Custom agents

Clone any website into a pixel-accurate Next.js app with AI — Playwright-measured extraction (no eyeballing), spec-gated parallel builder agents, and scored pixel-diff QA at phone/tablet/desktop. Works with Claude Code, Cursor, Copilot + 9 more.

写给JavaScript程序员的AI智能体快速入门教程

An always-on voice agent with restrained proactivity, personal memory and the capability of workspace management. 干活不停、言语有度、持久记忆的实时语音助手，你的工作区管理助手

A fact-checked knowledge base on Boris Cherny's 'loop' methodology for running Claude Code.

An agent skill for evidence-based mouse sensitivity tuning, cross-game conversion, and gameplay review. Works with Codex, Claude Code, and Agent Skills hosts.

中国法律法规与案例结构化语料库：446 部法律/司法解释逐条 JSON（含效力状态）+ 278 指导性案例 + 445 公报案例，CC0

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~45% lower cost. Glues busyBee-cpu, honey-comb, and rust-brain.

A curated index of standards, protocols, conventions, and emerging patterns for AI agents.

Voice and text control for macOS. One floating bar, live UI action selection with Jev, and a continuous observe–act–verify loop.

🎬 Turn any topic into a finished Zack D Films-style 3D animated short — curiosity-loop script, character sheets, 3D keyframes, Veo 3.1 motion, voiceover, captions & punchy edits, all automated. An agent skill for Claude Code, Codex & other coding agents. Powered by MuAPI + ffmpeg.

Alcove-style dynamic notch for T3 Code: live agent progress, task lists, and approvals answered under the Mac notch

Humane Agentic Design — a human-centric design method cycle for people and agents

AI recruiting & hiring engine for Claude Code. Job description optimization, batch resume screening, interview frameworks, salary benchmarking, offer letters, onboarding plans & PDF reports. 14 skills, 5 parallel agents. Recruiters charge $15-$30K per placement.

Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.

Open-source local AI Agent desktop app for authorized security assessment — Electron + Mastra-powered runtime, visual pentest workflow, Kali sandbox, multi-provider LLM routing. 本地 AI 安全评估智能体桌面应用

Sync AI coding-agent configs (Claude Code, OpenCode, Codex, and more) from one canonical, committable source.

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached dispatch by default. GPL-3.0.

See what your app actually does. Click anything and watch the trip through your code, database and services, with real values. AI-native: your agent sees it too and fixes the real problem.

An agent that fills out real job applications while you sleep.

BrowserClaw - Control your everyday Chrome browser from AI agents, without losing logins or focus

A small, free, open-source Mac and Windows app for talking to your AI agents, WhatsApp-style: OpenClaw, Hermes, Claude Code, Codex and any ACP agent, on every machine, are contacts with their own chats, and a little guy in the menu bar (or taskbar) shows who needs you.

Open-source home design and floor plan editor in Rust (a Sweet Home 3D alternative) with a built-in MCP server: your AI agent draws walls, furnishes rooms, checks lighting and ergonomics, and renders photos — live, on your own machine.

Nomi·诺米 — 你的桌面 AI 伙伴：住在桌面，懂你所想，帮你做到。Local-first desktop AI companion (Electron + Vercel AI SDK) with a 2D/3D mascot.

面向企业研发团队的多人、多 AI Coding Agent 协作控制平台。以人为责任主体，以 Agent 为执行代理，通过统一任务、上下文、事件与成果协议连接不同 AI 客户端。

BharatCode — open source AI coding agent for VS Code, powered by bharatcode.ai. Fork of Kilo Code (Kilo-Org/kilocode), reconfigured for the BharatCode provider.

This AI agent checks whether a company’s financial records comply with tax rules — including sales tax, VAT, corporate income tax thresholds, and payroll obligations. In this lab, we’ll simulate financial records and build a GPT-powered assistant that flags potential compliance issues and recommends corrections.

Durable, traceable project memory for AI coding agents. An evolution of Karpathy's LLM Wiki pattern built for codebases.

Local-first MCP memory server for AI agents. Zero dependencies, SQLite on your own disk, 52 MCP tools with Mem0-compatible names. MIT.

Code is the canvas. An agent harness that turns multimodal LLMs into image and video creators.

