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 16 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 151 |
OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn |
6,064 | +1 | +217 | +2,567 | -390 | 42 | 0.4x, slowing | |
| 152 |
The best file manager on Linux |
1,441 | 0 | +70 | +911 | -390 | 9 | 0.2x, slowing | |
| 153 |
Self-hosted AI workspace. |
94,459 | +5 | +495 | +7,265 | -389 | 56 | 0.6x, slowing | |
| 154 |
No description |
15,514 | +1 | +275 | +15,507all | -382 | 15 | 0.4x, slowing | |
| 155 |
A complete computer science study plan to become a software engineer. |
363,396 | 0 | +343 | +2,086 | -381 | 118 | 0.5x, slowing | |
| 156 |
Overdrive, a PS5 homebrew game store with 1,800+ games. |
1,343 | +1 | +417 | +1,340all | -381 | 40 | 0.5x, slowing | |
| 157 |
Git designed for AI agents. |
990 | +1 | +247 | +970all | -378 | 10 | Under 14 days | |
| 158 |
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot. |
4,215 | +12 | +718 | +3,764 | -369 | 308 | 0.7x, slowing | |
| 159 |
Hindsight: Agent Memory That Learns |
53,896 | +21 | +2,182 | +20,632 | -367 | 597 | 0.9x, slowing | |
| 160 |
Ultra-lightweight error tracking server compatible with Sentry SDKs |
789 | +1 | +77 | +631 | -362 | 26 | 0.2x, slowing | |
| 161 |
TokenSpeed is a speed-of-light LLM inference engine. |
2,791 | +2 | +74 | +616 | -362 | 72 | 0.2x, slowing | |
| 162 |
No description |
3,629 | +2 | +281 | +3,618all | -359 | 35 | 0.4x, slowing | |
| 163 |
Agent Substrate: the core system |
5,811 | +1 | +200 | +1,990 | -356 | 63 | 0.4x, slowing | |
| 164 |
DeepSeek Harness Tauri 桌面版 | Only 8mb installer, zero environment setup, preset plugins, Windows / macOS / Linux. |
3,280 | +2 | +131 | +1,016 | -355 | 65 | 0.3x, slowing | |
| 165 |
WinUI app for building smaller, customized Windows 11 images. |
21,155 | +4 | +430 | +1,593 | -352 | 120 | 0.5x, slowing | |
| 166 |
Evidence-grounded repository audit CLI - deterministic scanner, MCP server, live dashboard, and a GitHub Action that posts PR diffs. |
612 | 0 | +8 | +451 | -350 | 0 | 0.0x, slowing | |
| 167 |
Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender Foundation. |
32,371 | +6 | +665 | +3,013 | -345 | 110 | 0.7x, slowing | |
| 168 |
Agent Executor (AX) is Google's open agentic orchestration runtime |
14,092 | +2 | +111 | +2,178 | -345 | 82 | 0.2x, slowing | |
| 169 |
A free office suite where your document is inside the link and easy to share. There's no account and nothing saved unless you choose. |
492 | 0 | +43 | +492all | -345 | 23 | 0.1x, slowing | |
| 170 |
A Go-based OpenCode Zen / Zen Go API proxy with OpenAI & Anthropic API compatibility, key/proxy pooling, automatic routing, and WebUI. |
1,309 | 0 | +178 | +878 | -339 | 79 | 0.3x, slowing | |
| 171 |
Retarget human motion from video to an Adobe Mixamo-rigged 3D character. |
1,689 | +2 | +314 | +1,678 | -335 | 45 | 0.5x, slowing | |
| 172 |
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. |
25,721 | +22 | +1,792 | +9,488 | -334 | 325 | 0.8x, slowing | |
| 173 |
No description |
1,677 | +2 | +353 | +1,371 | -333 | 41 | 0.5x, slowing | |
| 174 |
Build with Vite. Deploy with Void. |
588 | 0 | +93 | +584 | -331 | 8 | 0.2x, slowing | |
| 175 |
Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry. |
1,386 | 0 | +44 | +1,386all | -331 | 14 | 0.1x, slowing | |
| 176 |
Native PC port (Linux/Windows) of inFAMOUS Second Son (PS4, CUSA00223) — in development, playable; runs your own game dump; no game or firmware files included. Motion sensor emulation. | Port nativo para PC de inFAMOUS Second Son (em desenvolvimento) — usa o seu próprio dump. |
909 | +1 | +242 | +904all | -331 | 41 | 0.4x, slowing | |
| 177 |
