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 49 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 501 |
MiMo Code: Where Models and Agents Co-Evolve |
13,726 | +1 | +53 | +316 | -390 | 41 | 0.4x, slowing | |
| 502 |
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all |
91,763 | +11 | +175 | +895 | -389 | 113 | 0.7x, slowing | |
| 503 |
Experimental DLSS Multi Frame Generation controls for any supported MFG title on RTX 40 series GPUs |
1,714 | +5 | +241 | +648 | -389 | 42 | Under 60 days | |
| 504 |
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG. |
3,788 | +3 | +84 | +358 | -388 | 51 | 0.5x, slowing | |
| 505 |
GoogleTest - Google Testing and Mocking Framework |
39,663 | 0 | +20 | +138 | -387 | 0 | 0.3x, slowing | |
| 506 |
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more. |
36,384 | +15 | +375 | +1,604 | -385 | 205 | 0.8x, slowing | |
| 507 |
Show usage stats for OpenAI Codex and Claude Code, without having to login. |
22,821 | +13 | +165 | +962 | -385 | 162 | 0.7x, slowing | |
| 508 |
No description |
1,347 | +1 | +15 | +471 | -385 | 0 | Under 60 days | |
| 509 |
A persistent workspace for development work that self-improves and continues beyond one session. |
4,579 | +2 | +81 | +440 | -384 | 34 | 0.5x, slowing | |
| 510 |
No description |
1,205 | +1 | +4 | +170 | -384 | 0 | 0.3x, slowing | |
| 511 |
The coding intelligence and skills for Hermes Agent ⚚ just install once. then type 'dag-ulw' to be graph engineering master. |
4,264 | +30 | +823 | +1,308 | -383 | 358 | 0.8x, slowing | |
| 512 |
A fork of gym-retro with additional games, emulators and supported platforms |
1,100 | 0 | +5 | +20 | -377 | 0 | 0.1x, slowing | |
| 513 |
The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS |
11,178 | +3 | +38 | +349 | -377 | 32 | 0.5x, slowing | |
| 514 |
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin. |
7,017 | 0 | +267 | +836 | -377 | 0 | 0.7x, slowing | |
| 515 |
Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns |
5,701 | +2 | +82 | +750 | -376 | 22 | 0.7x, slowing | |
| 516 |
A self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health. |
3,959 | +4 | +69 | +343 | -375 | 47 | 0.5x, slowing | |
| 517 |
A Swift library for reading, writing, and manipulating Xcode's JSON-based project.xcproj format. |
515 | 0 | +10 | +65 | -375 | 10 | Under 60 days | |
| 518 |
Components for making the Open Task Light |
1,093 | 0 | +1 | +31 | -374 | 0 | 0.1x, slowing | |
| 519 |
由夜安团队研发的AI Agent渗透测试平台，引入分形覆叠的概念，强调自监督，自循环，自进化（分形）首创寻宝机制、三段式上升结构（覆叠），此项目主要探索在可控环境（CTF）下的能力 |
690 | -1 | +27 | +152 | -374 | 0 | Under 60 days | |
| 520 |
Python scraper based on AI |
32,242 | +13 | +253 | +991 | -372 | 60 | 0.7x, slowing | |
| 521 |
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 50 other agents. |
6,276 | +3 | +73 | +322 | -372 | 32 | 0.5x, slowing | |
| 522 |
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included. |
692 | 0 | +6 | +28 | -372 | 0 | 0.1x, slowing | |
| 523 |
Stremio - Freedom to Stream |
14,804 | +3 | +107 | +888 | -370 | 29 | 0.7x, slowing | |
| 524 |
Move AI conversations between ChatGPT, Claude, Gemini, and DeepSeek with a local-first, open conversation format—no servers, no tracking. |
625 | 0 | 0 | +122 | -369 | 0 | 0.2x, slowing | |
| 525 |
Curated list of LLM-driven trading agents, MCP servers, and agent skills for market research, strategy, and execution. |
928 | +2 | +26 | +79 | -368 | 16 | 0.2x, slowing | |
| 526 |
Fast, scriptable CLI for the App Store Connect API. Automate TestFlight, builds, submissions, signing, analytics, screenshots, subscriptions, and more |
8,050 | +5 | +62 | +697 | -367 | 126 | 0.7x, slowing | |
| 527 |
