Custom agents

Free Claude Code skills to script, research and edit short-form videos. Markdown only.

Official code for "Focused Omni-Modal GUI Agents“

🦙 Opilot: Ollama for GitHub Copilot VS Code Extension – Run Ollama models locally and in the cloud within GitHub Copilot Chat

面向 DeepSeek Harness 的电影感产品视频 Agent Skill，包含 152 张镜头配方卡、Remotion 模板、代码组件和音频资产。

基于 go-zero + React 19 + Ant Design 6 的开源全栈微服务管理后台，采用单仓库、1 API + 5 RPC 架构。支持 RBAC + Casbin 接口权限与部门级数据范围、每租户独立容器栈与数据库、Nginx 子域名路由；集成 Eino AI Agent、工具调用与人工审批工作流。采用 goctl 代码生成和缓存 Model 数据层，提供完整初始化数据，适合作为企业管理后台与 SaaS 项目的开发起点。

Agent skills by kelvinkn17. First up: fun-isometric, stickers that move.

TypeScript toolkit for Windows x64 native systems programming, memory manipulation, and process instrumentation.

A modern terminal mail client for Gmail and Microsoft 365, with an MCP server for AI agents

多Agent工作台，额度看得见、用完不断档、多个Agent相互协作，多任务并行开发。| Multi-agent workbench for Claude Code, Codex, Cursor and more. See your quota, keep working when it runs out, run tasks in parallel, let agents delegate.

Let agents control any remote computer, anytime, anywhere. Self-hosted AI agent remote assistance via MCP and terminal.

[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform

Run, review, and orchestrate AI coding agents from anywhere

基于Qwen3VL大模型和GUI Agent技术的移动端智能体，能够通过 ADB 指令智能操控 Android 手机

开源人工智能，基于开源软硬件构建语音对话机器人、智能音箱……人机对话、自然交互，来宝拥有无限可能。特别说明，来宝运行于Python 3！

Powerful PHP library/framework for VK API bots, supporting LongPoll & Callback & OAuth2

ChatGLM-6B HTTP流式解码API的Flask、FastAPI实现，以及开箱即用的Web页面。 a stream decoding demo of ChatGLM-6B using Flask or FastAPI, with web page out-of-the-box.

eXtensible UPnP agent (official)

Fully Undetectable Native C++ Remote Access Agent / Botnet.

Agentic trading workflow builder with custom PineTS alert system

Harness for deep search agent

Fast CLI for Google Play Console, for developers optimized for your agentic development flows

Implementation of Agent Attention in Pytorch

http.request wrapper with gzip, request retries and http.Agent tuning

A simple agent for performing a sequence of http requests in node.js

A TensorFlow based implementation of the DeepMind Atari playing "Deep Q Learning" agent that works reasonably well

A framework to build GUI-like Agent Tools, enhancement to Function Calling of LLM AI.

AI Document Assistant

NeuroMinecraftGenesis (NMG): A revolutionary AI system that draws on the DiscoRL self-evolving algorithm, six-dimensional cognitive engine, and quantum-classical brain computing developed by DeepMind. It features multi-agent evolution, three-world integration, and AI toolkit capabilities.

Managed Claude Stack - Reproducible AI infrastructure for Claude Code

LLM Agentic Tool Mesh Platform is an innovative platform designed to streamline and enhance the use of AI in various applications. It serves as a central hub to orchestrate 'Intelligent Plugins,' optimizing AI interactions and processes.

Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation" An next generation robot LLM

VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders

This repository consists of work done to analyse sentiment of a customer in a conversation with a call center agent using various machine learning algorithms and audio features.

Vibe Island releases & update feed — download the latest DMG of the macOS notch panel for 25 AI coding agents (Claude Code, Codex, Cursor & more).

In-browser GraphRAG

A Chrome side-panel browser agent

Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.

Helping the Agents Compose the Things

Official Monte Carlo toolkit for AI coding agents. Skills and plugins that bring data and agent observability — monitoring, triaging, troubleshooting, health checks — into Claude Code, Cursor, and more.

Save 40%+ on agent token costs with code graphs: call graphs, dependency graphs, dead code detection, and blast radius analysis.

Pipe logs from all your dev servers into a single place accessible to your agents.

ClawdSecbot is a professional AI Bot security protection solution, providing security capabilities including real-time threat detection, prompt injection protection, and security auditing to comprehensively protect your AI applications. ClawdSecbot 是一款专业的 AI Bot 安全防护解决方案，提供实时威胁检测、提示词注入防护、安全审计等安全能力，全方位保护您的 AI 应用安全。

Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

Open Builder is an open-source AI-powered app generator. Build web applications through natural language conversations.

Harness the scientific methods of Sydney Brenner using AI Agents

Make AI work for Everyone - Monitoring and governing for your AI/ML

Interactive multi-agent NCA ecosystem simulation

Official Implementation of Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

Next-gen AI-native tensor-network-based quantum software framework

An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.

[Everything Gemini Code] A harness engineering toolkit for Gemini CLI & Antigravity. Tune the runtime around the model, not the model itself

Cesium AI Integrations is a collection of reference integrations and experiments connecting the Cesium ecosystem with AI systems including Model Context Protocol (MCP) tools, retrieval pipelines, and agent skills.

