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. Star counts come from GitHub. Last updated 13 Nov 2026, 23:20 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. 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 |
|---|---|---|---|---|---|---|---|---|---|
| 37551 |
Watch your computer connect across the internet in real time. Discover the world behind your apps. |
1,608 | 0 | +9 | +41 | -1 | 0 | 0.0x, slowing | |
| 37552 |
Zero-copy, content-addressed Rust build cache for Rust, C/C++ and more. No copies, no wasted disk |
1,421 | +11 | +51 | +238 | -1 | 170 | 0.9x, slowing | |
| 37553 |
Free & fast alternative to Wispr Flow |
3,089 | +3 | +36 | +190 | -1 | 46 | 0.8x, slowing | |
| 37554 |
Astrid is a portable, capability-secure operating system for composable software. |
10,292 | 0 | +1 | +13 | -1 | 0 | 0.0x, slowing | |
| 37555 |
一句话：试错成本越来越高，提示词的重要性从来没有像今天这样大。Seedance 2.0 Storyboard Generator 开源剧情剧本Skill工具，帮佬友一键写好剧本 - 将小说/故事转化为多集视频。 为什么做这个？ 因为 seedance2 已经改变了一切，需要新的剧本剧情制作工具，更好的利用新AI的能力和更方便的制作短剧 |
2,852 | +4 | +65 | +265 | -1 | 39 | 0.8x, slowing | |
| 37556 |
Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Kremer. Compatible with Claude Code and OpenAI Codex. |
718 | 0 | +9 | +58 | -1 | 8 | 0.0x, slowing | |
| 37557 |
用于写NSFC本子的Agent Skills |
787 | +3 | +32 | +116 | -1 | 42 | 0.7x, slowing | |
| 37558 |
sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRgv6ZD |
565 | 0 | +4 | +27 | -1 | 0 | 0.0x, slowing | |
| 37559 |
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig |
8,224 | +1 | +18 | +121 | -1 | 20 | 0.5x, slowing | |
| 37560 |
Real-time animated line chart for React. |
1,018 | +1 | +17 | +53 | -1 | 16 | 0.5x, slowing | |
| 37561 |
A cross platform Audiobookshelf client for Android and iOS |
834 | 0 | +16 | +94 | -1 | 0 | 0.0x, slowing | |
| 37562 |
Local guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more |
160 | +2 | +28 | -25 | -1 | 34 | 0.8x, slowing | |
| 37563 |
GEO Optimizer, the open-source engine behind GeoReady (geoready.dev): audit whether ChatGPT, Perplexity, Gemini & Google AI Overviews cite your site. CLI, Python, MCP. |
1,321 | +2 | +30 | +243 | -1 | 26 | 0.8x, slowing | |
| 37564 |
vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm |
918 | +1 | +8 | +28 | -1 | 18 | 0.5x, slowing | |
| 37565 |
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree |
1,088 | 0 | +8 | +40 | -1 | 0 | 0.0x, slowing | |
| 37566 |
A lightweight, LXC-like container runtime for Android and Linux. Run full Linux distributions natively with zero performance penalty |
2,512 | +3 | +37 | +202 | -1 | 58 | 0.8x, slowing | |
| 37567 |
Command Your AI Agent Empire from the CEO Desk — A local-first AI agent office simulator that orchestrates CLI, OAuth, and API-connected agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, and more) as a virtual autonomous company. |
1,446 | 0 | +1 | +34 | -1 | 8 | 0.0x, slowing | |
| 37568 |
The agent control plane: run Claude Code, Codex and Gemini CLI agents in parallel with a shared task board, schedules and usage-limit recovery. Native iPhone, iPad and Mac apps plus a web dashboard. Self-host (Rust + SQLite, Tailscale remote access) or use amux Cloud. MIT + Commons Clause. |
559 | 0 | +5 | +28 | -1 | 0 | 0.0x, slowing | |
| 37569 |
Detection intelligence turbocharged with Al. |
643 | 0 | +25 | +103 | -1 | 0 | 0.0x, slowing | |
| 37570 |
Your one-person Wall Street. An AI trading agent covering equities, crypto, commodities, forex, and macro — from research through position entry, ongoing management, to exit. |
7,445 | 0 | +24 | +160 | -1 | 0 | 0.0x, slowing | |
| 37571 |
异环/Neverness to Everness脚本 |
620 | -1 | -1 | +6 | -1 | 0 | No data | |
| 37572 |
Utilities for Android emulators, iOS simulators and real devices: launch, stream, control, record and automate them from a desktop app, TUI and CLI |
1,218 | 0 | +4 | +33 | -1 | 0 | 0.0x, slowing | |
| 37573 |
Free, open-source terminal SSH manager and SSH config editor in Rust for macOS and Linux that keeps ~/.ssh/config in sync with 18 cloud providers, monitors live SSH tunnels and manages Docker and Podman containers fleet-wide. Plus scp, Vault SSH certs and an MCP server for AI agents. |
