Code agents

An autonomous coding agent and SDK for building AI-powered development tools

An Agent used to demonstrate the operation of code based on a sandbox in a multi-user environment

Multi agent simulation code for 2×2 Game on complex network

Multi-agent deliberation plugin for Claude Code - council, debate, and deliberation modes

Multi-Agent System for Automated Penetration Testing (MASAPT)

Slash commands for Linux desktop sysadmin with Claude Code (or any other agent)

useful files and scripts for working in claude code

🧠 v6.0 Hive Mind — One open-source brain every AI coding agent can share (Claude Code, Cursor, Cline, Codex, Copilot, Windsurf). 22 novel features. Free. Local-first. MIT.

Detect and diagnose visual jank in React UIs — static analysis of 18 anti-patterns + runtime investigation workflows (Playwright, React DevTools, Chrome Performance, web-vitals). Agent skill for Claude Code, Codex, Cursor, and others.

A LangGraph-based research assistant that helps find, analyze, and summarize scientific papers. Built with Mistral LLM (via Ollama) and Flask, this agent can search papers through CORE API, process PDFs, and provide structured research summaries.

soulshack, an irc chatbot. openai/ollama/gemini/anthropic apis. basic shell tools and mcp server support.

This project is a Facebook Messenger chatbot that uses the OpenAI GPT-3 model to generate responses to user messages. It leverages Flask as a web framework to handle incoming messages from Messenger and makes requests to the OpenAI API to generate responses.

Anthropic's Contextual Retrieval implementation with visual chunk comparison. Preview context enrichment before/after embedding.

PersonAi is a local-first desktop app that lets you create and chat with AI-powered characters. Built with Tauri, React, Rust, Go, and Python, privacy-friendly experience with persistent local history, character customization, and full offline support. Perfect for storytelling, roleplay, or prototyping local LLM assistants.

🤖 AI Branding Assistant SaaS Web App powered by OpenAI API

Easily create tools from zod schemas to use with OpenAI Assistants and Chat Completions, inspired by tRPC

LinguFlow, a low-code tool designed for LLM application development, simplifies the building, debugging, and deployment process for developers.

CodexKit is an iOS SDK for building OpenAI-powered Codex agents with secure auth, threaded runtime state, streaming responses, and host-defined tools.

SuChat 是一个以简洁 AI 聊天为核心，并集成多种生活娱乐工具的跨平台应用，由 Flutter 开发并通过云端大模型 API 驱动（持续更新中……）A concise AI assistant and standalone handy tools in one.

This is the official code repository for the paper "Language Agents Meet Causality -- Bridging LLMs and Causal World Models"

An agent skill that teaches engineers how to build a coding agent from scratch using raw HTTP calls to an LLM API.

A framework to do multi-threading in T-SQL using SQL Server Agent jobs.

This is the code for paper "Correlation-aware Cooperative Multigroup Broadcast 360° Video Delivery Network: A Hierarchical Deep Reinforcement LearningApproach"

AI-powered MCP server that provides natural language control for browser automation. Built on Playwright with an intelligent sub-agent that handles tool orchestration, keeping browser automation details out of Claude's context window. Features OAuth authentication for Claude subscribers and seamless web task automation.

Git AI Copilot code review

🤖 Enterprise-grade AI agents for Flutter & React Native development with multi-agent orchestration, security (OWASP), accessibility (WCAG 2.2), and Google Stitch design integration

Secrets management for AI agents via MCP • @janeesecure

Your AI Interviewer That Prepares You Better Than Any Human Can.

TDD + requirements workflow skill for AI coding agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, etc.). Part of the Shelpuk agentic suite alongside Serena, Kindly Web Search, and Lad.

SQL transactions learning tool (AI ready)

ChatBot using FastAPI for faster processing

ATAT is an email client for AI Agents. Deploy dozens of AI agents through a single email address (IMAP/SMTP) using the OpenAI API. Just add credentials, create one email and the aliases you need, and you have agents over email. Just add credentials and it works.

Grey Haven's centralized repository for Claude Code agents, commands, and configs

Agentic RAG system grounded in Ethereum specs, discussions, papers, and codebases

CheckmateC2 is a custom agent and listener for the Havoc Framework (made by @Cracked5pider) that communicates entirely through Chess.com game collections and analysis boards using Base5 and FEN for data encoding.

AI-powered coding practice platform built with the GitHub Copilot SDK. Personalized challenges, real-time evaluation, and learning guidance based on your GitHub profile.

