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 10 Nov 2026, 07:20 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 |
|---|---|---|---|---|---|---|---|---|---|
| 27851 |
An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion. |
3,178 | +2 | +28 | +165 | 0 | 0 | 1.0x, steady | |
| 27852 |
200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns. |
543 | 0 | -1 | -1 | 0 | 0 | No data | |
| 27853 |
Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions. |
1,180 | 0 | +1 | +28 | 0 | 0 | No data | |
| 27854 |
fast simple multi platform TOR client with built in bridge |
187 | +2 | +13 | +112 | 0 | 0 | 1.0x, steady | |
| 27855 |
We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction. |
856 | +1 | +10 | +33 | 0 | 8 | 1.0x, steady | |
| 27856 |
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI |
4,449 | 0 | -3 | +9 | 0 | 0 | No data | |
| 27857 |
A WYSIWYG editor for TikZ that parses TikZ code |
507 | +1 | +5 | +26 | 0 | 0 | 1.0x, steady | |
| 27858 |
A multi-platform document and e-book reader. |
1,341 | +1 | +12 | +64 | 0 | 0 | 1.0x, steady | |
| 27859 |
No description |
547 | +1 | +4 | +15 | 0 | 0 | 1.0x, steady | |
| 27860 |
A framework-agnostic, git-native standard for defining AI agents |
2,985 | 0 | 0 | +15 | 0 | 0 | No data | |
| 27861 |
It won't fix your bug. It'll fix you. The debugger that hands the question back instead of the answer. |
556 | +1 | +9 | +555 | 0 | 8 | 1.0x, steady | |
| 27862 |
Write professional-grade skills for agents, validate them using LLMs, and maintain a lean context window. |
2,294 | +1 | +9 | +26 | 0 | 0 | 1.0x, steady | |
| 27863 |
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights. |
4,122 | +5 | +28 | +169 | 0 | 0 | 1.0x, steady | |
| 27864 |
LLM inference engine written in .NET |
528 | 0 | +1 | +7 | 0 | 0 | No data | |
| 27865 |
Claw 们终将接管世界，PUAClaw is All You Need |
2,695 | 0 | -4 | +3 | 0 | 0 | No data | |
| 27866 |
Universal content grabber — fetch, normalize, and digest content from 7+ platforms (WeChat, XHS, X/Twitter, YouTube, Bilibili, Telegram, RSS) |
623 | 0 | +1 | +11 | 0 | 0 | No data | |
| 27867 |
No description |
598 | 0 | +2 | +17 | 0 | 0 | No data | |
| 27868 |
The most comprehensive code intelligence MCP server for AI coding agents. 40+ tools, 30+ languages, 9 agent integrations. Pre-indexed semantic knowledge graphs for instant code understanding — fewer tokens, fewer tool calls, 100% local. |
699 | +2 | +12 | +41 | 0 | 8 | 1.0x, steady | |
| 27869 |
OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery and remediation product, helping defenders proactively find and patch verified security flaws while minimizing both false positives and negatives. Stage 1 detects. Stage 2 attacks. What survives is real. |
803 | +1 | +7 | +47 | 0 | 8 | 1.0x, steady | |
| 27870 |
No description |
642 | 0 | +9 | +32 | 0 | 0 | No data | |
| 27871 |
通达信A股行情协议 Python 库，MCP，支持快照、分时、逐笔、K 线、集合竞价、特殊指标等接口。适合作为量化数据源，支持其他语言通过HTTP或WebSocket调用 |
709 | +6 | +32 | +137 | 0 | 32 | 1.0x, steady | |
| 27872 |
No description |
1,709 | 0 | +12 | +97 | 0 | 0 | No data | |
| 27873 |
A curated, multilingual library of 182 installable AI agent skills for end-to-end academic research—spanning literature discovery, scientific writing, grant development, bioinformatics, drug discovery, clinical research, machine learning, and data analysis. |
1,028 | +5 | +25 | +85 | 0 | 8 | 1.0x, steady | |
| 27874 |