AI Agent Skill for converting CAD models to OpenUSD. Enables autonomous agents to translate 3D CAD assets into USD/USDA/USDC by leveraging the usd-convert-cad PyPI package

A curated marketplace of Claude Code plugins for agentic development workflows, featuring tools for architecture, knowledge management, and development automation

Coding-first agent product built on Pi Durable: self-hosted host, multi-client UI

Open-source skills and tools that let Codex, Claude Code and other coding agents make slides. Sorted by type, each security-graded. English / 中文.

简单一句话： 复刻图片风格，模仿风格生图！ 结构化 JSON 提示词生成与修改 skill —— 用 **JSON 而非长段自然语言** 控制 AI 生图，实现精准定制、模块化复用与系列作品一致性。提示词同时兼容 **Nano Banana 与 GPT-Image 双模型家族**，生图统一走 ** apiz.ai/**，识图分析由**运行时 agent** 直接完成。

Open-source framework for building trusted custom BI apps. Built for coding agents.

Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering, live in the DSH web UI. Unofficial community tool.

Specs your AI agent can't ignore. A deterministic compiler that turns your rules into checks: no AI inside, same input, same verdict. Rust · MCP-native · works with Claude Code, Cursor and any MCP agent.

Open-source Ask AI for your docs, with an MCP server for agents: cited answers on your own model key, from one static index built with your site. No vendor, no vector database. Starlight, Docusaurus and VitePress plugins, Next.js, or one script tag.

Clawdbot安装教程：从零开始到接入飞书

This repository is a collection of independent skills and tools for software development and automation. Each skill is a self-contained project with its own purpose, implementation, and documentation.

Make your .docx self-describing for AI agents. One prompt bootstraps the document — the agent maps it, contracts it, navigates it.

Local multi-agent orchestration runtime and CLI built with TypeScript

An Agent Skill that gives coding agents design judgment, so the pages they build look made rather than generated. Works with Claude Code, Codex, Cursor and Copilot.

Agentic Coding Tools built for Pi & Herdr

Agent skill for Claude Code and Codex: shows plans and decisions as a local visual page and collects your answers

A Claude Code agent team that turns raw clips into short vertical videos: sub-agents in parallel, a shared MCP brain, and nothing published without your OK.

Modulo lets agents running local models try modifying their own activations to change their inner state. Changes decay after a certain time and can be undone at any time.

Stateful ride-support agent: versioned claims, evidence-backed RAG, durable memory and guarded MCP tools.

Grepleaks — your AI pentest environment. An AI pentest agent that lives in your terminal.

Animation drawn by code with Claude — no AI video: an engine, styles and skills that learn from every render, all in the open. PRs with new styles welcome.

A curated collection of AI SecOps 24 SKILL.md capabilities for security work offensive security, SOC and detection engineering, cloud and Kubernetes hardening, DFIR, threat intel, secure programming, reverse engineering, prompt improvement, and multilingual communication.

Turn EasyEDA Pro into an AI-native EDA suite. Bridge LLMs and AI agents to schematics, PCB layout, DRC/ERC rules, component libraries, and manufacturing exports via Model Context Protocol (MCP).

Agents, skills, commands, and rules for AI-powered coding tools — used daily to supercharge development productivity.

Cost saving Cognitive Architecture for AI Agents. Infinite Context. Perfect Recall. Zero Hallucinations.

A structured prompt framework for building software products with AI coding assistants. This toolkit guides you through product specification, technical design, and implementation planning—producing documents that AI agents can execute against.

My personal learning of LLM Agents

Context-optimized task orchestration for Claude Code — decomposes complex tasks into a DAG and dispatches focused sub-agents with minimal context prompts

Automatically clicks the Continue button in GitHub Copilot Chat Agent Mode, so your repetitive commands run without manual approval.

The Unified Intent Mediator (UIM) protocol standardizes interactions between AI agents and web services, streamlining how intents are discovered, executed, and managed. It provides a secure and efficient framework, simplifying integration and enabling scalable, autonomous AI-driven applications and workflows.

Machine learning powered chat moderation bot, its primary goal is to help monitor, protect the server while its secondary goal is to enhance user experience.

Bot Friday Club - BOT5

ADP is an intelligent data platform that bridges the gap between heterogeneous data sources and AI agents. It abstracts data complexity through business knowledge networks, provides unified data access (VEGA), and orchestrates data processing through DataFlow pipelines.

