Repositories taking off
?
- 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 modeled on trendshift.io: 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.
- 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.
Updated 27 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 1 |
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. |
89,313 | +455 | +3,874 | +17,832 | -34,343 | 387 | 0.3x, slowing | |
| 2 |
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe. |
60,127 | +339 | +2,159 | +17,225 | -19,864 | 197 | 0.5x, slowing | |
| 3 |
A skill to stop your coding agent from burying the answer. ADHD-friendly output. |
58,751 | +123 | +1,071 | +7,832 | -18,611 | 104 | 0.3x, slowing | |
| 4 |
Fastest and cheapest web agent |
23,653 | +39 | +450 | +3,527 | -16,545 | 12 | Under 60 days | |
| 5 |
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click |
41,454 | +67 | +454 | +2,540 | -15,546 | 90 | 0.1x, slowing | |
| 6 |
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request. |
34,324 | +100 | +929 | +9,611 | -15,040 | 61 | Under 60 days | |
| 7 |
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible. |
48,279 | +62 | +717 | +7,129 | -12,723 | 50 | 0.4x, slowing | |
| 8 |
DeepSeek Harness: Everything is a Plugin. |
261,646 | +868 | +8,329 | +26,738 | -11,559 | 600 | 0.7x, slowing | |
| 9 |
Prompt as Code | GPT Image 2 / 2.5 提示词与案例库，530+ 个案例、20+ 套工业级模板与可复用 Skills，新增 2.5 同提示词对比专区，附完整提示词与生成记录，持续更新。 |
35,015 | +23 | +343 | +1,630 | -9,917 | 22 | 0.1x, slowing | |
| 10 |
Beautiful, Modern & Opinionated Linux |
45,704 | +68 | +623 | +2,847 | -8,360 | 46 | 0.3x, slowing | |
| 11 |
Agent Executor (AX) is Google's open agentic orchestration runtime |
14,085 | +23 | +150 | +2,520 | -7,089 | 23 | 0.3x, slowing | |
| 12 |
Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts. |
9,754 | +47 | +281 | +1,576 | -6,583 | 51 | Under 60 days | |
| 13 |
Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota. |
15,006 | +59 | +467 | +3,511 | -6,489 | 66 | 0.4x, slowing | |
| 14 |
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views. |
25,670 | +221 | +2,197 | +9,778 | -6,052 | 119 | 0.6x, slowing | |
| 15 |
like netcat, but over Tailscale's data plane, without Tailscale's control plane |
8,477 | +10 | +77 | +778 | -5,979 | 29 | 0.1x, slowing | |
| 16 |
World's first open-source enterprise world model. |
8,541 | +17 | +125 | +1,033 | -5,927 | 27 | 0.1x, slowing | |
| 17 |
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. |
7,766 | +8 | +83 | +960 | -5,825 | 18 | Under 60 days | |
| 18 |
🧠 Train a 64M-parameter LLM from scratch in just 2h! |
64,418 | +40 | +486 | +1,981 | -5,679 | 27 | 0.3x, slowing | |
| 19 |
A Tiny biped duck robot 🦆 |
11,840 | +689 | +2,267 | +3,094 | -5,626 | 1,144 | 0.4x, slowing | |
| 20 |
Z.ai's coding agent harness. Powerful, intelligent, extensible. |
8,244 | +34 | +305 | +1,522 | -5,181 | 53 | Under 60 days | |
| 21 |
Agent skill that removes signs of AI-generated writing from text |
60,663 | +315 | +2,509 | +8,821 | -5,076 | 218 | 0.6x, slowing | |
| 22 |
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦 |
43,926 | +164 | +1,177 | +6,462 | -4,994 | 91 | 0.6x, slowing | |
| 23 |
Python tool for converting files and office documents to Markdown. |
192,217 | +201 | +1,338 | +5,811 | -4,957 | 147 | 0.5x, slowing | |
| 24 |
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark. |
14,836 | +258 | +2,208 | +4,876 | -4,946 | 99 | 0.5x, slowing | |
| 25 |
The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具：先看懂对方再回复，发不发由你。 |
