Code agents

Terminal Agent is a DevOps-focused intelligent terminal assistant for system diagnostics, application deployment, service monitoring

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀

The control layer for AI agents. 1,200+ rules, 12 domains, 10 frameworks, 4,000+ adversarial payloads. Discover. Assess. Test. Monitor. Comply.

A brief introduction to agentic coding principles and practice

Telegram Bot API wrapper for Node.js written in TypeScript

An MCP (Model Context Protocol) server for performing accessibility audits on webpages using axe-core. Use the results in an agentic loop with your favorite AI assistants (Amp/Cline/Cursor/GH Copilot) and let them fix a11y issues for you!

60 self-contained, Dockerized vulnerable web applications for evaluating AI-powered penetration testing agents. Covers modern tech stacks (Node.js, Python, Go, Java, PHP, Ruby) across diverse vulnerability classes from basic injection to multi-step exploit chains.

Agentic closed loop with async capabilities

Save coding agents' conversations in Git Notes, automatically

a curation of questionably-useful coding agent plugins

credit score for context

AI Agent Orchestrator for Claude Code

A production-ready, all-in-one Docker image designed for AI agents and autonomous systems that need to execute code across multiple programming languages.

AI Agent which can do any kind of Browser Automation Task & Web Scraping, just using a single prompt!

FxChartAI AI-Agent Trading EA is an open-source MQL5 Expert Advisor for MetaTrader 5 that trades using signals from FxChartAI. It employs trend confirmation, candle tail/trendline analysis, and dynamic order management. Free for personal & commercial use. Contributions welcome.

🧠 A production-grade, agentic RAG platform for portfolio intelligence, combining LangChain, Chroma/FAISS, Hugging Face embeddings, and Ollama with dynamic entity extraction, backend API tool-chaining, and a real-time interactive assistant across deploy-ready frontend, backend, and infrastructure stacks.

A simple API server for performing Retrieval-Augmented Generation (RAG) of text based on content from a PostgreSQL database using pgvector.

A desktop coding agent built with Mastracode and Electron.

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

Tiny Agent: Production-Ready LLM Agent SDK for Every Developer

A modular and AI-powered appointment booking agent designed to streamline scheduling for businesses, starting with dental clinics. Built with LangGraph, Composio, and Bland.com, it integrates Google Calendar and Gmail to manage appointments, send confirmations, and handle voice interactions.

Embedded single file SQL database written in Golang

Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.

Investigation toolkit for Claude Code: case management, OSINT, structured analytic techniques, chain-of-custody evidence capture, and bundled threat-intel MCP servers.

🐾 ClawPilot — your OpenClaw copilot. Security-first agent skill for AI coding assistants. Supports 14+ chat platforms.

Shared config, skills, and update scripts for Claude Code, Codex, and Gemini CLI

🦞 Low-latency, limited-context AI harness for private on-device homes.

Governed infrastructure for internal tools and AI agents

Browser automation MCP server for Claude, powered by Puppeteer.

A JetBrains IDE plugin that integrates OpenCode — the open-source AI coding agent — directly into your development workflow.

Run any OpenAI-compatible model in Xcode Agent Mode. Use local models (Ollama and LM Studio) with no API key, or route to cloud providers with per-provider keys. Includes GUI, CLI, and over a dozen MCP tools.

This project includes code for using the AsyncWebRL and WebGym frameworks to train web agent models.

High-performance proxy router for LLM APIs with automatic load balancing, rate limiting, and fail2ban protection

Đây là bộ SKILL, RULES, COMMANDS do Anh Tester xây dựng dành riêng cho cộng đồng Tester để thiết lập AI Agent trên Claude Code hỗ trợ kiểm thử phần mềm.

Web dashboard for the pi coding agent — multi-session chat, file browser, doc collaboration, terminal, and more

🌍 30 AI-powered geoscience skills for Claude Code, Cursor & GitHub Copilot. Seismic, well logs, 3D modelling, inversion, geostatistics, spatial regression, NetCDF, and more.

