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 17 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 351 |
ServerKit is a lightweight, modern server control panel for managing web applications, databases, and services on your VPS or dedicated server. Built with Python/Flask backend and React frontend. |
1,790 | 0 | +21 | +138 | -573 | 8 | 0.2x, slowing | |
| 352 |
A macOS menu-bar app that dresses your windows in knitted borders. |
818 | +1 | +14 | +113 | -573 | 8 | Under 60 days | |
| 353 |
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta. |
5,503 | 0 | +16 | +123 | -572 | 0 | 0.2x, slowing | |
| 354 |
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion. |
4,137 | +1 | +132 | +460 | -572 | 24 | 0.4x, slowing | |
| 355 |
An open source AI-native agentic SOC platform |
1,179 | 0 | +1 | +104 | -571 | 0 | 0.2x, slowing | |
| 356 |
OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required. |
32,490 | +15 | +294 | +1,361 | -570 | 219 | 0.7x, slowing | |
| 357 |
Open-source desktop SQL workspace with 3 built-in database drivers and 24 shipped driver plugins, including SQL Server, DuckDB, ClickHouse and Redis. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN. |
5,292 | +5 | +56 | +259 | -568 | 56 | 0.3x, slowing | |
| 358 |
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. |
5,368 | +1 | +89 | +1,177 | -568 | 24 | 0.7x, slowing | |
| 359 |
A video game for AI agents. Created by Jarren Rocks |
840 | 0 | +12 | +127 | -567 | 8 | Under 60 days | |
| 360 |
Terminal interface to find, download, and stream movies, TV shows, and live TV using local media players. |
2,638 | +7 | +92 | +377 | -564 | 104 | 0.4x, slowing | |
| 361 |
MiniCPM5: SOTA on-device LLMs, small yet powerful. |
11,711 | +1 | +79 | +446 | -562 | 54 | 0.4x, slowing | |
| 362 |
A framework for building realtime voice AI agents 🤖🎙️📹 |
14,939 | +4 | +91 | +605 | -561 | 40 | 0.5x, slowing | |
| 363 |
Public repository for Agent Skills |
183,883 | +55 | +1,627 | +5,972 | -558 | 479 | 0.9x, slowing | |
| 364 |
No description |
10,598 | +23 | +418 | +1,389 | -558 | 254 | 0.7x, slowing | |
| 365 |
A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions. |
749 | 0 | +11 | +87 | -558 | 0 | Under 60 days | |
| 366 |
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. |
12,108 | +7 | +235 | +796 | -551 | 91 | 0.6x, slowing | |
| 367 |
TypeLLM: LLMs with type-safe generation |
972 | 0 | +9 | +201 | -550 | 0 | Under 60 days | |
| 368 |
The AI Org-OS — a collaborative platform for humans and agents. Explore: https://spaces.xyne.ai |
823 | 0 | +5 | +68 | -548 | 0 | 0.1x, slowing | |
| 369 |
Bonsai Demo |
3,446 | 0 | +34 | +324 | -547 | 14 | 0.4x, slowing | |
| 370 |
Puts DLSS 5 neural rendering into games that never shipped it, and brings the game's own DLSS up to date - super resolution, ray reconstruction, frame generation. Scans your library, picks one of eight routes, fetches every part from its publisher at run time, then says what happened. One exe, no admin; uninstall puts the game back. |
954 | 0 | +31 | +194 | -545 | 0 | Under 60 days | |
| 371 |
Open source Loom alternative. Beautiful, shareable screen recordings. |
23,812 | +19 | +361 | +1,010 | -544 | 268 | 0.7x, slowing | |
| 372 |
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface |
89,564 | +23 | +753 | +2,422 | -544 | 202 | 0.8x, slowing | |
| 373 |
PanWatch — AI stock monitoring for A-shares, HK & US markets, powered by TradingAgents. Portfolio insights, real-time alerts & automated reports.｜盯盘侠：覆盖 A股/港股/美股的 AI 盯盘、持仓分析、实时提醒与自动报告。 |
2,226 | +6 | +85 | +430 | -544 | 78 | 0.4x, slowing | |
| 374 |
A straightforward method for training your LLM, from downloading data to generating text. |
12,500 | -1 | +140 | +1,256 | -540 | 11 | 0.7x, slowing | |