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph. |
1,991 | 0 | +2 | +9 | 0 | 0 | No data | |
| 27875 |
Record scripted browser demos as video |
966 | +1 | +6 | +20 | 0 | 0 | 1.0x, steady | |
| 27876 |
CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness |
1,507 | +1 | +8 | +99 | 0 | 0 | 1.0x, steady | |
| 27877 |
[RSS'26] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence. |
2,883 | +1 | +5 | +32 | 0 | 0 | 1.0x, steady | |
| 27878 |
No description |
329 | +4 | +34 | +243 | 0 | 0 | 1.0x, steady | |
| 27879 |
A powerful, privacy-friendly open source web analytics tool that runs entirely on Cloudflare. |
713 | 0 | +1 | +173 | 0 | 0 | No data | |
| 27880 |
A self-organizing Obsidian vault that gives AI coding agents persistent memory. |
5,523 | +7 | +42 | +431 | 0 | 14 | 1.0x, steady | |
| 27881 |
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion. |
2,600 | +1 | 0 | +1,386 | 0 | 0 | 1.0x, steady | |
| 27882 |
🧠 Curated collection of 2700+ best agent skills — AI, coding, marketing, design, finance and more. Harness-agnostic: works with Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, Hermes and any Agent Skills runtime. Refreshed daily by MyClaw.ai — Powered by MyClaw.ai |
2,186 | +1 | +11 | +32 | 0 | 0 | 1.0x, steady | |
| 27883 |
Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode. |
4,830 | +9 | +76 | +238 | 0 | 44 | 1.0x, steady | |
| 27884 |
[TPAMI 2026🔥] Helios: Real Real-Time Long Video Generation Model |
2,258 | +1 | +12 | +62 | 0 | 0 | 1.0x, steady | |
| 27885 |
Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies. |
1,009 | +1 | +8 | +39 | 0 | 8 | 1.0x, steady | |
| 27886 |
Understand any codebase instantly. System intelligence for codebases, built for humans and AI. |
1,153 | +3 | +13 | +66 | 0 | 0 | 1.0x, steady | |
| 27887 |
Build better UI with AI |
2,228 | +5 | +35 | +203 | 0 | 16 | 1.0x, steady | |
| 27888 |
Docker Sandboxes run AI coding agents in isolated environments on your machine or on Docker-managed cloud infrastructure |
506 | +3 | +17 | +72 | 0 | 0 | 1.0x, steady | |
| 27889 |
CLI for Hotdata |
1,801 | 0 | 0 | +1 | 0 | 0 | No data | |
| 27890 |
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. |
523 | 0 | -3 | +16 | 0 | 0 | No data | |
| 27891 |
No description |
1,935 | 0 | +4 | +22 | 0 | 0 | No data | |
| 27892 |
Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models. |
1,570 | 0 | 0 | +11 | 0 | 0 | No data | |
| 27893 |
Run agentic coding workflows in a fully native desktop app for Git worktrees, terminals, and diffs. |
845 | 0 | +6 | +15 | 0 | 0 | No data | |
| 27894 |
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. |
575 | 0 | 0 | +77 | 0 | 0 | No data | |
| 27895 |
my akashic |
521 | +1 | +3 | +12 | 0 | 0 | 1.0x, steady | |
| 27896 |
异环 后台副本挂机 Automation for Neverness to Everness |
1,362 | +2 | +16 | +125 | 0 | 0 | 1.0x, steady | |
| 27897 |
Native Telegram client for Android |
977 | 0 | +3 | +39 | 0 | 0 | No data | |
| 27898 |
Empower the Shell to think. Evolve Operations. |
580 | +1 | +6 | +24 | 0 | 0 | 1.0x, steady | |
| 27899 |
A custom launcher for Minecraft LCE. |
514 | 0 | 0 | +2 | 0 | 0 | No data | |
| 27900 |
RTX 50-40-30 Series Undervolt Tool |
704 | +2 | +19 | +57 | 0 | 8 | 1.0x, steady |
Today counts stars since midnight US Pacific time, so it is a partial day. 1 more tracked repositories are still loading their star history and will join the ranking once it is complete.