775 | -1 | +4 | +52 | -1 | 0 | No data | |
| 37574 |
Self-hosted health tracking PWA for weight, blood pressure, glucose, sleep, mood, medications and cycle, with sync from Apple Health, Withings, WHOOP, Oura, Polar, Garmin, Strava, Google Health and Nightscout, a doctor report PDF and optional AI insights. |
301 | +1 | +20 | +134 | -1 | 16 | 0.5x, slowing | |
| 37575 |
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime. |
717 | 0 | +19 | +90 | -1 | 0 | 0.0x, slowing | |
| 37576 |
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs". |
848 | 0 | +5 | +37 | -1 | 0 | 0.0x, slowing | |
| 37577 |
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. |
10,528 | +16 | +261 | +1,490 | -1 | 134 | 0.9x, slowing | |
| 37578 |
Publication-quality molecular graphics. |
626 | 0 | +3 | +10 | -1 | 0 | 0.0x, slowing | |
| 37579 |
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev) |
660 | 0 | +22 | +48 | -1 | 0 | 0.0x, slowing | |
| 37580 |
Lightweight, fast and native Office-to-PDF libraries and command-line tools for Rust, .NET, Java, Python, JS, Python. |
511 | 0 | +3 | +8 | -1 | 0 | 0.0x, slowing | |
| 37581 |
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults |
1,402 | 0 | +10 | +62 | -1 | 0 | 0.0x, slowing | |
| 37582 |
A curated collection of essential resources, tools, and playbooks to help founders build, launch, and scale startups successfully. |
2,334 | 0 | +2 | +27 | -1 | 0 | 0.0x, slowing | |
| 37583 |
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE. |
3,816 | -1 | +12 | +129 | -1 | 0 | No data | |
| 37584 |
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM. |
1,586 | -1 | 0 | +1 | -1 | 0 | No data | |
| 37585 |
AV/EDR evasion via direct and indirect system calls Windows NT 3.1 through Windows 11 24H2 · x64 · x86 · WoW64 · ARM64 |
640 | 0 | +3 | +61 | -1 | 8 | 0.0x, slowing | |
| 37586 |
Daily AI ecosystem digest from 10 sources (GitHub, ArXiv, HN, HuggingFace, Product Hunt, Dev.to, Lobste.rs). Bilingual ZH/EN reports via GitHub Actions. |
1,160 | 0 | +7 | +34 | -1 | 0 | 0.0x, slowing | |
| 37587 |
OpenClaw: Use All Major AI Models NO API Token! Claude/ChatGPT/Gemini/DeepSeek/Doubao/Grok/Qwen/Manus/Kimi |
5,218 | 0 | +6 | +46 | -1 | 8 | 0.0x, slowing | |
| 37588 |
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI |
4,448 | -1 | 0 | +4 | -1 | 0 | No data | |
| 37589 |
Zero Hour rebuilt from EA's source: x64, Direct3D 11, VS2022/CMake, ~60 original bugs fixed, an AI that builds a base. Bring your own game. |
329 | 0 | +15 | +102 | -1 | 10 | 0.0x, slowing | |
| 37590 |
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev. |
1,912 | 0 | +6 | +20 | -1 | 0 | 0.0x, slowing | |
| 37591 |
Write professional-grade skills for agents, validate them using LLMs, and maintain a lean context window. |
2,295 | 0 | +3 | +24 | -1 | 0 | 0.0x, slowing | |
| 37592 |
No description |
90 | +7 | +57 | +77 | -1 | 56 | 0.9x, slowing | |
| 37593 |
The ultimate setup harness for OpenClaw. Deploy in minutes. Stay running for months. No CLI required. |
1,487 | 0 | +8 | +16 | -1 | 8 | 0.0x, slowing | |
| 37594 |
No description |
1,288 | 0 | +3 | +16 | -1 | 0 | 0.0x, slowing | |
| 37595 |
#1 Persistent memory for AI coding agents based on real-world benchmarks |
30,347 | +14 | +164 | +941 | -1 | 186 | 1.0x, steady | |
| 37596 |
Turn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls. |
2,093 | 0 | +23 | +541 | -1 | 0 | 0.0x, slowing | |
| 37597 |
AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync. |
2,973 | +2 | +28 | +183 | -1 | 24 | 0.8x, slowing | |
| 37598 |
A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power. |
1,200 | 0 | +1 | +48 | -1 | 8 | 0.0x, slowing | |
| 37599 |
OpenOcta is an open-source AIOps Agent installed on Windows & macOS. |
3,245 | 0 | +8 | +47 | -1 | 0 | 0.0x, slowing | |
| 37600 |
Render Mermaid diagrams in your coding agent |
579 | 0 | +4 | +26 | -1 | 0 | 0.0x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 20 more tracked repositories are still loading their star history and will join the ranking once it is complete.