 | +67 | -2 | 60 | 0.6x, slowing | |
| 43909 |
A visual, non-linear conversation workspace plugin for DeepSeek Harness ; A canvas-based session explorer and branching workspace for DeepSeek Harness. |
723 | +2 | +26 | +188 | -2 | 26 | 0.4x, slowing | |
| 43910 |
基于dsh web实现的多种模式,目的是服务于redteam进行授权的安全研究,覆盖渗透测试、红队评估、代码审计等范围领域,请勿用于非法行为。(允许二开,赋予模块各位自己的业务逻辑,方法论只有自己熟练的才好用,好的方法论=好的生态) |
893 | +4 | +40 | +201 | -2 | 72 | 0.6x, slowing | |
| 43911 |
Hermes3D is an open source 3D engine built on Hermes Agents for creating games, simulations, and high-performance 3D applications. |
788 | 0 | +25 | +189 | -2 | 8 | 0.0x, slowing | |
| 43912 |
Watch a Claude Code or Codex session as a live flow graph, in your terminal or your browser. |
1,174 | +1 | +21 | +125 | -2 | 8 | 0.4x, slowing | |
| 43913 |
A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos. |
6,587 | +7 | +95 | +568 | -2 | 140 | 0.8x, slowing | |
| 43914 |
No description |
2,249 | 0 | +31 | +353 | -2 | 0 | 0.0x, slowing | |
| 43915 |
Case-study journal of MiniMax H3 prompt engineering experiments |
499 | +3 | +237 | +336 | -2 | 29 | 0.6x, slowing | |
| 43916 |
CrowdGPT is an opensource framework that aims to train AI without any datacenters |
218 | +4 | +33 | +163 | -2 | 50 | 0.6x, slowing | |
| 43917 |
One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography. |
3,662 | +1 | +32 | +221 | -2 | 32 | 0.3x, slowing | |
| 43918 |
🌌 Mebular 忆云 · 智能体共享记忆与任务协作 | One shared memory and task graph for all your AI agents and devices: automatic or on-demand, secure, controllable, and decentralized! |
211 | +4 | +52 | +210 | -2 | 54 | 0.6x, slowing | |
| 43919 |
SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases. |
844 | +2 | +17 | +103 | -2 | 34 | 0.5x, slowing | |
| 43920 |
Native Ubuntu control center for agent usage, system utilities, media, clipboard, emoji and GNOME integration. |
1,052 | -2 | +20 | +1,038 | -2 | 0 | No data | |
| 43921 |
Compatibility layer and high level emulator hybrid for running macOS applications across operating systems and architectures |
379 | 0 | +15 | +282 | -2 | 16 | 0.0x, slowing | |
| 43922 |
You don't write AGENTS.md. You train it with gradient descent. |
1,519 | +1 | +31 | +127 | -2 | 18 | 0.4x, slowing | |
| 43923 |
Local observability for AI coding agents. Agenttrail Map shows your project as a live map of what each agent is working on, in the browser or natively in Herdr. |
1,031 | +2 | +29 | +122 | -2 | 52 | 0.4x, slowing | |
| 43924 |
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 |
1,206 | +8 | +145 | +860 | -2 | 99 | 0.8x, slowing | |
| 43925 |
现代化的开源跨平台视频下载工具 — 一键保存全网无水印高清视频 / A modern, cross-platform open-source video downloader GUI for yt-dlp & FFmpeg |
1,582 | +2 | +134 | +565 | -2 | 3 | 0.5x, slowing | |
| 43926 |
Official Codebase of 3DCodeVerse |
400 | +1 | +23 | +286 | -2 | 18 | 0.4x, slowing | |
| 43927 |
A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse. |
905 | 0 | +10 | +115 | -2 | 8 | 0.0x, slowing | |
| 43928 |
Run Omarchy on MacOS without any setup. |
2,993 | +1 | +53 | +333 | -2 | 16 | 0.3x, slowing | |
| 43929 |
My AI learning system. |
4,241 | +8 | +86 | +601 | -2 | 124 | 0.8x, slowing | |
| 43930 |
