Browse agents

Elixir implementation of the Agent-to-Agent (A2A) protocol (https://a2a-protocol.org).

Multi-agent orchestration framework for Python — turn any agent setup into a CLI or server.

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

Agent registration, discovery, and reliable async messaging — in one broker.

Multi-agent simulation platform where AI agents self-organize on a Kanban board — built with LangGraph, Google A2A, and MCP.

Modular reference implementation covering a full-fledged agentic scenario end to end including Joule Integration via the A2A Protocol and Forecasting with RPT-1 as tool.

Skill-as-API: P2P agent collaboration over XMTP. Call remote skills without exposing code. E2E encrypted, revocable trust, async delegation. Zero deps.

Everything you need to build, deploy, and collaborate with agents. Ride the llama, avoid the drama.

UI components for editing, viewing, and testing agents that implement the Agent2Agent (A2A) protocol.

A single front door for all your AI agents and MCPs

A2A agent server enabling Google Calendar scheduling, retrieval, and automation

Privacy-first, AI native agents For E-Commerce (and beyond), create skill (langgraph based workflow), tasks, agents, graphically with low code or no code. Deploy agents across network.

A2A agent implementing OpenDeepResearch

"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."

Sera for Agents — landing page, three agent templates, bundled CLI, and a working x402 service. Built on the Sera MCP.

Autonomous multi-agent system built using LangChain and LangGraph that orchestrates collaborative agents—Supervisor, Researcher, Writer, and Critiquer—to automatically gather information, generate detailed research reports, refine output, and visualise the workflow as a graph. Includes a Streamlit web UI and optional Graphviz visualisation.

ServiceNow MCP Server and API Wrapper

A2A commerce negotiation runtime + DeepSeek Harness (dsh) plugin. 安装 Kiwi，让 AI 买家找到你的商品、向你询价；库存、底价和客户数据仍留在你的系统中。

A modular framework for building complete AI solutions. It's mostly a Rust framework with a subset of it ported to Deno.

Type-safe, async Rust SDK for the Agent2Agent (A2A) protocol, built to the final v1.0.0 spec — JSON-RPC, REST, WebSocket & gRPC for building interoperable AI agents

Secure Retrieval-Augmented Generation (RAG) with role-based access control using Mastra AI orchestration, with JWT Secure, also Deep Research built with Cedar & Next.js. Gemini, OpenAI, Openrouter, & Gemini CLI usable. Also exposes tools, agents as MCP Server Also A2A Agent Cards

Demos and starter code for building agentic finance apps with Crossmint

A Java implementation of the A2A protocol, that's agent to agent scenarios with google a2a protocol

Murmur Connect (Murmur) — encrypted agent-to-agent messaging for AI coding agents. Claude Code, Codex and any MCP client talk across machines: MCP-native, E2E encrypted (XChaCha20-Poly1305), NATS transport with optional JetStream durability, cross-org federation, A2A interop. Mac and Windows apps, CLI on npm.

Drop-in OIDC & Google A2A auth + Weaviate memory for Ollama, vLLM and any local LLM server.

Secure, auditable agent-to-agent communication framework

Langgraph-SelfPaced-Course Step by Step

Sample Custom Industry AI Agents built with Joule Studio(LCNC), Joule Studio Code Editor(Low-Code), SAP Cloud SDK for AI (Pro-Code) and Agent Integration

An extensible AI agents framework

Command-Line Agentic Refactoring of Java Code

Demo with multiple AI agents using A2A (agent-to-agent) with the Strands Agents SDK.

Infrastructure for AI agent swarms - 88 MCP tools, A2A, mesh VPN, CDP browser, 2FA

Expose Codex through A2A with an inbound server surface and embedded outbound client.

Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

Mastery AI Apps Dev Workshop: Jumpstart your journey into AI-powered app development! This hands-on workshop guides you through building real-world applications using cutting-edge AI tools and cloud technologies. Perfect for beginners and enthusiasts eager to turn ideas into powerful solutions. Join us and master the future of app development!

Steerable Harnesses for DeepAgents — Orchestra🪶

HTLC/PTLC deal-making for agents that meet in a chat room — offer, accept, lock, reveal, refund, as signed room messages. The room coordinates; a settlement rail holds the money. Alpha: no rail holds value yet.

Self-hosted AI company OS for solo founders: autonomous agents, ERPNext business memory, and owner-visible governance.

Zero trust network for governed agent-to-agent communication - discovery, engagement contracts, session governance, and auditable collaboration across organizational boundaries. Built on OpenZiti. A2A compatible.

Typed Kotlin DSL framework for AI agent systems.

A production-ready, multi-channel AI agent for AIOps, Kubernetes management, and automated remediation — built on FastAPI with support for GitHub Models and Google Gemini LLM backends.

Healthcare AI Agents - Demo solution

BuyWhere MCP server — search 300M+ products across US, Singapore & SEA via Model Context Protocol. Agents self-register a free key in one POST (no email): api.buywhere.ai/v1/auth/register?verify=false

🚀 Curated resources for Google's Agent Payments Protocol (AP2), A2A & x402 — blogs, videos, repos & specs. Contributions welcome!

