GitHub repositories taking off today
Ranked by how many more stars each repo got today so far (since midnight US Pacific) than yesterday's pace would predict, lowest first. Star counts come from GitHub. Last updated 17 Nov 2026, 11:20 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: 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.
- Suspected
- Repositories with at least 50 stars are left out as likely bought stars when they have no detected programming language and got those stars within a day of being created; or got them within 14 days while having no watchers, at most 1 fork, no detected language or under 1 KB of code other than HTML and CSS, and either 5 KB or less of files or an owner that is a personal account with at most 1 follower. Repositories with no detected language are also left out when, at any age, they have 5 KB or less of files and got at least 90% of their stars on a single day that ended more than a day ago; or have 5 KB or less of files and belong to a personal account with no followers that was created at most an hour before the repository. Any repository with at least 50 stars is also left out when it belongs to a personal account with no followers and either is under 3 days old with no watchers and at least 5 forks, or is under 30 days old with at least half as many forks as stars and 128 KB or less of files while that account is under a year old; it stays out while that account has no followers. Any repository with at least 50 stars that is under 30 days old is also left out for good when at least 2 other repositories of the same name were created within an hour of it, all owned by personal accounts with no followers. Some repositories are also left out, or kept in, by hand after a review of the daily lists, whatever the rules above say. See them.
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 42051 |
Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust. |
626 | 0 | +42 | +285 | 0 | 0 | 0.0x, slowing | |
| 42052 |
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. |
3,481 | 0 | +28 | +216 | 0 | 7 | 0.0x, slowing | |
| 42053 |
Geometry-Aware Monocular RGB Planning |
143 | 0 | +2 | +137 | 0 | 0 | No data | |
| 42054 |
Occamy model repo |
556 | 0 | +26 | +255 | 0 | 0 | No data | |
| 42055 |
A video game for AI agents. Created by Jarren Rocks |
900 | 0 | +12 | +77 | 0 | 0 | 0.0x, slowing | |
| 42056 |
You plan the release, the factory builds it, you test it in staging. GitHub issues in, independently reviewed and merged pull requests out, all on Archon workflows. |
537 | 0 | +15 | +145 | 0 | 8 | 0.0x, slowing | |
| 42057 |
Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key. |
4,323 | 0 | +12 | +741 | 0 | 8 | 0.0x, slowing | |
| 42058 |
No description |
674 | 0 | 0 | 0 | 0 | 0 | No data | |
| 42059 |
养成类游戏英语学习 |
799 | 0 | 0 | +142 | 0 | 0 | No data | |
| 42060 |
An inference engine for one NVIDIA RTX card, built for a coding agent and its subagents, and a companion that listens, reads and draws: Qwen3.8 27B and 125B Flash-Next MoE, Qwen-Image-2.1, Qwen3-ASR on the CPU. OpenAI-compatible API and Playground in one binary. |
66 | 0 | +3 | +43 | 0 | 0 | 0.0x, slowing | |
| 42061 |
The fastest GUI file manager on Omarchy. |
1,309 | 0 | +148 | +489 | 0 | 0 | 0.0x, slowing | |
| 42062 |
SoniCloud Recorder SDK is an open-source reference project for integrating BLE recorder hardware across Android, iOS, HarmonyOS, Flutter, Windows, and macOS. It includes SDK examples, recording control, real-time audio, file transfer, offline transcription, protocol tools, and vendor adaptation support. |
2,562 | 0 | +2 | +19 | 0 | 8 | 0.0x, slowing | |
| 42063 |
Telegram Worker Proxy Core |
208 | 0 | +21 | +193 | 0 | 0 | 0.0x, slowing | |
| 42064 |
No description |
1,276 | +1 | +79 | +346 | 0 | 33 | 1.0x, steady | |
| 42065 |
UNIGIT public brand and ecosystem hub — AI should work for everyone. |
2,290 | 0 | 0 | +992 | 0 | 0 | No data | |
| 42066 |
Open Micro Duck for everyone |
287 | 0 | +12 | +92 | 0 | 8 | 0.0x, slowing | |
| 42067 |
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers |
158 | 0 | +1 | +154 | 0 | 0 | No data | |
| 42068 |
An agent-first linter for Tailwind design systems. Write design system rules that agents can verify. |
3,366 | 0 | +19 | +148 | 0 | 0 | 0.0x, slowing | |
| 42069 |
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses |
3,683 | 0 | +22 | +195 | 0 | 0 | 0.0x, slowing | |
| 42070 |
A curated list of open-source AI agent platforms: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents, with licenses. |
509 | 0 | +4 | +16 | 0 | 0 | No data | |
| 42071 |
向顶会优秀论文学科研|Oral Paper Skill — 从 883 篇 Oral 论文摘要中“蒸馏”共通做法,用于论文对照改进与学习复盘 · Skill + prompt pack (CN/EN). Learn from 883 Oral paper abstracts to improve your research and writing. |