无线麦 SayAll Windows 版:支持小米蓝牙遥控器 2(RC001)和 2 Pro(RC003)的 Windows 真机适配与语音桥接。 |
315 | +3 | +47 | +178 | -2 | 52 | 0.6x, slowing | |
| 43931 |
Monid - OpenRouter for agent tools. Join our community at https://discord.gg/rQzztcgJV8 |
6,207 | +2 | +55 | +1,944 | -2 | 50 | 0.5x, slowing | |
| 43932 |
Watch for bugs like a hawk! gohawk is a set of static analyzers for Go, focused on concurrency and resource-lifetime bugs. |
157 | +1 | +16 | +148 | -2 | 40 | 0.3x, slowing | |
| 43933 |
A Decentralized, Scalable Multiagent Harness |
922 | 0 | +17 | +920 | -2 | 8 | 0.0x, slowing | |
| 43934 |
Streaming 3D reconstruction from only video input: Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction |
1,461 | 0 | +17 | +135 | -2 | 16 | 0.0x, slowing | |
| 43935 |
Official Hex-Rays IDA MCP Server. |
1,627 | +1 | +51 | +372 | -2 | 23 | 0.4x, slowing | |
| 43936 |
Use Omarchy Linux on Windows without any hassle. |
789 | 0 | +21 | +153 | -2 | 0 | 0.0x, slowing | |
| 43937 |
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex. |
673 | -1 | +11 | +197 | -2 | 0 | -1.6x, slowing | |
| 43938 |
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes. |
699 | +4 | +68 | +344 | -2 | 72 | 0.6x, slowing | |
| 43939 |
OptiScaler bridges upscaling/frame gen across GPUs. Supports DLSS2+/XeSS/FSR2+ inputs, replaces native upscalers, enables FSR-FG/XeFG on non-FG titles. Supports Nukem mod for DLSSG-to-FSR3 FG. This fork adds support for neural rendering on dx12 games, more to come. |
873 | 0 | +9 | +65 | -2 | 8 | 0.0x, slowing | |
| 43940 |
No description |
321 | +2 | +64 | +319 | -2 | 18 | 0.4x, slowing | |
| 43941 |
Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later. |
1,031 | +6 | +63 | +524 | -2 | 72 | 0.8x, slowing | |
| 43942 |
Lecture and lab slides for EECS 498 AASE (Applied Agentic Software Engineering), UMich Fall 2026 |
334 | -2 | -1 | +235 | -2 | 0 | No data | |
| 43943 |
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. |
3,480 | +1 | +32 | +224 | -2 | 18 | 0.4x, slowing | |
| 43944 |
通过102万字语料提炼的公文写作 skill,把公文写作风格变成可测量、可验收的量化数据 |
2,557 | +7 | +85 | +1,039 | -2 | 92 | 0.8x, slowing | |
| 43945 |
向顶会优秀论文学科研|Oral Paper Skill — 从 883 篇 Oral 论文摘要中“蒸馏”共通做法,用于论文对照改进与学习复盘 · Skill + prompt pack (CN/EN). Learn from 883 Oral paper abstracts to improve your research and writing. |
591 | +1 | +23 | +170 | -2 | 24 | 0.3x, slowing | |
| 43946 |
下一代跨平台水杉输入法(MSIME):面向 Android、iOS、macOS、Linux、Windows 与 HarmonyOS 的多平台中文输入法,使用共享输入引擎与各平台原生宿主。 |
1,333 | +8 | +96 | +575 | -2 | 122 | 0.8x, slowing | |
| 43947 |
Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux |
611 | -1 | +7 | +28 | -2 | 0 | -1.6x, slowing | |
| 43948 |
Cloudflare 优选域名 API,服务于 Cloudflare 免费代理搭建方案,优质域名即为优质节点。 |
267 | 0 | +14 | +75 | -2 | 0 | 0.0x, slowing | |
| 43949 |
CFNext —— 部署在 Cloudflare Workers / Pages 的多功能代理订阅管理面板 |
3,003 | +8 | +95 | +1,091 | -2 | 110 | 0.8x, slowing | |
| 43950 |
An AI toolkit that turns agents into teachers rather than code yapping machines |
883 | +2 | +16 | +80 | -2 | 40 | 0.4x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 10 more tracked repositories are still loading their star history and will join the ranking once it is complete.