1.google / elephant-goldfish-model
Open-source skills for designing and reviewing software with AI agents
+7,956 stars
from 984 · score 8.98
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
55 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.thedotmack / claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
+6,109 stars
from 103,109 · score 8.72
3.Graphify-Labs / graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
+5,300 stars
from 135,226 · score 8.58
4.heygen-com / hyperframes
Write HTML. Render video. Built for agents.
+4,958 stars
from 72,143 · score 8.51
5.milind-soni / OpenMausBot
Open-source Grok Bot alternative with a virtual machine that bots can use
+4,895 stars
from 5,605 · score 8.50
6.microsoft / TokenEconomizer
Experience-Driven Black-Box Cost Control for Coding Agents
+3,653 stars
from 226 · score 8.20
7.NVIDIA / SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
+2,260 stars
from 21,603 · score 7.72
8.JuliusBrussee / caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
+1,656 stars
from 115,043 · score 7.41
9.herdrdev / herdr
the runtime your coding agents live on
+1,469 stars
from 45,852 · score 7.29
10.anthropics / claude-plugins-official
Official, Anthropic-managed directory of high quality Claude Code Plugins.
+1,159 stars
from 44,558 · score 7.06
11.headroomlabs-ai / headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
+754 stars
from 77,813 · score 6.63
12.rtk-ai / rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
+691 stars
from 84,535 · score 6.54
13.genspark-ai / genoffice
Free, open-source AI Office suite: Docs, Sheets, Slides, PDF, Markdown and HTML editors with a built-in AI agent, plus a `genoffice` CLI and agent skill so Claude Code, Codex and Cursor can create and edit real .docx/.xlsx/.pptx files locally. Bring your own key. macOS, Windows & Linux.
+671 stars
from 10,830 · score 6.51
14.iOfficeAI / OfficeCLI
OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required.
+456 stars
from 32,456 · score 6.12
15.mukul975 / Anthropic-Cybersecurity-Skills
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
+392 stars
from 35,012 · score 5.97
16.openqodex / openqodex
Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Codex, Cursor and Cline. No account or key of its own.
+309 stars
from 784 · score 5.74
17.humanlayer / humanlayer
The best way to get AI coding agents to solve hard problems in complex codebases.
+258 stars
from 12,488 · score 5.56
18.iOfficeAI / AionUi
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up｜Star if you like it!
+215 stars
from 33,761 · score 5.38
19.reason-machines / reason-network
Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.
+206 stars
from 1,231 · score 5.33
20.Tejashmakwana / motionmaxxing
Looksmaxxing for motion graphics. An agent skill that turns AI slop videos into films that look made by a motion designer.
+203 stars
from 1,047 · score 5.32
21.sno-ai / sno-station
When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.
+199 stars
from 891 · score 5.30
22.davidondrej / cloudroom
cloudroom is the open-source platform to run 1,000+ agents productively
+194 stars
from 1,024 · score 5.27
23.respanai / respan-gateway
Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.
+177 stars
from 301 · score 5.18
24.everyinfra / everyinfra-agent-plugins
EveryInfra MCP server & agent plugin: scraper API for TikTok, Instagram, Amazon, YouTube, Xiaohongshu & Douyin. 573 data APIs across 106 platforms, from $0.56/1K calls. For Claude Code, Cursor, Codex.
+140 stars
from 54 · score 4.95
25.DayuanJiang / next-ai-draw-io
Draw and edit draw.io diagrams by chatting with an AI. Web app, desktop app, and an MCP server for Claude Code, Cursor, Codex and VS Code.
+135 stars
from 36,409 · score 4.91
26.Graphicle-AI / graphicle
Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.
+131 stars
from 358 · score 4.88
27.alexgreensh / anidoodle
Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens of styles, identical on every render.
+116 stars
from 1,104 · score 4.76
28.jeecgboot / JeecgBoot
【低代码v2.0，一句话即可生成整个系统】企业级AI低代码平台，一键生成前后端代码甚至整个系统。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖：AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，解决 Java 项目 90% 重复工作，提高效率又不失灵活。
+84 stars
from 48,278 · score 4.44
29.lcoutodemos / chums
Talk to Claude Code and Codex agents from an Apple Watch and an iPhone. Each agent is a character on the watch.
