GitHub repositories taking off in the last 90 days
Ranked by how many more stars each repo got in the last 90 days than its pace over the 90 days before would predict. Star counts come from GitHub. Last updated 19 Nov 2026, 00:20 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 | 90d | Above pace ↑ | Momentum | Speed-up | Weekly stars |
|---|---|---|---|---|---|---|---|---|---|---|
| 47601 |
A GUI Panel providing Worker subscriptions for VLESS, Trojan and Warp configs alongside a private DoH server and chain proxies, offering full DNS, clean IP, Fragment, Warp, Warp pro and routing settings for cross-platform clients using Amnezia, Wireguard, Sing-box, Clash/Mihomo and Xray cores. |
13,897 | +1 | +16 | +172 | +871 | -1,998 | 0 | 0.3x, slowing | |
| 47602 |
Eagle: Frontier Vision-Language Models with Data-Centric Strategies |
3,857 | +1 | +24 | +147 | +448 | -2,007 | 0 | 0.2x, slowing | |
| 47603 |
基于Python的开源量化交易平台开发框架 |
46,417 | +7 | +67 | +520 | +1,963 | -2,008 | 0 | 0.5x, slowing | |
| 47604 |
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces |
11,543 | +3 | +62 | +294 | +697 | -2,020 | 0 | 0.3x, slowing | |
| 47605 |
2,955+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. CLI, MCP and plugins. |
49,963 | +42 | +385 | +2,072 | +5,163 | -2,022 | 0 | 0.7x, slowing | |
| 47606 |
Robust Speech Recognition via Large-Scale Weak Supervision |
113,021 | -54 | +485 | +2,218 | +5,763 | -2,026 | 0 | 0.7x, slowing | |
| 47607 |
FluentCleaner is the transparent, community-powered CCleaner alternative for Windows. |
7,356 | +70 | +312 | +865 | +2,041 | -2,030 | 0 | 0.5x, slowing | |
| 47608 |
Simple, unified interface to multiple Generative AI providers |
16,403 | +1 | +11 | +65 | +354 | -2,031 | 0 | 0.1x, slowing | |
| 47609 |
Open-source foundation of ToolJet AI - the enterprise app generation platform for internal tools, dashboards, business applications, workflows and AI agents. Build visually, from a prompt, or from Claude Code, Codex and Cursor over MCP 🚀 |
41,252 | +6 | +28 | +182 | +805 | -2,033 | 0 | 0.3x, slowing | |
| 47610 |
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one |
96,746 | +6 | +79 | +558 | +1,821 | -2,034 | 0 | 0.5x, slowing | |
| 47611 |
花笺,轻量优雅的跨平台桌面便签工具,支持 Markdown 编辑与预览 |
5,638 | +3 | +22 | +185 | +872 | -2,037 | 0 | 0.3x, slowing | |
| 47612 |
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents |
2,646 | +6 | +15 | +159 | +298 | -2,037 | 0 | Under 180 days | |
| 47613 |
The authentication glue you need. |
26,380 | +4 | +67 | +392 | +1,471 | -2,039 | 0 | 0.4x, slowing | |
| 47614 |
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. |
3,345 | -1 | +10 | +54 | +276 | -2,041 | 0 | 0.1x, slowing | |
| 47615 |
A fully-featured team and group chat application that you can easily selfhost. |
2,982 | +2 | +44 | +147 | +464 | -2,042 | 0 | 0.2x, slowing | |
| 47616 |
Multi-account API gateway for Grok Build, Grok Web, and Grok Console |
7,907 | +1 | +10 | +114 | +545 | -2,053 | 0 | 0.2x, slowing | |
| 47617 |
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills. |
32,389 | +13 | +122 | +707 | +2,065 | -2,055 | 0 | 0.5x, slowing | |
| 47618 |
The agent engineering platform. |
149,860 | +25 | +470 | +1,918 | +5,843 | -2,058 | 0 | 0.7x, slowing | |
| 47619 |
Huashu Design 3.0 · 在 agent 里打一句话,拿回能交付的设计:网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent |
29,820 | +45 | +520 | +4,417 | +6,668 | -2,058 | 0 | 0.8x, slowing | |
| 47620 |
A contact solver for physics-based simulations involving 👚 shells, 🪵 solids, 🪢 rods, 🧱 rigid bodies and ⏳ sand. |
4,613 | +1 | +11 | +57 | +200 | -2,059 | 0 | 0.1x, slowing | |
| 47621 |
npx ccusage |
19,496 | +20 | +86 | +451 | +1,539 | -2,073 | 0 | 0.4x, slowing | |
| 47622 |
Make any agent harness multimodal-native. |
3,210 | 0 | +8 | +83 | +558 | -2,078 | 0 | Under 180 days | |