Native web search for OpenCode, powered by your model's built-in search capability. No extra API keys or search services required. Inspired by Claude Code's WebSearch tool.

A minimal, low-friction memory system for Claude Code

Multi-instance Claude Code manager with intelligent translation proxy. Use Claude Code with Grok, ChatGPT, DeepSeek, Gemini, Kimi, GLM, Ollama and more.

CLI for AI-powered web scraping, structured data extraction, web search, multi-page crawling, and scheduled page-change monitoring powered by the ScrapeGraph AI API. Turn any URL into markdown, HTML, screenshots, links, images, summaries, or brand assets; pull structured JSON with a prompt + schema; watch pages on a cron with webhook alert

Turn Claude Code into a design-first Kotlin Multiplatform pipeline — an Android + iOS feature from one prompt, with architecture that doesn't drift. MIT.

AICodePilot is an AI codebase understanding and development assistance system based on LLM Agents, designed for programmers. It supports codebase analysis, semantic code retrieval, code Q&A, log analysis, tool calling, and development assistance.

X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent

Multi-Agent works on native GUI desktop. Supports skills and IM channel, build-in a IDE for light development. Built on the shared piscis-engine kernel.

A channel for Codex & other AI agents to access a live Claude Code session.

Public documentation and support hub for ECC Tools, the GitHub App that turns repo history into reusable workflows, skills, rules, hooks, audits, and rollout plans for AI coding agents.

External-agent-first orchestration for AI coding workflows: dispatch to Antigravity CLI, Grok CLI, Claude Code, and Codex CLI with structured receipts, recovery, and low-token wait/watch.

The first AA-native x402 payment stack on NERO Chain — facilitator, SDK, audited settlement contract, and a public playground showing AI agents paying APIs in USDC with paymaster-sponsored gas.

Code for "Agentic Very Long Video Understanding" (EGAgent) [ACL 2026 Main]

Reuse your Kimi Code (Moonshot) Coding plan inside pi-coding-agent

A WebSocket-based inter-terminal communication system that creates a local network between multiple Pi coding agent terminals. Enables terminals to discover each other, exchange messages, and orchestrate work across agents, all automatically on localhost.

Claude Code skills for developers who code like cats — never more effort than the problem requires.

✨ A programmable content review harness for AI agents. The slop filter your agents are missing.

Local-first analytics dashboard for AI coding sessions. See what you built with Claude Code & Codex CLI.

Email gateway that opens a Claude Code session per inbound AgentMail message (cmux or Ghostty)

Your codex login → a full ChatGPT Plus/Pro account (every model, deep research, image gen, code exec) inside Claude Code, Codex & any MCP client. One-line install.

React Native + Expo template with Feature-Sliced Design (FSD) architecture and AI Agent Harness for Claude Code

Security skills for AI coding assistants and agentic systems

a TypeScript-based CLI coding agent built with OpenAI SDK and Ink

Vibe CSA (Code Security Audit)，是一款基于 AI Agent 架构的代码审计工具，采用多 Agent 并行执行架构，用“上帝视角”静态审计源代码，用“实战模拟”动态验证漏洞，保证了 Web 漏洞挖掘的全面性和准确性，输出稳定可靠的安全报告，并提供可落地整改建议。

Evidence-based pruning for your AI-agent stack — scan, report, and safely prune unused skills/MCP servers/agents using real transcript evidence

The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.

Open-source engine that turns any website into API for AI agents.

AI coding assistant configurator. Detects stack, generates agent configs for Claude Code, Cursor, Windsurf.

Create or audit AI agent skills. Synthesizes source material bottom-up into strategic, interactive skills. Works with Claude Code, Codex, OpenCode, and 35+ agents.

🤖 零基础 AI 学习之路 | 30 天从小白到实战 | Python → 机器学习 → 深度学习 → Agent应用 → 项目实战 一个完整的 AI 入门教程，包含： 📚 30 天系统教程（费曼学习法·大白话讲解） 💻 9 个完整项目（图像分类·文本生成·目标检测·模型部署·AI客服·数据分析·智能投研·RAG·AutoGPT） 🎯 200+ 代码示例（可直接运行） 🆓 完全免费开源（MIT 许可证） 📖 配套教程：CSDN专栏 https://blog.csdn.net/m0_67081842 ⭐ 如果有帮助，欢迎 Star 支持！

Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.