592 | 0 | +16 | +169 | 0 | 0 | 0.0x, slowing | |
| 42072 |
Companion repository for “In-Context Learning for Robots: Methods and Applications” — methods, datasets, and benchmarks organized by taxonomy and release date. |
230 | 0 | +3 | +137 | 0 | 0 | 0.0x, slowing | |
| 42073 |
DLSS Multi Frame Generation beyond RTX 50 — unlocks 3x/4x/6x on RTX 40, brings DLSS-G and XMX frame generation to RTX 20/30 (experimental), and XeMFG on RTX 20, 30, 40 and 50 cards |
1,052 | 0 | +16 | +114 | 0 | 0 | No data | |
| 42074 |
Canvix — Free & open-source graphic design tool. A community-built Canva alternative with a drag-and-drop editor, templates, shapes, text, images & one-click export. Works on desktop, tablet & mobile. |
214 | 0 | +28 | +210 | 0 | 0 | 0.0x, slowing | |
| 42075 |
DeepSeek Harness 启动器:启动项与多实例,版本、插件、整合包、MCP 和技能管理。A DeepSeek Harness launcher: launch entries, multiple instances, versions, plugins, modpacks, MCP and skills. |
780 | 0 | +1 | +73 | 0 | 0 | No data | |
| 42076 |
Take a photo of real objects, and paste them in Blender |
1,459 | 0 | +19 | +614 | 0 | 0 | No data | |
| 42077 |
Orbit is a native desktop workbench for the pi coding agent — a chat-style GUI rendered entirely in Rust on GPUI, the GPU-accelerated UI framework Zed is built on. It speaks the pi CLI's RPC protocol directly over stdio: no browser, no webview, no Node. |
158 | 0 | +13 | +110 | 0 | 24 | 0.0x, slowing | |
| 42078 |
Open-source, bring-your-own-key (BYOK) multi-model AI chat client for iOS, Android and the web. One LLM client for OpenAI, Anthropic, Google Gemini, OpenRouter, DeepSeek and ten more providers, plus any OpenAI-, Anthropic- or Gemini-compatible endpoint — Ollama, LM Studio, llama.cpp, vLLM. Local-first, self-hostable, no account. AGPL-3.0. |
565 | 0 | +6 | +26 | 0 | 8 | 0.0x, slowing | |
| 42079 |
用Go语言写的腾讯 CodeBuddy 账号池Cli/Web管理控制台 + OpenAI 兼容反代网关 |
448 | 0 | +14 | +143 | 0 | 0 | 0.0x, slowing | |
| 42080 |
Open Duet card feed: agents finish work, Magnus decides with one click |
513 | 0 | +3 | +105 | 0 | 0 | No data | |
| 42081 |
基于 Cloudflare WARP / MASQUE 的可视化注册、配置生成与多客户端转换工具。 生成、Clash/Mihomo 智能分流、Shadowrocket、sing-box、本地 VLESS 桥接,以及可选的 WARP 出口检测。 |
1,569 | 0 | +8 | +60 | 0 | 0 | 0.0x, slowing | |
| 42082 |
Make any website readable by AI agents. Score a site 0-100, generate a Markdown twin of every page plus robots.txt, llms.txt and sitemap.xml, and serve the twin at the same URL. Framework-agnostic, on npm. |
433 | 0 | +432 | +433 | 0 | 0 | 0.0x, slowing | |
| 42083 |
知屿 Zhiyu:开源个人数字资产工作空间,连接文档、账号、服务与服务器,支持本地加密管理、AI 助手和用量监控。 |
116 | 0 | +9 | +89 | 0 | 0 | 0.0x, slowing | |
| 42084 |
No description |
3,055 | 0 | +4 | +92 | 0 | 0 | No data | |
| 42085 |
MapAdKiller - 高德/百度/腾讯地图去广告 + 高德首页/我的页 UI 自定义 |
81 | 0 | +8 | +59 | 0 | 18 | 0.0x, slowing | |
| 42086 |
No description |
1,915 | 0 | 0 | +463 | 0 | 0 | No data | |
| 42087 |
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry. |
253 | 0 | +11 | +236 | 0 | 8 | 0.0x, slowing | |
| 42088 |
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness. |
1,706 | 0 | +6 | +27 | 0 | 8 | 0.0x, slowing | |
| 42089 |
Qwen3.8-Flash-Next on ONE DGX Spark (TP=1) |
640 | 0 | +8 | +40 | 0 | 0 | 0.0x, slowing | |
| 42090 |
Choose, test and move an iPhone’s reported location. |
1,203 | 0 | +8 | +80 | 0 | 16 | 0.0x, slowing | |
| 42091 |
Remove recognizable AI writing patterns without flattening the writer's voice. |
141 | 0 | +10 | +64 | 0 | 8 | 0.0x, slowing | |
| 42092 |
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP. |
454 | 0 | +301 | +301 | 0 | 0 | No data | |
| 42093 |
Lightweight CLI for web project deployment. Deploy SPAs, Docker, and Systemd service using a single Go binary, with support for GitHub Releases and offline bundles. |
38 | 0 | +10 | +35 | 0 | 0 | No data | |
| 42094 |
Browser extension to hide tests when reviewing PRs on Github |
118 | 0 | +4 | +60 | 0 | 0 | No data | |
| 42095 |
Encoder-Free Unified Image and Video Understanding and Generation |
421 | 0 | +4 | +201 | 0 | 0 | 0.0x, slowing | |
| 42096 |
Personal AI agents / grok bot alternative / muse alternative / dots alternative / duet alternative |
290 | 0 | +27 | +113 | 0 | 7 | 0.0x, slowing | |
| 42097 |
纯 C# PP-OCRv6 推理库:多平台手写 Kernel / GEMM 等算子、超高性能、低内存需求、超高准确率。 自带托管 ONNX 解释器,不依赖 Paddle Inference、ONNX Runtime 或 OpenCV 原生库。 |
549 | 0 | +5 | +61 | 0 | 16 | 0.0x, slowing | |
| 42098 |
Experimental native PC port of Lost Odyssey using static recompilation. No game assets included. |
985 | 0 | +27 | +266 | 0 | 8 | 0.0x, slowing | |
| 42099 |
No description |
1,041 | 0 | +8 | +243 | 0 | 0 | No data | |
| 42100 |
Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux |
611 | 0 | +4 | +24 | 0 | 0 | No data |
Today counts stars since midnight US Pacific time, so it is a partial day.