| 47623 |
Learn AI Engineering! Learn it. Build it. Ship it for others. |
79,513 | +135 | +988 | +8,155 | +32,620 | -2,079 | 0 | 0.9x, slowing | |
| 47624 |
An Obsidian plugin that embeds Claude Code, Codex and other agents as an AI collaborator in your vault. |
16,028 | +5 | +50 | +330 | +1,274 | -2,085 | 0 | 0.4x, slowing | |
| 47625 |
The open-source AI workbench for scientific research |
4,395 | +1 | +24 | +276 | +1,146 | -2,087 | 0 | Under 180 days | |
| 47626 |
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP. |
8,180 | +9 | +59 | +295 | +2,102 | -2,090 | 0 | 0.5x, slowing | |
| 47627 |
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support. |
6,220 | +25 | +151 | +321 | +804 | -2,103 | 0 | 0.3x, slowing | |
| 47628 |
Beautiful, AI-native markdown IDE and LLM wiki |
4,866 | +4 | +34 | +236 | +1,367 | -2,110 | 0 | Under 180 days | |
| 47629 |
Your agent team, in one group chat. |
18,297 | +6 | +130 | +283 | +1,074 | -2,115 | 0 | 0.3x, slowing | |
| 47630 |
No description |
3,867 | 0 | -5 | -5 | -3 | -2,124 | 0 | -0.0x, slowing | |
| 47631 |
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] |
63,502 | +35 | +357 | +1,990 | +6,992 | -2,130 | 0 | 0.8x, slowing | |
| 47632 |
Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw |
5,522 | +7 | +43 | +260 | +1,680 | -2,133 | 0 | Under 180 days | |
| 47633 |
Standalone iOS app to spoof GPS location without jailbreak. Includes Shadowrocket/Surge/Loon/QX/Stash module. |
4,620 | +2 | +18 | +128 | +1,226 | -2,135 | 0 | Under 180 days | |
| 47634 |
Build AI Agents, Visually |
55,575 | -2 | +7 | +117 | +491 | -2,142 | 0 | 0.2x, slowing | |
| 47635 |
No description |
3,014 | -1 | -1 | +7 | +425 | -2,142 | 0 | 0.2x, slowing | |
| 47636 |
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities |
10,355 | +8 | +69 | +298 | +1,115 | -2,146 | 0 | 0.3x, slowing | |
| 47637 |
The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps. |
2,565 | 0 | +2 | +49 | +144 | -2,150 | 0 | 0.1x, slowing | |
| 47638 |
TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification. |
2,849 | +1 | +4 | +69 | +343 | -2,154 | 0 | Under 180 days | |
| 47639 |
An AI Hedge Fund Team |
64,748 | +10 | +107 | +701 | +2,111 | -2,158 | 0 | 0.5x, slowing | |
| 47640 |
Gen1Recomp - A native Lua / LÖVE2D recreation of Gen 1, 2, and 3 Poke |
4,184 | -1 | +41 | +209 | +996 | -2,172 | 0 | Under 180 days | |
| 47641 |
A powerful, all-in-one Discord assistant built for every server. |
9,665 | +12 | +132 | +637 | +2,988 | -2,185 | 0 | 0.6x, slowing | |
| 47642 |
Open-source live-chat, email support, omni-channel desk. An alternative to Intercom, Zendesk, Salesforce Service Cloud etc. 🔥💬 |
40,126 | +49 | +434 | +2,177 | +4,248 | -2,191 | 1 | 0.7x, slowing | |
| 47643 |
better agentic engineering |
4,406 | +2 | +9 | +66 | +810 | -2,193 | 0 | 0.3x, slowing | |
| 47644 |
Comet: agent skill harness for turning ideas into evaluated workflows |
3,306 | 0 | +12 | +105 | +544 | -2,198 | 0 | 0.2x, slowing | |
| 47645 |
原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复 |
23,376 | +16 | +86 | +466 | +1,408 | -2,200 | 0 | 0.4x, slowing | |
| 47646 |
Agent Skills for Google products and technologies |
24,433 | +22 | +451 | +3,039 | +5,987 | -2,200 | 0 | 0.7x, slowing | |
| 47647 |
张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。 |
10,799 | +5 | +47 | +268 | +731 | -2,232 | 0 | 0.2x, slowing | |
| 47648 |
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. |
161,443 | +46 | +432 | +2,681 | +9,231 | -2,235 | 0 | 0.8x, slowing | |
| 47649 |
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress |
29,244 | +6 | +69 | +640 | +2,017 | -2,247 | 0 | 0.5x, slowing | |
| 47650 |
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step |
108,623 | +32 | +355 | +1,825 | +5,956 | -2,248 | 0 | 0.7x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.