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 42 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 751 |
MCP server integration for DaVinci Resolve Studio |
3,781 | +9 | +127 | +622 | -237 | 129 | 0.7x, slowing | |
| 752 |
A fully functional AI Agent desktop client that supports Webui access and can be creatively customized and expanded! |
2,247 | +1 | +14 | +85 | -237 | 16 | 0.3x, slowing | |
| 753 |
Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill. |
3,049 | +9 | +124 | +1,025 | -236 | 103 | 0.8x, slowing | |
| 754 |
Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus or Claude. |
4,508 | +6 | +89 | +334 | -236 | 69 | 0.6x, slowing | |
| 755 |
Every display control macOS hides, in one menu bar app: sharp HiDPI/Retina scaling (no more blurry or tiny text), DDC brightness and volume, Extra Brightness past 100%, presets, virtual displays. Free and open source, a no-cost alternative to BetterDisplay and Lunar. |
2,227 | +9 | +93 | +332 | -236 | 90 | 0.6x, slowing | |
| 756 |
WheelWizard, Retro Rewind Launcher |
880 | 0 | +19 | +96 | -235 | 0 | 0.3x, slowing | |
| 757 |
Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing. |
6,280 | +3 | +55 | +281 | -234 | 15 | 0.5x, slowing | |
| 758 |
Windows pod system for Linux |
2,118 | +3 | +10 | +66 | -234 | 24 | 0.2x, slowing | |
| 759 |
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density |
7,084 | +1 | +10 | +93 | -234 | 12 | 0.3x, slowing | |
| 760 |
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. |
60,129 | +20 | +255 | +1,193 | -233 | 253 | 0.8x, slowing | |
| 761 |
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs |
5,284 | 0 | +20 | +125 | -233 | 8 | 0.3x, slowing | |
| 762 |
Open-source SEO, GEO, and marketing skills for AI agents. |
4,064 | +2 | +104 | +214 | -232 | 8 | 0.5x, slowing | |
| 763 |
BookOrbit: Your Reading Space |
5,739 | +26 | +250 | +1,079 | -232 | 279 | 0.8x, slowing | |
| 764 |
The open-source docs framework for humans and agents. |
1,805 | +1 | +8 | +110 | -232 | 0 | 0.3x, slowing | |
| 765 |
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security |
11,212 | +6 | +80 | +406 | -232 | 82 | 0.6x, slowing | |
| 766 |
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter. |
92,229 | +29 | +324 | +1,560 | -231 | 339 | 0.9x, slowing | |
| 767 |
Tangle is a web app that allows the users to build and run Machine Learning pipelines without having to set up development environment. |
515 | 0 | 0 | +7 | -231 | 0 | 0.0x, slowing | |
| 768 |
DeepTeam is a framework to red team LLMs and AI agents. |
3,054 | +3 | +24 | +105 | -231 | 40 | 0.3x, slowing | |
| 769 |
Ministack: Free, open-source local AWS emulator - 60+ services, Terraform compatible, real databases. Free forever. MIT licensed. |
5,017 | +2 | +33 | +320 | -231 | 18 | 0.6x, slowing | |
| 770 |
Shadowrocket_Rules |
1,274 | +7 | +54 | +201 | -230 | 82 | 0.5x, slowing | |
| 771 |
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. Native Mac app source, CLI, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex. |
560 | +65 | +84 | +162 | -230 | 524 | 0.4x, slowing | |
| 772 |
A Collection of application ideas that can be used to improve your coding skills ❤. |
17,057 | +5 | +67 | +280 | -229 | 37 | 0.6x, slowing | |
| 773 |
Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe |
4,519 | +22 | +196 | +372 | -229 | 248 | 0.6x, slowing | |
| 774 |
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source. |
8,077 | +1 | +25 | +105 | -229 | 0 | 0.3x, slowing | |
| 775 |
📚 从零开始构建大模型 |
34,569 | +5 | +122 | +569 | -228 | 136 | 0.7x, slowing | |
| 776 |
Speakr is a personal, self-hosted web application designed for transcribing audio recordings |
4,122 | +4 | +17 | +118 | -228 | 32 | 0.3x, slowing | |
| 777 |
