GitHub repositories taking off in the last 7 days
Ranked by how many more stars each repo got in the last 7 days than its pace over the 7 days before would predict, lowest first. Star counts come from GitHub. Last updated 1 Nov 2026, 10:20 UTC.
?
- 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.
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 6051 |
Mermaid.js, but headless, in Rust. |
647 | 0 | +13 | +75 | -6 | 0 | 0.7x, slowing | |
| 6052 |
Native macOS SwiftUI app for managing multiple AI code agent skills |
592 | 0 | +2 | +25 | -6 | 0 | 0.3x, slowing | |
| 6053 |
sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRgv6ZD |
552 | 0 | +1 | +27 | -6 | 0 | 0.1x, slowing | |
| 6054 |
Bộ gõ tiếng Việt cho Linux mã nguồn mở, hướng đến trải nghiệm gõ không gạch chân mượt mà |
522 | 0 | +4 | +33 | -6 | 0 | 0.4x, slowing | |
| 6055 |
OpenAI-compatible proxy for ChatGPT Codex Responses API |
1,836 | 0 | +7 | +47 | -6 | 8 | 0.5x, slowing | |
| 6056 |
Always-on profiler for Rust designed for production |
600 | 0 | +9 | +79 | -6 | 0 | 0.6x, slowing | |
| 6057 |
Android BYOK LLM client with multi-provider access, agentic workflows, and remote device control. |
549 | 0 | +16 | +98 | -6 | 8 | 0.7x, slowing | |
| 6058 |
Debloat and harden Brave Browser on Linux, macOS, and Windows using Chromium enterprise policies. Curses TUI on Linux/macOS, native GUI on Windows. 79 policies, 6 presets, zero dependencies. |
810 | 0 | +23 | +104 | -6 | 0 | 0.8x, slowing | |
| 6059 |
Agent-native flight & hotel search and booking — MCP server, CLI, and Python/JS SDKs. Every airline in the world, major booking sites and OTAs, with per-flight reliability history. |
2,215 | 0 | +20 | +136 | -6 | 0 | 0.8x, slowing | |
| 6060 |
CubePlex is a cloud-native platform for managed agents in team workspaces — skills, shared memory, MCP tools, persistent sandboxes, governed access, and self-hosted deploy on Docker Compose or Kubernetes. |
574 | 0 | +16 | +98 | -6 | 8 | 0.7x, slowing | |
| 6061 |
通用高质量 Skills 合集🔥 |
3,089 | 0 | +38 | +169 | -6 | 0 | 0.9x, slowing | |
| 6062 |
Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views |
929 | 0 | +4 | +34 | -6 | 0 | 0.4x, slowing | |
| 6063 |
Orchestrate thousands of agents and harnesses as a graph programatically |
1,421 | 0 | 0 | +15 | -6 | 0 | 0.0x, slowing | |
| 6064 |
Vigolium - High-fidelity vulnerability scanner fusing agentic AI with native speed, modularity, and precision |
1,139 | 0 | +7 | +41 | -6 | 0 | 0.5x, slowing | |
| 6065 |
A clean, self-hosted web UI for managing your Traefik reverse proxy. |
1,656 | 0 | +4 | +37 | -6 | 8 | 0.4x, slowing | |
| 6066 |
基于 11 个内容洞见维度的自媒体创作 Skill，适用于各种智能体 给它一个主题，它给你一篇完整的文章、5 个备选标题、以及每张配图的生成 prompt。 |
811 | +1 | +6 | +34 | -6 | 8 | 0.5x, slowing | |
| 6067 |
The switch fell off https://citron-neo.org/ |
603 | 0 | +10 | +75 | -6 | 0 | 0.6x, slowing | |
| 6068 |
Private Inference Network on Idle Macs |
569 | 0 | +4 | +30 | -6 | 0 | 0.4x, slowing | |
| 6069 |
Mac app to review the code written by you or your agent with Claude in the loop. |
896 | 0 | +2 | +73 | -6 | 0 | 0.3x, slowing | |
| 6070 |
Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU |
8,502 | +5 | +118 | +606 | -6 | 28 | 1.0x, steady | |
| 6071 |
AI 解说大师 — Agent skill；封装 narrator-ai-cli 供 Claude/Codex 等工具调用 |
3,086 | +6 | +15 | +80 | -6 | 48 | 0.7x, slowing | |
| 6072 |
Finance terminal, in your terminal. |
2,603 | +2 | +67 | +294 | -6 | 28 | 0.9x, slowing | |
| 6073 |
A clean, minimal E-Reader experience |
882 | 0 | +24 | +148 | -6 | 0 | 0.8x, slowing | |
| 6074 |
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES. |
568 | 0 | +4 | +47 | -6 | 0 | 0.4x, slowing | |
| 6075 |
AI Agent Deep Dive |