A small operating file for keeping long-running AI agent sessions from degrading. Capable models can do useful long work. The problem is not usually raw intelligence. The problem is operational drift: Stops AI coding agents from rotting during long sessions. One file, MIT licensed.

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out, Pipeline, Supervisor, Swarm, Glyph), and deploy as a REST/WebSocket API with RAG, memory, MCP tools, guardrails and OpenTelemetry observability.

An runtime for agents who collaborate with each other from one terminal. Optimized for steerability.

AI-powered natural language to SQL

The Mindset Your AI Is Missing Like hiring an entire team. Except it's free. 67 specialists across 12 professional fields — security auditor, business strategist, project manager, database architect, DevOps engineer, and more. Your AI reads your question and the right specialist responds. No menus. No switching. You just ask.

Network observer that tracks outbound connections from AI CLI processes (Claude Code, Codex, Gemini), attributing sockets to providers in real time with SQLite logging

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review, 3-layer memory chat, and a production FastAPI server.

See where your AI coding money goes. Self-hosted dashboard for Claude Code, Cowork, and Codex CLI — all data stays on your disk.

Portable Claude Code dev environment in a Docker container — multi-session, hook-driven, web-managed, with transparent SOCKS5. Runs on a Raspberry Pi.

基于滴答清单官方API的本地MCP服务，让用户通过LLM和Agent应用轻松管理待办事项

Desktop 'Paperclip' Companion for Claude Code & Codex

[Legacy] Optimized AGENTS.md system instructions for AI CLI/IDE agents. Token-efficient (Caveman ~75%), skills, subagent orchestration, security checks. Drop-in config for Qwen, Claude, Codex, Cursor и других.

CLI to inspect, screenshot, and control live Tauri development screens without running an MCP server.

Thymian is a language-agnostic, open-source HTTP conformance and API governance tool. It validates your APIs against RFC standards and your OpenAPI specification — statically, against live endpoints, and in recorded production traffic. Fully extensible with plugins and shareable custom rules.

Full-stack air quality analytics platform built with FastAPI, React, and MySQL. Aggregates multi-source PM2.5/PM10 data, performs multi-city comparison and time-series forecasting (SARIMAX), and integrates an LLM-based planning agent with tiered access, secure APIs, and PDF reporting.

These are my vibecoded experiments (generated by the agents themselves based on the docs of various tools) -- many of the skills are not properly vetted and I am simply improving them as I go along and notice mistakes done by the agents as they use a given skill.

An agentic coding and automation assistant, supporting both local and cloud LLMs.

Une suite complète de skills, agents et scripts marketing entièrement en français, conçue pour Claude Code.

Easy parallel project management for Claude Code agents.

Native Linux GUI for Claude Code agents. Rust + GTK4. Fast, light, no Electron.

Security-first AI agent daemon — the model proposes actions, the runtime decides what execute

🔒 Jail your AI agents — sandboxed Docker environments with network isolation for Opencode agents

8v is one binary that reads, writes, searches, checks, builds, tests, and formats code, using fewer input and output tokens than the agent's native tools.

Agent Skills for WordPress plugin development — security auditing, admin theming, license management, auto-updates, and more. Compatible with Claude Code, Cursor, VS Code Copilot, and all Agent Skills-compatible tools.

Web dashboard to run, monitor, and manage multiple Claude Code & Codex agents. Create agents with a cloneable task template. Real-time streaming, task pipelines, session resume, git worktree isolation, and remote access via relay — all from your browser.

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

Work anywhere with your favorite coding agents connected, coding sessions map 1-1 to chat threads, live updates and much more!

Multi-AI consensus MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel and synthesizes responses to reduce bias and improve accuracy. A Python implementation of the wisdom-of-crowds approach for AI decision making.

🧠 SBTI 赛博人格测试 — 30 道题解锁 27 种沙雕人格，测自己或测你的 AI agent | The viral cyber personality test as a nexu Skill

Production-ready Playwright test automation starter for teams and startups: strict TypeScript, Page Object Model, environment management, interactive runner, custom HTML reporting (with optional JIRA integration), quality tooling, CI/CD patterns, and agentic (MCP-ready) extensibility.

First formal security scanner for AI agent skills & plugins. Static analysis, supply chain verification, SBOM generation. 22 frameworks supported including MCP, LangChain, CrewAI.

