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 5 Nov 2026, 12:20 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, under 3 days old, it has no watchers and at least 5 forks and belongs to a personal account with no followers; it stays out while that account has no followers. 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 |
|---|---|---|---|---|---|---|---|---|---|
| 9851 |
Native ARM64 port of OpenEmu for Apple Silicon MacBooks |
564 | 0 | +14 | +82 | -6 | 24 | 0.7x, slowing | |
| 9852 |
RDNA-native LLM inference engine in Rust. |
795 | 0 | +26 | +148 | -6 | 7 | 0.8x, slowing | |
| 9853 |
No description |
695 | 0 | +3 | +31 | -6 | 0 | 0.3x, slowing | |
| 9854 |
Codex2API 是一个基于 Go + Gin + React/Vite 的 Codex 反向代理与管理后台项目 |
2,341 | 0 | +13 | +100 | -6 | 12 | 0.7x, slowing | |
| 9855 |
AgentPilot: Better Next Moves for Your Agent. Get Things Done Faster. |
7,785 | 0 | +9 | +65 | -6 | 0 | 0.6x, slowing | |
| 9856 |
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。 |
3,851 | 0 | +10 | +53 | -6 | 8 | 0.6x, slowing | |
| 9857 |
One command. Your entire AI skill stack. Installed. |
6,987 | 0 | +4 | +69 | -6 | 16 | 0.4x, slowing | |
| 9858 |
🔮 An engineering framework to stop LLM hallucinations in Chinese astrology. / 给“赛博半仙”戴上紧箍咒：减少幻觉、固定排盘步骤的奇门遁甲与紫微斗数 AI skills。 |
1,567 | 0 | +33 | +183 | -6 | 0 | 0.8x, slowing | |
| 9859 |
Real-time observability of claude code sessions & multi-agents. |
715 | 0 | +3 | +24 | -6 | 0 | 0.3x, slowing | |
| 9860 |
AI writing skill that eliminates detectable AI patterns. Works with Claude Code, Codex, Cursor, Gemini CLI, and 8+ other agents. |
590 | 0 | +12 | +81 | -6 | 10 | 0.7x, slowing | |
| 9861 |
A benchmark built to evaluate and improve agent capabilities for supporting legal work. |
1,560 | 0 | +21 | +142 | -6 | 0 | 0.8x, slowing | |
| 9862 |
Before I go to bed, I tell my agents: good night, have fun |
4,257 | 0 | +16 | +97 | -6 | 0 | 0.7x, slowing | |
| 9863 |
AI Agent Deep Dive |
5,832 | 0 | -3 | +12 | -6 | 0 | -1.1x, slowing | |
| 9864 |
Runnable ClaudeCode source code |
3,329 | 0 | -2 | +20 | -6 | 0 | -0.6x, slowing | |
| 9865 |
~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server |
645 | 0 | -3 | +5 | -6 | 0 | -1.1x, slowing | |
| 9866 |
Smart, Fast & Lossless session compaction for Pi. No LLM calls - produces structured, transcript-preserving summaries using pure extraction and formatting. |
569 | 0 | +12 | +91 | -6 | 0 | 0.7x, slowing | |
| 9867 |
Isolated VM environment for running Claude Code and Codex |
806 | 0 | +2 | +48 | -6 | 0 | 0.3x, slowing | |
| 9868 |
童锦程视角 Skill — 用深情祖师爷的思维框架分析人际关系 |
2,976 | 0 | +17 | +209 | -6 | 8 | 0.7x, slowing | |
| 9869 |
Automated book download manager for Usenet. Monitor authors, search indexers, download via SABnzbd, and organize your library. The modern replacement for Readarr. |
549 | 0 | +6 | +57 | -6 | 8 | 0.5x, slowing | |
| 9870 |
An agent runtime and tool protocol for principled agent concurrency |
719 | +6 | +325 | +702 | -6 | 163 | 1.0x, steady | |
| 9871 |
No description |
1,520 | 0 | +18 | +105 | -6 | 0 | 0.8x, slowing | |
| 9872 |
🔱 Vedic/Jyotish AI analysis toolkit | 吠陀占星AI分析工具包——从排盘开始，到以后的长期追问。支持所有可以挂载Skill的平台。感谢大家的支持。 |
1,015 | 0 | +14 | +79 | -6 | 16 | 0.7x, slowing | |
| 9873 |
SQLite extension + bindings for Postgres NOTIFY/LISTEN semantics with durable queues, streams, pub/sub, and scheduler |
3,044 | 0 | 0 | +19 | -6 | 0 | 0.0x, slowing | |
| 9874 |
🚀你的私人数据分析助手。通过对话式交互，自动生成可视化报表与商业洞察，让数据决策变得像聊天一样简单。 🚀 Your personal data analysis assistant. Say goodbye to complex SQL and Excel formulas. An LLM-powered data analysis agent. Chat with your data to instantly generate visualizations and business insights. Making data-driven decisions has never been easier. |