SSH workspace, SFTP, and terminals in one |
6,816 | +6 | +143 | +580 | -228 | 102 | 0.7x, slowing | |
| 778 |
一个基于 Cloudflare Workers + D1 + Durable Objects 的免费多服务器监控探针系统，支持实时监控、离线告警，到期通知，历史数据查看、延迟追踪、地图展示等功能。兼容主流Linux系统，Alpine Linux，OpenWrt，macOS，群晖 DSM、飞牛 fnOS、Windows系统。 |
2,735 | +8 | +157 | +501 | -228 | 150 | 0.7x, slowing | |
| 779 |
A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions. |
583 | +3 | +11 | +174 | -228 | 32 | Under 60 days | |
| 780 |
IPED Digital Forensic Tool. It is an open source software that can be used to process and analyze digital evidence, often seized at crime scenes by law enforcement or in a corporate investigation by private examiners. |
3,068 | +1 | +14 | +73 | -227 | 10 | 0.2x, slowing | |
| 781 |
Python - 100天从新手到大师 |
187,465 | +12 | +239 | +1,098 | -226 | 195 | 0.8x, slowing | |
| 782 |
simple terminal UI for git commands |
83,429 | +7 | +141 | +844 | -226 | 118 | 0.8x, slowing | |
| 783 |
AI-native SwiftUI component library with full-stack recipes — connect via MCP for instant access. |
3,244 | 0 | +4 | +33 | -225 | 0 | 0.1x, slowing | |
| 784 |
Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT. |
1,236 | +3 | +166 | +481 | -225 | 19 | 0.7x, slowing | |
| 785 |
Job application tracker and AI-powered job search assistant. Helps job seekers manage their search journey with AI resume review, job matching, task logging, and application analytics, all while keeping your data private. |
1,457 | +1 | +26 | +137 | -224 | 20 | 0.4x, slowing | |
| 786 |
access to david ondrej's personal agent skills |
4,172 | +2 | +16 | +106 | -224 | 18 | 0.3x, slowing | |
| 787 |
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering. |
70,360 | +20 | +206 | +1,253 | -223 | 223 | 0.8x, slowing | |
| 788 |
Open-source e-reader firmware |
8,529 | +9 | +108 | +475 | -223 | 118 | 0.7x, slowing | |
| 789 |
Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools. |
551 | +3 | +11 | +161 | -223 | 24 | Under 60 days | |
| 790 |
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] |
9,899 | +5 | +62 | +309 | -222 | 74 | 0.6x, slowing | |
| 791 |
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis. |
16,894 | +6 | +99 | +425 | -222 | 110 | 0.7x, slowing | |
| 792 |
A free, open-source bilingual 3D museum where young children and their grown-ups explore prehistoric animals across land, sea, and sky. |
1,169 | 0 | +21 | +117 | -222 | 16 | 0.3x, slowing | |
| 793 |
Diskless Kafka® on S3. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency. Multi-AZ Availability. |
10,921 | 0 | +8 | +83 | -221 | 0 | 0.3x, slowing | |
| 794 |
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization. |
39,047 | +3 | +81 | +225 | -221 | 49 | 0.5x, slowing | |
| 795 |
No description |
4,007 | +16 | +111 | +349 | -221 | 140 | 0.6x, slowing | |
| 796 |
Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables. |
2,654 | +7 | +127 | +541 | -221 | 78 | 0.7x, slowing | |
| 797 |
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents |
3,027 | +5 | +78 | +271 | -221 | 66 | 0.6x, slowing | |
| 798 |
Turn scattered health data into answers you can trace. Self-hosted AI health data engine for lab reports, wearables and genetics, with a built-in MCP server. Run it with Docker and one LLM key, or keep every model local on llama.cpp. |
1,393 | +1 | +8 | +55 | -220 | 18 | 0.2x, slowing | |
| 799 |
Curated coding interview preparation materials for busy software engineers |
143,158 | +2 | +108 | +515 | -218 | 42 | 0.7x, slowing | |
| 800 |
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。 |
3,801 | +8 | +68 | +257 | -218 | 72 | 0.5x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 602 more tracked repositories are still loading their star history and will join the ranking once it is complete.