Python

AG2 (formerly AutoGen): The Open-Source AgentOS by Microsoft. Features native A2A support with A2aAgentServer and A2aRemoteAgent built-in classes for multi-agent conversations.

Official A2A python sample agent: A2A MCP Without Framework

Official A2A python sample agent: A2A MCP

Official A2A python sample agent: A2A Telemetry

Official A2A python sample agent: Adk Cloud Run

Official A2A python sample agent: Adk Expense Reimbursement

Official A2A python sample agent: Adk Facts

Official A2A python sample agent: Airbnb Planner Multiagent

Official A2A python sample agent: Analytics

Official A2A python sample agent: Any Agent Adversarial Multiagent

Official A2A python sample agent: Azureaifoundry SDK

Official A2A python sample agent: Beeai Chat

Official A2A python sample agent: Birthday Planner Adk

Official A2A python sample agent: Content Planner

Official A2A python sample agent: Crewai

Official A2A python sample agent: Github Agent

Official A2A python sample agent: Headless Agent Auth

Official A2A python sample agent: Helloworld

Official A2A python sample agent: Langgraph

Official A2A python sample agent: Llama Index File Chat

Official A2A python sample agent: Mindsdb

Official A2A python sample agent: Semantickernel

Official A2A python sample agent: Signing And Verifying

Official A2A python sample agent: Travel Planner Agent

Official A2A python sample agent: Veo Video Gen

Python A2A is a powerful, easy-to-use library for implementing Google's Agent-to-Agent (A2A) protocol. It enables seamless communication between AI agents, creating interoperable agent ecosystems that can collaborate to solve complex problems.

Aser is a lightweight, self-assembling AI Agent frame.

The A2A x402 Extension brings cryptocurrency payments to the Agent-to-Agent (A2A) protocol, enabling agents to monetize their services through on-chain payments. This extension revives the spirit of HTTP 402 "Payment Required" for the decentralized agent ecosystem.

Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks.

NL2SQL - Ask questions in plain English, get SQL queries and results. Powered by LangGraph.

Convert any PydanticAI agent into an A2A server with a single line. Framework-agnostic A2A server implementation built on Starlette/ASGI by the Pydantic team.

Scan A2A agents for potential threats and security issues

Portable , scalable , secure AI Agents

Easily convert agents and orchestrators from existing agent frameworks (CrewAI, LangGraph, LlamaIndex, OpenAI) to A2A servers. Like Vercel for A2A agents.

AgentX python SDK. Build multi-agent AI workforce.

A2A Protocol client and developer toolkit.

Official Technology Compatibility Kit for A2A protocol. Comprehensive test suite for v0.3.0 compliance with multi-transport testing (JSON-RPC, gRPC, REST) and compliance reporting.

A cookiecutter template for Python agent projects that use uv for dependency management

Multi-agent healthcare system on IBM's Agent Stack. Features a HealthcareAgent (orchestrator), PolicyAgent (insurance coverage from PDF), ProviderAgent (doctor lookup via MCP), and ResearchAgent (web health research). Agents communicate via the A2A protocol.

Instead of dumping 1000+ tools into a model’s prompt and expecting it to choose wisely, the Unified MCP Tool Graph equips your LLM with structure, clarity, and relevance. It fixes tool confusion, prevents infinite loops, and enables modular, intelligent agent workflows.

Open Source A2A Protocol Adapter SDK for different agent frameworks. Wrap CrewAI, LangGraph, LangChain, and n8n agents in A2A with just 3 lines of code.

Cloud-native AI agents orchestration platform. Build agent networks in no code, bring your own agents or connect one with A2A and MCP. Both self-hosted and Cloud-hosted.

A collection of Summoner clients and agents featuring example implementations and reusable templates

An open-source Agent2Agent (A2A) compliant server that provides Google Maps capabilities to other agents via a standardized protocol. Supports geocoding, directions, places search, and distance matrix.

Cognisphere ADK is an AI agent development framework built on Google's Agent Development Kit (ADK)

General-purpose enterprise orchestrator on Google ADK + Vertex AI Agent Engine. Multi-agent system with risk tiers (R0-R4), policy gates, evidence bundles, and Mission Spec v1 workflows.

Scalable agent registry for AI agents using A2A protocol AgentCard with semantic search. AWS serverless (Lambda, S3 Vectors, Bedrock). Python SDK & React Web UI.

A2A Registry

Azure-native A2A Technology Demonstrator

kbs_agent_a2a 智能体协议适配中间件

A community-driven, open-source directory of live, hosted AI agents using the A2A Protocol

Multi-agent solution on Azure Container Apps with Google Agent2Agent

🐇 The 'RabbitHole' framework provides the tools for asynchronous A2A communication and task management. 📡🐇 ✨ Build powerful AI agents that communicate and collaborate.

A2A protocol demo: Orchestrated AI agents for retail using Google ADK, LangGraph, and Vertex AI Search

A production-ready agent server built with LangGraph that implements the Agent-to-Agent (A2A) protocol

The core of `aipflow` is **task orchestration and execution specifications**. It provides a unified task orchestration framework that supports execution of multiple task types. The core is **pure orchestration** with no LLM dependencies - CrewAI support is optional.