2,627 | 0 | +3 | +47 | -6 | 0 | 0.3x, slowing | |
| 9875 |
Your personal web archiver. |
395 | 0 | +29 | +394 | -6 | 0 | 0.8x, slowing | |
| 9876 |
World2Agent(W2A) is an open protocol that standardizes how Al agents perceive the real world. |
1,122 | 0 | -6 | -3 | -6 | 0 | No data | |
| 9877 |
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week. |
2,004 | 0 | -3 | +12 | -6 | 0 | -1.1x, slowing | |
| 9878 |
A hardware-accelerated video editor built on Rust, Tauri v2, and React 19. Sub-10ms frame decoding, GPU-native rendering, and a frame-accurate timeline — all free and open source under MIT. |
3,350 | 0 | +5 | +56 | -6 | 8 | 0.5x, slowing | |
| 9879 |
中国软件著作权申请材料 生成器 Skills，本 Skills 通过阅读本地项目，自动生成全套 .docx 软著申请材料，全开源，无须再付费购买任何软著申请服务 |
6,248 | +5 | +95 | +497 | -6 | 164 | 0.9x, slowing | |
| 9880 |
Open-source cross-platform software KVM for sharing keyboard, mouse, and clipboard across Windows, macOS, and Linux on trusted LANs. |
731 | 0 | +3 | +31 | -6 | 16 | 0.3x, slowing | |
| 9881 |
Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generation, editable first cut on a real timeline. Local-first: projects, prompts, and keys stay on your machine. No account, no telemetry. |
629 | 0 | +9 | +79 | -6 | 8 | 0.6x, slowing | |
| 9882 |
Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations. |
1,383 | 0 | +25 | +117 | -6 | 16 | 0.8x, slowing | |
| 9883 |
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns. |
1,133 | 0 | +3 | +48 | -6 | 0 | 0.3x, slowing | |
| 9884 |
No description |
936 | 0 | +7 | +48 | -6 | 0 | 0.5x, slowing | |
| 9885 |
批量稳定注册 Grok 账号，支持 WebUI/GUI/CLI、多邮箱服务、多线程并发、账号级多协议代理池、grok2api 入池、SSO 风控筛查与CPA OIDC 凭证导出。 |
2,404 | 0 | +21 | +130 | -6 | 0 | 0.8x, slowing | |
| 9886 |
tiny-world-builder |
1,620 | 0 | +3 | +31 | -6 | 0 | 0.3x, slowing | |
| 9887 |
Headless MCP server for Android APK static analysis, built directly on jadx-core. No JADX GUI required. |
154 | 0 | +13 | +106 | -6 | 0 | 0.7x, slowing | |
| 9888 |
A high performance 3DGS renderer |
1,119 | 0 | +3 | +36 | -6 | 8 | 0.3x, slowing | |
| 9889 |
The Programming Language for Agents |
5,402 | 0 | +6 | +33 | -6 | 16 | 0.5x, slowing | |
| 9890 |
Single-host, read-only disk diagnostics TUI. |
542 | 0 | -1 | +21 | -6 | 0 | -0.2x, slowing | |
| 9891 |
Run Minecraft Bedrock for Windows seamlessly on Linux. |
1,174 | 0 | +31 | +194 | -6 | 6 | 0.8x, slowing | |
| 9892 |
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning. |
2,278 | 0 | +27 | +146 | -6 | 6 | 0.8x, slowing | |
| 9893 |
An enterprise AI workspace for model routing, multimodal chat, files, tools, billing, identity, and operations. |
1,626 | 0 | +11 | +107 | -6 | 0 | 0.7x, slowing | |
| 9894 |
Pure-Rust astronomical ephemeris for astrology — Vedic, Western, Chinese, and 9 world traditions |
882 | 0 | -3 | +3 | -6 | 0 | -1.1x, slowing | |
| 9895 |
A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously. |
1,140 | 0 | +4 | +44 | -6 | 0 | 0.4x, slowing | |
| 9896 |
The fast all-in-one Node.js toolkit |
4,432 | 0 | +6 | +78 | -6 | 8 | 0.5x, slowing | |
| 9897 |
Orca Agent — a DeepSeek-native terminal coding agent |
512 | 0 | -1 | +7 | -6 | 0 | -0.2x, slowing | |
| 9898 |
Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0 |
567 | 0 | +7 | +27 | -6 | 0 | 0.5x, slowing | |
| 9899 |
Free strategy scorecard for trading backtests. Detect overfitting, weak edge, drawdown risk, and random-timing luck from returns, equity curves, or trade logs. |
927 | 0 | -5 | -4 | -6 | 0 | -5.7x, slowing | |
| 9900 |
Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark. |
734 | 0 | +13 | +90 | -6 | 34 | 0.7x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.