Intent as Code | the workflow language for AI. One file, 4 verbs, one Rust binary. Local-first, any model, AGPL-3.0. 🦋

Open-source alternative to Maestri. Native macOS multi-agent orchestration canvas — connect, coordinate & deploy Claude Code, Codex, OpenCode, Gemini CLI agents visually.

gradio mcp multi-agent research code-generation ai-assistant python web-search

transformers safetensors qwen2 text-generation code chat

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Frappe Agent Skills gives AI coding assistants structured Frappe knowledge for DocTypes, APIs, Desk customization, frontend apps, reports, testing, and production patterns.

Tools for testing APIs with AI agents

CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vulnerabilities to generating proof-of-concept to writing patches.

The GTM co-founder you don't have. Open-source GTM Agent Skills for technical AI/dev-tool founders building alone: positioning, first users, launch, pricing. Built from real dev-tool GTM experience, sharpened by Frankl & Czakon. MIT.

Official code for the paper "A New Role for Relevance: Guiding Corpus Interaction in Agentic Search"

Local web console for Pi Coding Agent — models, agents, sessions, usage, OpenVL

Accelerates agentic development in legacy codebases. Creates context and backlogs for agents via pretty good static analysis. Saves inference tokens.

The easiest way to manage semantic versioning and generate CHANGELOG.md automatically for AI-native projects.

Sistema de gestión de proyectos, impulsado por OpenCode y ClaudeCode como asistentes de CEOs, CTOs, PMs, Scrum Masters, aquitectos, desarrolladores/as, QAs... con capacidad de delegar implementación técnica a agentes de IA.

基于 Sub2API 二开的 AI API 网关：多平台账号接入、账号共享与广场调度、Token 级计费与分账

NVIDIA Fleet Intelligence Agent - Host agent for GPU telemetry collection and attestation

A simple but powerful TUI coding agent. Fully native rust, cross-compatible.

Curated DESIGN.md files for inspiring websites — design systems decoded for AI agents. By Sparkbites.

Codex-native CLI for AI-assisted game development, scaffolding local projects with studio roles, bounded prompts, and hard-failing validation.

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle, runs codex exec, validates the JSON response with jq.

ZKE（Z Kubernetes Engine）：macOS 风格的 Kubernetes 多集群控制台，基于 Server + Agent 与 QUIC/mTLS，适用于私有云、混合云及边缘环境。

🦞 Non-destructive upgrade tool for existing OpenClaw installations. Merges Clawdboss improvements without destroying your customizations.

Context-aware Open AI chatbot for Telegram using aiogram-3.

企业级 LLM API 快速集成系统，支持OpenAI、Azure、文心一言、讯飞星火、通义千问、智谱GLM、Gemini、DeepSeek、Anthropic Claude以及OpenAI格式的模型等，简洁的页面风格，轻量高效且稳定，支持Docker一键部署。

Code for the paper "MARL-iDR: Multi-Agent Reinforcement Learning for Incentive-based Residential Demand Response"

AI-first Blazor CSS and Component library, ultra-generic, lightweight and optimized for AI agents

Redistributable ChatBot APIs with ChatGPT + RAG(Agents) with metadata, Nest.js + Langchain

Purpose-built security agent for hosted runners

☁️ DevOps & Cloud Infrastructure skill suite derived from VoltAgent/awesome-agent-skills.

Designed for offline use, this RAG application template offers a starting point for building your own local RAG pipeline, independent of online APIs and cloud-based LLM services like OpenAI.

Teach ChatGPT the Alda music programming language, show it some superb code, and consult with it to compose a melody.

JavaScript library for OpenAI's Chat Completion API. Comes with conversation history management, parameter configuration, callable functions and plugin support!