Run:ai is the AI workload orchestration platform for Kubernetes. This monorepo contains the control plane services, in-cluster Kubernetes operator/controllers, shared libraries and clients, the installer, and the local dev environment. |
653 | +1 | +106 | +623 | -329 | 70 | 0.2x, slowing | |
| 178 |
A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI. |
123,565 | +11 | +1,235 | +5,894 | -321 | 224 | 0.8x, slowing | |
| 179 |
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, or just a CPU. |
7,340 | 0 | +134 | +2,181 | -320 | 22 | 0.3x, slowing | |
| 180 |
给所有中国小学生打造的免费学习平台，从一年级到六年级所有的课本知识点全汇总。 |
1,076 | +1 | +131 | +733 | -317 | 75 | 0.3x, slowing | |
| 181 |
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8 |
709 | 0 | +124 | +709all | -317 | 32 | 0.3x, slowing | |
| 182 |
Maps and turn-by-turn navigation for Android without Google Play Services: the best of open map data, with Google lookups by choice. Runs on degoogled phones and can avoid Flock cameras |
2,159 | 0 | +91 | +1,732 | -316 | 8 | 0.2x, slowing | |
| 183 |
Reverse engineer anything with agents, from app behavior down to native binaries. |
992 | +3 | +181 | +989all | -316 | 53 | 0.4x, slowing | |
| 184 |
知らない分野を、原文にたどりつくまで芋づる式に掘る Claude Code のスキル |
1,297 | +1 | +431 | +1,295all | -316 | 40 | 0.6x, slowing | |
| 185 |
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux. |
5,367 | 0 | +88 | +1,176 | -315 | 17 | 0.2x, slowing | |
| 186 |
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. |
35,473 | +10 | +722 | +5,218 | -312 | 457 | 0.7x, slowing | |
| 187 |
Academic Research Skills for Claude Code: research → write → review → revise → finalize |
53,930 | +19 | +922 | +4,516 | -311 | 297 | 0.7x, slowing | |
| 188 |
Stretchtext replies for Claude Code: short by default, each phrase grows in place when you click it |
421 | 0 | +29 | +421all | -310 | 6 | Under 14 days | |
| 189 |
Fully automatic censorship removal for language models |
36,512 | +7 | +599 | +4,231 | -306 | 85 | 0.7x, slowing | |
| 190 |
Use all your internet connections at once on Windows, macOS, Linux and Android: per-connection load balancing over Wi-Fi, Ethernet, mobile data and phone tethers |
2,271 | +6 | +878 | +2,269all | -304 | 56 | 0.7x, slowing | |
| 191 |
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees. |
1,892 | +3 | +179 | +1,716 | -302 | 65 | 0.4x, slowing | |
| 192 |
Async Python client for collecting public data from X (Twitter) - search, profiles, threads, replies, and media. Built-in account rotation, adaptive rate limiting, and export to JSON/CSV/SQLite. |
650 | 0 | +8 | +650 | -302 | 8 | 0.0x, slowing | |
| 193 |
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input. |
33,055 | +57 | +4,528 | +32,791 | -299 | 808 | 0.9x, slowing | |
| 194 |
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. |
208,615 | 0 | +617 | +3,299 | -295 | 92 | 0.7x, slowing | |
| 195 |
Use an iPhone, iPad, or spare Mac as a true second display for your Mac without restrictions. |
5,905 | +1 | +130 | +1,100 | -295 | 19 | 0.3x, slowing | |
| 196 |
User-friendly AI Interface (Supports Ollama, OpenAI API, ...) |
156,776 | +6 | +613 | +4,126 | -289 | 93 | 0.7x, slowing | |
| 197 |
An ancient Chinese divine beast, now reincarnated as an enterprise-grade data analysis and VibeCoding assistant. |
569 | 0 | +6 | +511 | -288 | 0 | 0.0x, slowing | |
| 198 |
No description |
9,760 | +6 | +769 | +2,207 | -286 | 189 | 0.7x, slowing | |
| 199 |
🎮 An open-source game speed modifier. |
20,344 | +2 | +320 | +2,145 | -284 | 73 | 0.5x, slowing | |
| 200 |
Build a modern LLM from scratch. Every line commented. Explained like we are five. |
4,137 | 0 | +74 | +786 | -284 | 0 | 0.2x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.