Semiont supports human+ai collaborative knowledge work. Use it as: a Wiki, Knowledge Base, Context Graph, Semantic Layer, or Agentic Memory.

Building a Senior Staff Engineer with Sub-Agent Teams in Claude Code

Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing

PRB's collection of agent skills

An opinionated Claude Code Plugin Pack. Skills, Agents, Hooks, MCPs. Examples: Email draft preview assistance & humanisation. Agents for Codex and Gemini "outsourcing". Skills for Google Analytics & Google Tag Manager, Shopify and much more

EdgeCrab 🦀 A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw — Rust-native, blazing-fast terminal UI, ReAct tool loop, multi-provider LLM support, ACP protocol, gateway adapters, and built-in security hardening.

Build your own Company OS with Claude Code. CLAUDE.md template, 5 GTM skills, workflow plugin, safety hooks, and full blueprint.

Renshu AI is a multi-agent Traditional Chinese Medicine (TCM) consultation system featuring a decoupled front-end and back-end architecture built with FastAPI and React, utilizing the "Harness" paradigm. It aims to address key pain points in TCM consultations—such as low intent recognition accuracy, the fragmentation of structured and unstructured

MOTO is an automated theorem generator for science. It's a creative novelty-seeking researcher with autonomous Lean 4 proof generation. Run for days at a time once pressing start - no interaction needed! Agents working in parallel from either local host LM studio, OpenRouter, OAuth or all 3. No internet required. Star us for more!

WSO2 AI Agent Manager is an open control plane designed for enterprises to deploy, manage, and govern AI agents at scale.

All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully private, no cloud required.

🔥 构建高质量的AI编程Skills库，利用AI来学习编程技术。Collect and build high-quality skills to enable AI to serve you better.

AI agent skills for applying Feature-Sliced Design (FSD) v2.1 in frontend projects.

Dedicated agent skills for building, upgrading, and maintaining Shopify Hydrogen storefronts — works with Claude, Cursor, Copilot, and more.

PurrCat Agent

Multi-agent macro trading bot: multi-factor stock scoring, momentum portfolio construction, backtesting vs SPY/Nasdaq, and live Alpaca execution.

Relay any model into any coding agent

一个旨在用 AI 帮助没有写作经验的小白/老书虫落地网文/小说故事，使用了 Harness 架构思想，多个专项 Agent + Skills，同时维护了小说知识包市场

token trading agent on solana via twitter post engagement

Agentic hypervisors for the 21st century

完整的多 Agent 多 Skill 小说改编影视流水线系统。

Malleable coding agent app. Use Claude Code and Codex to code and reshape the app itself live.

Using recursion to acheive predictable agent output

Headless MCP server for Screaming Frog SEO Spider – run crawls, export and analyze crawl data via the CLI. Small locked-down tool surface for scheduled audits, CI, and unattended AI agents.

Personal AI Assistant, secure first, self learning and self defending

The environment engine for agent worktrees - zero-config dep sync + port/DB/compose isolation

Beads, planning, and knowledge injection for AI coding agents

Official Aspire skills and plugins for AI coding agents to initialize, wire, orchestrate, monitor, and deploy distributed apps.

OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.

Official repository for the NDSS 2026 research paper titled "FirmAgent: Leveraging Fuzzing to Assist LLM Agents with IoT Firmware Vulnerability Discovery"

Agent-ready HTML design skill collection for decks and Xiaohongshu cards

Travel MCP server + CLI for AI assistants — flights, hotels, trains, cars, ferries, price alerts. No API keys, single Go binary. 1 smart MCP tool + 66 aliases (98.9% smaller tools/list). Works with Claude, Cursor, Windsurf, Codex.

Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.

Build your own AI hedge fund with Claude, Codex, Cursor & OpenClaw. The agent-native skills directory for Trader Dev MCP — write Pine Script, backtest crypto strategies, optimize parameters.

Use your OpenCode Go subscription in the Codex app. Local Responses-to-Chat-Completions bridge for all 13 OpenCode Go models.

Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and contribute ForgeCat packages.

Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.

NEXBENCH measures what an autonomous agent can actually do on-chain — execute transactions, route swaps, bridge funds, manage DeFi positions, research tokens, catch drainers, reconstruct portfolios, and run treasury governance — across 214 tasks in 8 categories, each run 5 times against deterministic forked-mainnet environments.

把书拆成 AI Agent 可执行的 Skill，让书中的智慧变成你的决策副驾驶 | Turn books into executable AI Agent Skills

[ECCV 2026] Promsa: Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

Official code for "MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management"

An easy-to-use harness for agentic projects.

MCP server for debugging Electron apps via Chrome DevTools Protocol. Start/attach processes, capture screenshots, read console errors & network logs, inspect DOM, evaluate JS, and automate UI — built for Cursor and other MCP clients.

基于对 Claude Code 源码的系统性分析，从 11 个维度拆解其架构设计，涵盖 Agent Loop、Context 管理、Tool 调用、Memory、权限安全、多智能体协作、可观测性等核心模块

A curated collection of custom agents, skills, rules, and prompts for GitHub Copilot, Google Antigravity, OpenCode, ChatGPT Codex, and Oh My Pi. Tailored for Indonesian and International developers to streamline SDLC workflows with AI.

AI-Agent-ready CLI framework for editing, testing, running, tracing, and diffing Excel VBA projects.