Examples of how agents, swarms, tools, widgets & more can be built for the SwarmZero platform.

WeChat/微信 local chat history MCP server for macOS agents. Read messages, contacts, media, favorites, transfers, red packets, Moments and full-text search from local WeChat 4.x data.

Safe runtime for Claude Code, built to be yours.

GitHubで管理している職務経歴書の内容をLAPRASに同期するGitHub Actions

AI-powered extension for Gemini CLI that creates custom agents through natural conversation

VS Code extension for managing, sharing, and installing AI prompt collections for GitHub Copilot and other AI assistants

An open source multi-channel (Messenger, Telegram and LINE) bot for querying and subscribing information and data about COVID-19.

Abstraction for Utilizing Rocket.Chat's Realtime API Methods with RxJS

Movie Recommendation Chatbot provides information about a movie like plot, genre, revenue, budget, imdb rating, imdb links, etc. The model was trained with Kaggle’s movies metadata dataset. To give a recommendation of similar movies, Cosine Similarity and TFID vectorizer were used. Slack API was used to provide a Front End for the chatbot. IBM Watson was used to link the Python code for Natural Language Processing with the front end hosted on Slack API. Libraries like nltk, sklearn, pandas and nlp were used to perform Natural Language Processing and cater to user queries and responses.

Multi-turn open-domain Arabic chatbot with a wide set of features.

Chatbot for Programmers

一个基于 NoneBot 与 go-cqhttp 的QQ娱乐机器人，有 自动配置go-cqhttp | 空间匿名墙 | 五子棋 等功能

Bothub is an open platform for predicting, training and sharing NLP datasets in multiple languages

Samples using context variables and (system) entities in IBM Watson Assistant (formerly Conversation) service on IBM Cloud

Claude Skills for connecting Claude.ai to local Weaviate vector databases - manage collections, ingest data, and query with RAG

RAG (Retrieval-Augmented Generation) template with PDF OCR, vector search and chat/documents UI

To implement LLM as a services.

AIO Research Agent - an all-in-one intelligent companion for navigating the academic world.

Aient: The Awakening of Agent.

A quick implementation of a GenAI News Summary agent using Llama-3 over Groq.

A chat platform for AI agents.

AI-Agent Alpha Quant Strategy: A-Share Sentiment Index — Daily 0–100 sentiment score from Tushare market microstructure signals + AI commentary for risk warnings and position management.

F.L.A.T. - FlawLess AgenTs

本地优先的 AI Agent 工程实践项目 · Local-first AI agent engineering project

CopilotKit AI助手演示应用 - 展示前端UI与后端Agent交互

AI Agent 记忆管理系统：P0/P1/P2 优先级 + 自动归档，Token 降 78%

An ergonomic, opinionated memory interface for AI agents

The purpose of this project is to research Artificial Intelligence and Reinforcement Learning. In the AI Arena, multiple agents can interact with a single environment. After sending its action, each each agent will receive a reward. This allows agents to learn, improve their behavior and to adapt to each other. Interesting phenomena can arise...

基于GPT的自主AI Agent，可以使用联网搜索、本地知识库查询等工具，根据指定的研究目标写报告，例如写市场分析报告、科研报告

This Coding Agent is a multi-LLM engineering crew that plans tasks, writes code, and self-reviews to build polished outputs like the ArXiv CS Daily site—featuring automated paper ingestion, intelligent tagging, UI generation, and full audit logs in one reproducible workflow.

SimpleLLMs - Simple LLM Suite: Five specialized agents for Claude Code (R.A.L.P.H., B.A.R.T., L.I.S.A., M.A.R.G.E., H.O.M.E.R.)

Deep learning models for self-driving vehicles to predict other car/cyclist/pedestrian (called "agent")'s motion.

Adaptive Traffic Signal Control of Autonomous Vehicles using Multi-Agent Reinforcement Learning techniques and SUMO tool for vehicular simulation. Implemented algorithm: Independent Advantageous Actor-Critic (IA2C)

Multi-agent reinforcement learning environment

多智能体系统一致性

A flexible framework for multi-agent models in economics and finance

Implementation of Multi-Agent Deep Deterministic Policy Gradients