+73 stars
from 222 · score 4.30
30.onlook-dev / onlook
The Developer Tool for Visual Engineers • An Open-Source AI-First Design tool • Visually build, style, and edit your code with AI • World's best, top-most agent recommended #1 Developer tool for Designers and Visual Engineers to design with Real Code.
+70 stars
from 27,005 · score 4.26
31.Usmansayed / scubiee
Save up to 30% of your AI coding tokens. Scubiee turns any codebase into searchable context for your AI coding agent. A local context engine for Cursor, Claude Code, Copilot, Codex, and more: semantic search, code relationships, live sync, MCP integration, and code that never leaves your machine.
+65 stars
from 80 · score 4.19
32.vercel-labs / durable-harness
Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK World
+42 stars
from 237 · score 3.76
33.IvanMurzak / Unity-MCP
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
+36 stars
from 4,530 · score 3.61
34.rowboatlabs / rowboat
AI coworker with memory and collaboration
+34 stars
from 18,085 · score 3.56
35.activeing123 / mcptoon
One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 561KB, pure Python. | 零依赖 CLI：管所有 MCP 工具与技能，工具发现省 99.2% token。
+26 stars
from 391 · score 3.30
36.sno-ai / sno-station-skills
Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.
+22 stars
from 839 · score 3.14
37.higress-group / HiRoute
Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
+22 stars
from 346 · score 3.14
38.olimorris / codecompanion.nvim
✨ AI Coding, Vim Style
+18 stars
from 6,901 · score 2.94
39.IvanMurzak / Godot-MCP
Godot-MCP — Model Context Protocol (MCP) integration for the Godot Engine. AI tools for the Godot Editor in C#, with cloud connection to ai-game.dev. Apache-2.0.
+14 stars
from 306 · score 2.71
40.YeonwooSung / my-claude-code-mods
Custom Claude Code Mods that I need
+13 stars
from 1,092 · score 2.64
41.klarluft / pitupitu
Talk to Claude Code and Codex by voice, from your phone, on any of your machines. The open-source box agent for pitupitu.chat; your agents run in herdr.
+12 stars
from 212 · score 2.56
42.LumaryLabsLLC / muxin
All your machines, one app. For you and your AI agents: agent sessions, desktops, files, logs and GitHub across your Macs, Linux and Windows machines, with an MCP server.
+9 stars
from 374 · score 2.30
43.starswallow / lessloc
Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.
+7 stars
from 102 · score 2.08
44.zero-lab-ai / skills
Portable, evidence-bound security skills for authorized defensive assessment, red teaming, penetration testing, detection engineering, and engagement operations.
+4 stars
from 282 · score 1.61
45.node9-ai / node9-proxy
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
+4 stars
from 219 · score 1.61
46.juyterman1000 / entroly
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
+3 stars
from 480 · score 1.39
47.Rich627 / whatsapp-claude-plugin
Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
+3 stars
from 112 · score 1.39
48.ccf / agentcairn
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
+3 stars
from 67 · score 1.39
49.IvanMurzak / Unreal-MCP
AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server
+3 stars
from 51 · score 1.39
50.josstei / maestro-orchestrate
Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools
+1 stars
from 484 · score 0.69
51.Zafer-Liu / claude-super-sidebar
A visual sidebar for Claude Code and Codex: agent trees, live status, and conversation task flows.
+1 stars
from 155 · score 0.69
52.Fmarzochi / EGC
EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
+1 stars
from 67 · score 0.69
53.hrygo / hotplex
HotPlex — Unified access layer for AI Coding Agent.
+1 stars
from 51 · score 0.69
54.anneschuth / claude-threads
Think of it as screen-sharing for AI pair programming, but everyone can type.
+1 stars
from 45 · score 0.69
55.saivedant169 / AegisFlow
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
+1 stars
from 37 · score 0.69