8,106 | +51 | +220 | +1,646 | -4,797 | 26 | Under 60 days | |
| 26 |
Create polished demo videos without editing skills. Mac/Windows/Linux |
35,225 | +101 | +827 | +4,045 | -4,664 | 61 | 0.5x, slowing | |
| 27 |
Run a virtual iPhone on an Apple Silicon Mac. |
16,012 | +26 | +349 | +1,670 | -4,653 | 4 | 0.3x, slowing | |
| 28 |
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own |
9,532 | +20 | +242 | +2,524 | -4,465 | 54 | Under 60 days | |
| 29 |
Advanced UX and interoperability extension for Wand (WeMod) app |
32,996 | +91 | +787 | +4,329 | -4,451 | 45 | 0.5x, slowing | |
| 30 |
AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js). |
5,669 | +6 | +48 | +389 | -4,308 | 5 | 0.1x, slowing | |
| 31 |
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently. |
14,769 | +18 | +202 | +1,062 | -4,208 | 3 | 0.2x, slowing | |
| 32 |
Tinycast — a tiny, fully native macOS launcher, hotkeys, and clipboard history. |
8,834 | +7 | +160 | +1,446 | -4,087 | 15 | 0.3x, slowing | |
| 33 |
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. |
35,446 | +118 | +825 | +5,436 | -3,993 | 274 | 0.6x, slowing | |
| 34 |
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins |
7,273 | +41 | +292 | +1,607 | -3,981 | 69 | 0.3x, slowing | |
| 35 |
The headless browser for AI agents and web scraping |
29,387 | +79 | +369 | +1,631 | -3,974 | 50 | 0.3x, slowing | |
| 36 |
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue) |
80,727 | +24 | +269 | +1,201 | -3,809 | 22 | 0.2x, slowing | |
| 37 |
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard. |
54,618 | +145 | +1,934 | +8,106 | -3,735 | 76 | 0.7x, slowing | |
| 38 |
Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust. |
4,249 | +1 | +18 | +97 | -3,707 | 0 | 0.0x, slowing | |
| 39 |
Make Every Team AI Native |
5,658 | +13 | +101 | +677 | -3,651 | 31 | 0.2x, slowing | |
| 40 |
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码 |
55,875 | +127 | +1,044 | +5,025 | -3,588 | 142 | 0.6x, slowing | |
| 41 |
Open source alternative to Semrush and Ahrefs |
24,991 | +151 | +944 | +3,972 | -3,573 | 99 | 0.5x, slowing | |
| 42 |
Removes 20+ patterns of AI slop from any piece of writing. |
12,829 | +41 | +290 | +1,586 | -3,573 | 25 | 0.3x, slowing | |
| 43 |
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验 |
6,981 | +32 | +277 | +1,703 | -3,563 | 49 | 0.3x, slowing | |
| 44 |
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent. |
9,572 | +56 | +406 | +2,350 | -3,492 | 111 | 0.4x, slowing | |
| 45 |
Codex登陆助手：安全地在本地导出您的已登录 ChatGPT 会话配置，生成符合 Codex 规范的 auth.json 本地备份文件。 |
19,748 | +63 | +557 | +3,160 | -3,477 | 40 | 0.5x, slowing | |
| 46 |
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change. |
5,592 | -1 | +10 | +438 | -3,451 | 0 | 0.1x, slowing | |
| 47 |
Turn your coding agents into research agents |
7,574 | +32 | +241 | +1,886 | -3,401 | 32 | 0.4x, slowing | |
| 48 |
Open-source 3D anatomy explorer: 2,234 selectable BodyParts3D meshes, system layers, search, and exploded views. |
4,358 | +12 | +77 | +476 | -3,397 | 0 | Under 60 days | |
| 49 |
OpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for everyone, forever free. |
20,871 | +21 | +532 | +1,708 | -3,396 | 11 | 0.3x, slowing | |
| 50 |
The agent that grows with you |
257,112 | +240 | +2,282 | +9,281 | -3,394 | 152 | 0.7x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 90 more tracked repositories are still loading their star history and will join the ranking once it is complete.