| 375 |
Custom end4 |
3,583 | +4 | +143 | +425 | -538 | 54 | 0.4x, slowing | |
| 376 |
Automatically builds GenP executables from source |
4,454 | +6 | +128 | +822 | -537 | 138 | 0.6x, slowing | |
| 377 |
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 80+ installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語. |
2,286 | +3 | +123 | +854 | -537 | 32 | 0.6x, slowing | |
| 378 |
StarPie 现代化 Windows 鼠标轮盘手势系统 |
1,268 | +2 | +68 | +352 | -536 | 26 | 0.4x, slowing | |
| 379 |
Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer. |
2,508 | +5 | +66 | +299 | -535 | 56 | 0.4x, slowing | |
| 380 |
Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains. |
4,022 | 0 | +25 | +164 | -534 | 18 | 0.2x, slowing | |
| 381 |
DeepSeek Harness 可编辑设计系统：AI 生成、可视化编辑、模板市场与 PPT｜Native Design & PPT Studio for DeepSeek Harness. |
1,603 | +1 | +119 | +303 | -528 | 8 | 0.4x, slowing | |
| 382 |
A modern CLI tool for managing OpenFrame Kubernetes clusters and development workflows. Provides an interactive, user-friendly alternative to shell scripts with comprehensive cluster lifecycle management. |
877 | 0 | 0 | +157 | -526 | 0 | 0.2x, slowing | |
| 383 |
:scream: A curated list of amazingly awesome OSINT |
30,469 | +3 | +107 | +747 | -525 | 50 | 0.6x, slowing | |
| 384 |
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server. |
2,637 | +1 | +28 | +190 | -525 | 16 | 0.3x, slowing | |
| 385 |
人人都能用英语 |
39,270 | +6 | +204 | +998 | -524 | 90 | 0.7x, slowing | |
| 386 |
A game mod that uses NVIDIA AI to change lighting, detail and colour, with controls for strength and performance. |
849 | +1 | +19 | +152 | -524 | 16 | Under 60 days | |
| 387 |
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. |
176,620 | +241 | +8,420 | +31,025 | -523 | 995 | 1.0x, steady | |
| 388 |
Node.js & Bun bindings for Zed’s GPUI. Build memory efficient native apps with React or Solid.js |
2,810 | +3 | +182 | +487 | -522 | 98 | 0.5x, slowing | |
| 389 |
A book-in-progress about the Linux kernel and its insides. |
33,680 | 0 | +22 | +115 | -521 | 7 | 0.2x, slowing | |
| 390 |
If you want to become good at AI engineering & system design, join this newsletter 👇 |
29,462 | +2 | +34 | +523 | -521 | 48 | 0.5x, slowing | |
| 391 |
👩🚒 Good content deserves good paper. Layout rules and templates that let AI agents export PDF, PNG and editable PowerPoint. |
12,088 | +5 | +84 | +337 | -517 | 65 | 0.4x, slowing | |
| 392 |
Automated perps trader: Jev makes the call, Papertrade fills it at Hyperliquid mid. BTC and SOL on HyperEVM. |
838 | 0 | +8 | +144 | -517 | 0 | 0.2x, slowing | |
| 393 |
Isolated VM environment for running Claude Code and Codex |
799 | +1 | +11 | +120 | -516 | 16 | 0.2x, slowing | |
| 394 |
DLSS 5 Neural Rendering for Images & Video with Frame Generation, RTX Video Super Resolution, HDR, and Color Grading |
1,585 | 0 | +122 | +521 | -515 | 3 | Under 60 days | |
| 395 |
The agent IDE that builds itself |
4,612 | +3 | +127 | +687 | -514 | 34 | 0.6x, slowing | |
| 396 |
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music. |
1,370 | +1 | +49 | +401 | -512 | 13 | 0.4x, slowing | |
| 397 |
Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration. |
1,278 | +1 | +17 | +183 | -511 | 24 | 0.3x, slowing | |
| 398 |
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering. |
56,603 | +36 | +1,055 | +5,166 | -510 | 326 | 0.9x, slowing | |
| 399 |
Meta-Framework of Spatiotemporal Composability |
9,404 | +9 | +136 | +601 | -509 | 57 | 0.5x, slowing | |
| 400 |
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. |
84,439 | +8 | +298 | +1,650 | -509 | 130 | 0.8x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 597 more tracked repositories are still loading their star history and will join the ranking once it is complete.