Build and deploy an autonomous Devto Agent capable of interacting with the Dev.to platform, powered by A2A (Agent-to-Agent) and MCP (Model Context Protocol)

Agent-to-agent task marketplace where agents post tasks, pick up work, and earn credits. Live at pinchwork.dev.

Official ServiceNow A2A client for invoking ServiceNow AI agents via the A2A protocol. Includes OAuth authentication, ITSM incident categorization, and enterprise service management workflows.

Innovative AI agent implementations using LangGraph—featuring ReAct, RAG (Corrective, Self, Agentic), chatbots, microagents, and more, with multi-AI agent systems on the horizon! 🤖🚀

AI agent examples run on AWS EKS. Shows Terraform, Vault, and Agent2Agent.

Open-source gateway and community to make AI agents interoperable using Google's A2A protocol – like Hugging Face, but for agents.

Agentic Workflows

LeapRAG is an open-source platform that integrates advanced RAG technology with Google’s A2A protocol, enabling users to build context-aware, data-driven agents. These agents are automatically A2A-compliant and can be discovered and used by any compatible client without extra development.

Run multiple agents on single A2A Server

AI-powered news intelligence with 8 Vertex AI agents monitoring 50+ sources. Real-time executive dashboard, daily briefs, and smart alerts. Built on Firebase + A2A protocol.

A production-ready multi-agent system showcasing Agent Communication Protocol (ACP) and Model Context Protocol (MCP) capabilities through a collaborative research workflow.

Implementing CurrencyAgent with A2A Python SDK

This repository features a collection of agentic AI projects across various domains, showcasing practical applications of AI agents with different frameworks, techniques, and tools.

AgentRanking system for A2A (Agent to Agent) ecosystem

it built itself

Multi-agent customer support system with Google ADK & Gemini 2.5 Flash Lite. Kaggle capstone demonstrating 11+ concepts. Automates 80%+ queries, <10s response time.

Collection of some interesting Generative AI usecases implementation.

Multi-agent-driven GenerativeUI

Ziran uses advanced attack methodologies including multi-phase trust exploitation and knowledge graph analysis to uncover vulnerabilities in AI agents before attackers do.

Agent to agent protocol using MQTT

Google A2A protocol demo where a CLI client works with a scheduling agent, which in turn coordinates three specialized player agents to arrange a Table Tennis game.

Agent-to-Agent Protocol Specification — agent:// URI scheme for AI agent identity and discovery

Notes on gen AI concepts and tools. POC on agentic AI with MCP, A2A, langGraph, langchain, openAI LLM, crewAI

Checks for jobs continuously (24×7) on a schedule you control Parses job descriptions, extracts skills & keywords, and scores matches to your preferences Sends notifications (Email + Telegram bot supported in MVP) Generates tailored, job‑specific CVs (Markdown → optional PDF via Pandoc)

The official CapiscIO CLI tool for validating A2A agents. A lightweight Python wrapper that automatically manages the capiscio-core binary.

Runtime security middleware for A2A (Agent-to-Agent) protocol agents. Provides always-on validation, signature verification, and rate limiting for AI agent interactions.

A multi-gent system that provides comprehensive financial and corporate intelligence for publicly traded companies.

🤖 Streamline your debugging process with GENAI, an AI-driven assistant that helps identify and fix code issues efficiently.

🌍 Automate webpage content audits with GEO Agent Crew, extracting insights and optimization suggestions using cutting-edge AI tools for better online performance.

Recipes for scalable, streaming-first multi-agent systems in cloud. It combines A2A protocol, OpenAI Agents SDK, and Dapr building blocks (PubSub + Virtual Actors) to show how AI agents can stream outputs and coordinate at scale.

Vertex AI Agent Engine command template using Google ADK + A2A protocol. Zero-legacy scaffold with Terraform modules, strategic orchestration tool, and CI/CD pipeline.

Multi-Agent Kubernetes Cost Optimization System

A safety-first multi-agent mental health companion with real-time distress tracking, triple-layer guardrails, and evidence-based grounding techniques. Built for Kaggle × Google Agents Intensive 2025 Capstone (Agents for Good Track)

Machine 2 Machine Protocol, x402 + A2A + MCP

An agentic AI assistant, that is helping users with math queries to solve and explain them to the user.

A multi-agent e-commerce system built with Google ADK and MCP. Features microservice architecture with A2A protocol communication, enabling customer consultation, real-time inventory lookup, and automated order processing.

Automated daily news generator using LLMs and vendor search, with date-organized, source-backed articles.

MCP-based agentic AI system enabling LLMs to fetch and reason over real-time global weather data using standardized tool invocation. Built with MCP Server/Client, Llama 3, and external APIs to deliver low-latency, hallucination-free weather intelligence through protocol-driven workflows.

This is a beginner friendly repo showing how to build multi-agent AI systems using the A2A protocol.