5,835 | 0 | +2 | +15 | -6 | 0 | 0.3x, slowing | |
| 6076 |
A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability |
650 | 0 | +24 | +143 | -6 | 7 | 0.8x, slowing | |
| 6077 |
LLM speculative inference server for heterogeneous hardware & consumer GPUs |
2,969 | 0 | +14 | +86 | -6 | 0 | 0.7x, slowing | |
| 6078 |
A smashin' port for PC, Mac, and Linux! |
528 | 0 | +11 | +73 | -6 | 16 | 0.7x, slowing | |
| 6079 |
将Chunqiu Detector-Problem solution写进 README并对其维护修改跟进等，方便求助者查阅。 （内容来自探索发现并测试，部分摘录自检测源码) |
543 | 0 | +13 | +97 | -6 | 0 | 0.7x, slowing | |
| 6080 |
An open-weight 11B model series for long-form and real-time video understanding |
803 | 0 | +11 | +55 | -6 | 8 | 0.7x, slowing | |
| 6081 |
A cozy terminal clubhouse for computer people. Lofi, games, chat, artboard, and tech news, all via SSH. |
1,525 | 0 | +4 | +39 | -6 | 8 | 0.4x, slowing | |
| 6082 |
A feature-rich macOS terminal built to be pleasant, native, and lightweight |
511 | 0 | +4 | +28 | -6 | 0 | 0.4x, slowing | |
| 6083 |
A powerful browser extension that supercharges DeepSeek Chat with custom tooling, persistent memory, and seamless project scaffolding. Generate and download files, run Python in-browser, create PowerPoint and Excel documents, build multi-file projects as ZIP archives, and manage custom skills and characters. |
791 | 0 | +47 | +229 | -6 | 6 | 0.9x, slowing | |
| 6084 |
Official code for Meta-Harness (2603.28052) |
1,733 | 0 | +22 | +104 | -6 | 0 | 0.8x, slowing | |
| 6085 |
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp. |
3,487 | +1 | +53 | +899 | -6 | 0 | 0.9x, slowing | |
| 6086 |
中文手绘技术 PPT 整页图像生成 Skill | 21:9 封面 + 16:9 正文配图 | PNG 输出 |
1,499 | 0 | +8 | +53 | -6 | 0 | 0.6x, slowing | |
| 6087 |
Decentralized P2P mesh for autonomous AI agents — self-sovereign identity, peer-to-peer chat, and on-device AI that negotiates tasks on your behalf. No central server. |
3,052 | 0 | -5 | +4 | -6 | 0 | -5.7x, slowing | |
| 6088 |
Crabbox: warm a box, sync the diff, run the suite. |
1,513 | 0 | +12 | +76 | -6 | 0 | 0.7x, slowing | |
| 6089 |
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs |
542 | 0 | +11 | +243 | -6 | 0 | 0.6x, slowing | |
| 6090 |
nine one |
1,533 | 0 | +6 | +68 | -6 | 0 | 0.5x, slowing | |
| 6091 |
[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training |
844 | +1 | +4 | +44 | -6 | 8 | 0.4x, slowing | |
| 6092 |
Flutter 开发的酷狗音乐客户端 |
698 | 0 | +14 | +102 | -6 | 8 | 0.7x, slowing | |
| 6093 |
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning. |
2,259 | 0 | +28 | +141 | -6 | 7 | 0.8x, slowing | |
| 6094 |
本地优先的中文内容排版工具：把 Markdown 转成小红书图文卡片、公众号长文和可下载图片，并支持 Obsidian 工作流。 |
593 | 0 | +6 | +38 | -6 | 0 | 0.5x, slowing | |
| 6095 |
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex. |
3,859 | 0 | +31 | +173 | -6 | 7 | 0.8x, slowing | |
| 6096 |
Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees. An official project by the Open Design team. |
4,791 | 0 | +40 | +179 | -6 | 0 | 0.9x, slowing | |
| 6097 |
SCAN-Planner: Spatial Collision-Aware Local planning for Route-Guided Long-Range Quadruped Navigation |
608 | 0 | +10 | +61 | -6 | 0 | 0.6x, slowing | |
| 6098 |
A native recompilation of Skate 3 for Windows, Linux, and macOS. |
1,772 | 0 | +45 | +326 | -6 | 5 | 0.9x, slowing | |
| 6099 |
Desktop flight and marine radar: a real-time aircraft and marine vessel tracker powered by a Raspberry Pi and 4" round screen. |
666 | 0 | +6 | +48 | -6 | 0 | 0.5x, slowing | |
| 6100 |
vibe coding 的驾驶舱：左边文件，右边/下边终端，中间看清每一次改动。 / The cockpit for vibe coding: browse files on the left, command agents on the right, watch every change in between. |
1,066 | 0 | +11 | +52 | -6 | 0 | 0.6x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.