Open-Box 一体化透明代理：OpenWrt / Debian / Ubuntu / Docker；自有程序闭源，第三方组件遵守原许可。 |
2,342 | +6 | +109 | +968 | -367 | 55 | 0.7x, slowing | |
| 528 |
Smart PVR for newsgroup and bittorrent users. |
17,435 | +5 | +113 | +916 | -366 | 42 | 0.7x, slowing | |
| 529 |
Makepad is a creative software development platform for Rust that compiles to wasm/webGL, osx/metal, windows/dx11 linux/opengl |
7,221 | 0 | +24 | +142 | -362 | 16 | 0.3x, slowing | |
| 530 |
A calm menu bar, done the native way. Hides the icons you don't need until you do. |
930 | +1 | +43 | +276 | -361 | 50 | 0.4x, slowing | |
| 531 |
AI Coding 福利站导航：免费白嫖 Claude Code / Codex 的中转站与公益站合集，含额度、模型、价格自动更新与一键配置脚本 |
1,178 | +2 | +36 | +391 | -361 | 12 | 0.5x, slowing | |
| 532 |
1207 public resources for Jev, TypeSafe AI's System One decision model, indexed by decision pattern. Source citations, dated link checks and scheduled call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema and platform compatibility. |
594 | +1 | +2 | +111 | -361 | 8 | Under 60 days | |
| 533 |
AI Agent 驱动的开源可自部署视频工作台：将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿，支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production |
5,745 | +17 | +143 | +577 | -360 | 220 | 0.6x, slowing | |
| 534 |
An agent skill for building premium, immersive, scroll-driven websites. Works with Codex, Claude Code, and other coding agents. Also available as a Claude Code plugin. |
4,062 | +9 | +357 | +1,277 | -360 | 110 | 0.8x, slowing | |
| 535 |
Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup. |
17,185 | 0 | +62 | +368 | -358 | 28 | 0.5x, slowing | |
| 536 |
Spectrum UI ⭐ is a collection of re-usable components built using Aceternity UI Magic UI and ShadCN UI that you can copy and paste into your apps. |
1,507 | 0 | +7 | +58 | -357 | 8 | 0.1x, slowing | |
| 537 |
🎓 Path to a free self-taught education in Electrical Engineering |
517 | 0 | +13 | +75 | -357 | 10 | Under 60 days | |
| 538 |
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI |
5,506 | +9 | +62 | +250 | -355 | 72 | 0.4x, slowing | |
| 539 |
Daily-updated Top 100 Agent Skills rankings — installs, growth, and social buzz aggregated from skills.sh, ClawHub, Tencent SkillHub, GitHub, X and 10+ communities. Open data (CSV). |
666 | +1 | +15 | +64 | -355 | 24 | 0.2x, slowing | |
| 540 |
Memory that AI Agents Love! |
2,342 | 0 | +9 | +83 | -354 | 0 | 0.2x, slowing | |
| 541 |
Canonical source and governance toolkit for Zhijian AI public Agent Skills |
784 | 0 | +1 | +12 | -354 | 0 | 0.0x, slowing | |
| 542 |
Your Jellyfin or Plex library as a walkable 1990s video rental store, self-hosted |
942 | 0 | +9 | +53 | -354 | 0 | 0.1x, slowing | |
| 543 |
eBPF-based Networking, Security, and Observability |
25,716 | +3 | +32 | +190 | -352 | 42 | 0.4x, slowing | |
| 544 |
Web UI for the pi coding agent |
7,809 | +11 | +282 | +1,015 | -352 | 148 | 0.7x, slowing | |
| 545 |
智能求职 Agent（source-available，PolyForm 非商业许可；商业使用需另行书面授权） |
1,352 | +5 | +63 | +236 | -352 | 90 | 0.4x, slowing | |
| 546 |
Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins. |
869 | +5 | +25 | +149 | -352 | 48 | 0.3x, slowing | |
| 547 |
Open-source inference server and production cluster for all the models your agent needs. |
3,450 | +2 | +35 | +131 | -351 | 16 | 0.3x, slowing | |
| 548 |
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition. |
2,109 | +1 | +69 | +213 | -351 | 11 | 0.4x, slowing | |
| 549 |
🔬 Harness Vibe Research with Self-evolving AI Scientists |
4,917 | 0 | +14 | +83 | -350 | 0 | 0.2x, slowing | |
| 550 |
Modular SenseNova skills for building AI-powered office assistants and productivity workflows |
5,925 | +5 | +138 | +246 | -350 | 58 | 0.4x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.