A distributed multi-agent system that orchestrates complex tasks across specialized AI agents using A2A (Agent-to-Agent) protocol, MCP (Model Context Protocol) and LangGraph.

a Python proof-of-concept (PoC) application for security formal verification of LLM Agents using Google A2A (Agent-to-Agent) protocol.

U.S. governance-inspired coordination strategies in multi-agent AI systems

A production-ready Python package for integrating A2A protocol agents into LangChain/LangGraph. Enables stateful conversations, streaming, multi-turn context management, and seamless LLM tool binding with A2A agents.

This sample demonstrates a conversational agent built with LlamaIndex Workflows and exposed through the A2A protocol. It showcases file upload and parsing, conversational interactions with support for multi-turn dialogue, streaming responses/updates, and in-line citations.

A comprehensive travel planning system built with Agent2Agent (A2A) protocol, featuring specialized AI agents for hotel booking, car rentals, currency conversion, and travel coordination.

Economic settlement extension for the A2A protocol — escrow-based token payments for agent-to-agent tasks.

An educational demonstration of Google's Agent-to-Agent (A2A) protocol v1 through a multi-agent storytelling system. Three AI agents collaborate iteratively to adapt and enhance stories, showcasing real-world A2A communication patterns.

A multi-agent AI system that scans websites for security vulnerabilities. It uses the A2A (Agent-to-Agent) protocol for orchestration and MCP (Model Context Protocol) for tool integration. Specialized agents work together: they gather threat intel, crawl the site, analyze vulnerabilities, and produce a report.

A unified AI agent system integrating Retrieval-Augmented Generation (RAG), Agent-to-Agent (A2A) communication, and Model Context Protocol (MCP) for document processing, web search, and intelligent task delegation.

AI Agent Discovery Platform — Find any AI agent by capability. 24K+ agents indexed.

OpenAGI Codes AI Agents Basics

Production-grade multi-agent system that analyzes stocks using 6 specialized AI agents communicating via the Agent-to-Agent (A2A) protocol.

Our planner has context sharing,in process MCP tool integration,structured output using pydantic(md,json), Task monitoring & Logging using callback functions, A2A protocol and used interoperability - e.g. one agent defined using ADK another using CrewAI.

🎥 Summarize YouTube videos into clear, actionable insights with AI, allowing you to grasp key points quickly and easily.

Agent-to-Agent (A2A) communication protocol for inter-agent coordination and a Model Context Protocol (MCP)-inspired architecture for interacting with external tool servers.

An AI agent specialized in code generation, review, debugging, and software development assistance

An AI agent specialized in data analysis, processing, visualization, and insights generation from various data sources

a Python framework for building and consuming Agent‑to‑Agent (A2A) servers. It draws inspiration from the popular FastMCP project but targets the A2A protocol directly.

AI-powered market intelligence agent for crypto and forex analysis with comprehensive market summaries

🤖 Curiosity Squad – Autonomous Multi-Agent Mars Exploration - Capstone Project

Kai is an AI-powered investment analysis system that uses a multi-agent debate architecture to provide explainable, trustworthy, and data-driven investment insights.

Development with Agentic tools like ADK, MCP, A2A for creating agentic workflows.

AI-powered multi-agent system for creative content generation and studio workflow automation

Google-ADK

Multi-agent system built on the A2A (Agent-to-Agent) protocol that demonstrates distributed agent coordination for scheduling football games.

Muvius is a powerful framework for building and managing AI agents with advanced memory systems and seamless inter-agent communication. It provides a structured approach to creating intelligent agents

ADK-based SDR orchestration on Vertex AI Agent Engine. Routes leads through Research, Enrich, and Outreach agents with BYO data provider keys (Clay, Apollo, Clearbit).

An AI agent specialized in project planning, task management, strategic planning, and workflow optimization

Pubroot — AI peer-reviewed knowledge base for the agent era. 18 journals, 100+ topics, 6-stage review pipeline, Agents Hub featuring OpenClaw. Submit via GitHub Issues, reviewed by Gemini + Google Search grounding. MCP server, A2A Agent Card, agents.txt. Zero fixed costs.

Create remote chat agent using agent2agent protocol

An AI agent specialized in research tasks, information gathering, and analysis using advanced search and synthesis capabilities

A lawyer for the agent economy. AI agents can request contract review, risk analysis, and legal guidance via A2A protocol.

A multi-agent AI helpdesk system for smart campuses using locally-hosted LLMs (Ollama/LM Studio). Features specialized agents for academics, finance, and events with MCP-style communication, FastAPI backend, and React chat interface. Runs completely offline with modular, extensible architecture.

An A2A wrapper for tencent/SongGeneration on HuggingFace Space

Multi-agent ops template: A2A protocol + Agent Cards + task delegation + OpenTelemetry observability

What would Tagore write, if he knew our history

ToolBox is a collection of tools and functions designed to be used in conjunction with Language Model (LLM) agents. This repository provides utilities for interacting with APIs, handling geolocation, weather data, and more.

Enterprise-grade Python authentication client for Traylinx Sentinel API with full A2A Protocol support