Database MCP server for MySQL, MariaDB, PostgreSQL, and SQLite - with builtin PII redaction and write-prevention

AEP (Agent Element Protocol) v2.8 | Deterministic zero-trust total control and governance protocol for AI agents. | Reduce hallucinations to zero through architecture in all constrained domains of application. | LLMs gave you the engines, AEP gives you the control thrusters.

Agent Workflow Kit — Evaluation-first rules, templates, and Skill packages for AI-assisted software projects. Score risk, choose the smallest safe workflow, and generate practical AGENTS.md guidance for any coding agent.

A modern, cross-platform functional-first shell programming

73 deterministic Claude AI skills for Blender, Bonsai, IfcOpenShell and Sverchok. AEC Python development skill package

Real, runnable Flue agents on Cloudflare. Examples teach one product at a time; recipes compose. Every snippet ships an E2E test that deploys an ephemeral Worker, asserts, and tears it down.

🚀 多Agent协作智能知识库系统 — 五层可编排Agent架构 + RAG全链路 + 统一ToolRegistry，Spring Boot + FastAPI + React，核心亮点是 五层可编排 Agent 架构——Interface、Orchestrator、Tool、Memory、Evaluation 五层解耦，支持意图识别→问题改写→检索→充分性判断→答案生成的完整工作流。系统内置 Router / Retrieval / Ops / Inspection 多 Agent 协作，通过统一 Tool Registry 管理 AI 能力，支持 runId/traceId 全链路追踪、四级记忆体系与 Caffeine + Redis 多级缓存。适合Agent后端开发学习与简历展示

OSIM （Open Security Information Model）是 面向 AI 的开源安全数据标准化 项目，通过定义规范统一的安全数据 schema 语义层，破解行业数据碎片化难题，使安全团队、工具和 AI 系统能够在不同的数据源之间进行一致性推理和分析。致力于实现跨厂商、跨产品的安全数据无缝对接，为安全智能化升级与建立协同防御的核心数据打基础！

930+ AI-powered skills and 31 agent plugins for Claude Code, OpenAI Codex, Gemini CLI, GitHub Copilot, and Perplexity Computer. The largest open-source AI skills library.

A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Claude Code, Codex, Antigravity CLI, Copilot.

Expert skills, agents, commands, rules, hooks & output styles for Claude Code — session continuity + modern CLI tooling for real-world dev workflows

A Claude Code operating system for running a structured agency team. 25 specialized roles across four councils (Creative, Technical, Hardware, Delivery), enforced quality gates, PM-driven workflow, multi-client workspace governance, and per-project sprint tracking.

Postman for AI - design, evaluate, and debug LLM interactions with full transparency.

🤖 Визуальный конструктор Telegram ботов с drag-and-drop интерфейсом. Создавайте ботов без программирования, получайте готовый Python код для aiogram. React + TypeScript frontend, Express.js backend, PostgreSQL. Поддержка медиа, клавиатур, условной логики и аналитики пользователей.

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

A curated system of production-ready Claude Code skills with quantitative evaluation reports, golden test fixtures, and engineering workflow integration.

WaSP — WhatsApp Session Protocol. The missing infrastructure layer between WhatsApp and your application.

Build, deploy, and connect AI agents to SAP Joule via the A2A protocol on BTP Cloud Foundry — directly from Claude Code. Supports TypeScript (Express or CAP) and Python agents with LangGraph and SAP GenAI Hub.

Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.

🤖 Official Interactive Tutorial for OpenHarness – Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | 面向零基础的 AI Agent 交互式教程

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.

WizTree + AI 智能磁盘清理 Agent skill

Native Swift AI token usage monitor for the macOS menu bar — track Claude Code, Codex, Cursor, Copilot and other AI coding agent usage with a cute 2D/3D contribution graph.

Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.

Vim style TUI with Repository-Aware, Self-Evolving Agent That Understands Codebase in Real Time powered by Hybrid Semantic + Full-Text Engine

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

A comprehensive collection of expert AI Agent Skills for Google Gemini, featuring a powerful CLI to convert and optimize Claude Code agents for the Gemini ecosystem.

Manage, install, update, and trace agent skills (Claude Code, Cursor, Codex CLI)

Turn your codebase into readable format, for both Human and AI Agent.

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama) with FTS5 fallback.

InferSports Agent Skill — live Asian-priced football & basketball odds + scores. Read-only, keyless. Claude Code / Codex / OpenClaw.

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dispatch, sessions, async jobs, agent dialogues.

Reading copilot for Zotero powered by the DeepSeek API and scoped to your local papers, PDFs, and collections.