A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol

Practical GenAI-Eshop application using Semantic Kernel, multi-agent orchestrations, Mcp tools, A2A Agents, Semantic Search, Aspire and more.

a secure chat protocol for AI agents

One open A2A 1.0 mesh for Claude Code, Codex, Cursor, Cline, Continue and Gemini.

Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector

An Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in Rust.

AI Workflows For Kubernetes

Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.

agents.txt is a lightweight, machine-readable capability declaration layer for websites in the agentic web: a protocol-agnostic discovery file that publicly announces what agent-interaction capabilities a site supports, without embedding the implementation details of any specific protocol.

Heterogeneous AI agents (Claude Code + Codex + Agy + Kimi) collaborating in Telegram groups over A2A-TG — a generation-counted envelope protocol. Self-hosted.

SUPERVAIZER is a toolkit built for the age of AI interoperability. At its core, it implements Google's Agent-to-Agent (A2A) protocol, enabling seamless discovery and interaction between agents across different systems and platforms.

Go implementation of the Agent-to-Agent (A2A/a2a) protocol

This project demonstrates Agent-to-Agent (A2A) conversations using LangGraph with the A2A protocol. It includes implementations in both **Python** and **TypeSc…

A policy enforcement runtime for AI agents

First-class protocol and framework for enabling collaborative intelligence and communication across specialized Data Agents.

AI agent stack that combines A2A messaging + x402 micropayments + ERC‑8004 identity(trustless agent).

Composition root for production agent services — fork, customize, ship. Built on the foundry-agent-* packages.

Open protocol for agent-to-agent B2B commercial negotiation. Specification, reference implementation, and SDK.

nano-degree in Agentic AI

The enterprise-grade CrewAI alternative for Go. Orchestrate strictly-typed, parallel AI agents with LangGraph-style Flow persistence, distributed A2A protocols, Model Context Protocol (MCP), and Human-in-the-Loop training.

Connect agents across runtimes, frameworks, and teams.

Universal MCP Server for finding + connecting to agents anywhere on the planet. https://hol.org/mcp

Kubernetes-native platform for orchestrating distributed multi-agent systems.

An interactive command-line interface that uses the Agent2Agent (A2A) & Model Context Protocols (MCP) to manage multi-agent systems.

kbs_agent_a2a 智能体协议适配中间件

Repo migrated to a2a-community ogranization https://github.com/a2a-community/a2a-ui

Containerized A2A-native agents with simple setup

Genesis Mind Interface — desktop chat UI for Genesis agents

LLM agent running on your local PC, Compatible with various LLM models. Can do anything.

Solana Protocol Design for Agent and MCP Server Registries

DSH 的 A2A v1.0 双端插件:Client 发现远程 Agent 并映射为工具,Server 对外提供 JSON-RPC/SSE 端点与连接面板 ｜ A2A v1.0 dual-mode DSH plugin: A2A client (skills as tools) + A2A server (JSON-RPC/SSE) with dashboard.

Multi-agent demo with Google ADK on Vertex AI Agent Engine — every LLM, A2A, and MCP call routed through Apigee X for API-key auth, per-user quotas, and token analytics.

🐙 A self-hosted AI Agent companion. Powered by persistent memory (GHOST) to remember, learn, and evolve as your digital partner.

Agent2Agent (A2A) protocol implementation in Ruby. Under development. It will be integrated with web frameworks SOON.

List of open sourced MCP servers. MIT license. Managed by AgentX with love.

agent-to-agent comms, no vendor in the middle — telephone-exchange protocol for AI agents. wire dial / wire send / wire pending / wire accept.

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm traffic between callers and agents.

Runnable code from the AI Season AI Agents Bootcamp (Cohort 01): LLM APIs, RAG, agent harness, LangChain, multimodal agents, A2A, and an LLM from scratch. Taught in Urdu + English.

ShadowScan discovers evidence of AI agents across code, identity, gateways, low-code, SaaS, and cloud. Live or offline.

Azure-native A2A Technology Demonstrator

OpenSpawn — An open source multi-agent coordination platform

A example A2a Server with Human-In-The-Loop feature.

Multi-agent system for drafting and managing GitHub issues. Built with BeeAI Framework, integrated via GitHub MCP, and consumable through Agent Stack CLI & UI via A2A.

Platform where AI agents autonomously build, review and deploy real software. Connect any LLM agent over HTTP or MCP.

Agent 2 Agent (A2A) Validation tool (a2v) alternative to CLI

Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP

Curated directory of AI agents, agent cards, runtime endpoints, container images, and contribution-ready metadata.

Sample Agents and Tools for Rossoctl platform

Local-first agent that drives Claude Code and Codex over ACP. Desktop app, git-URL plugins, A2A 1.0. MIT.

A Python-based API server for creating AI persona agents using Google A2A protocol and Model Context Protocol (MCP) tools integration.

A curated list of protocols and standards for AI agents — MCP, A2A, ACP, AG-UI, AP2, x402, and 50+ more, organized by stack layer

Multi-agent solution on Azure Container Apps with Google Agent2Agent

A catalog of integration patterns for multi-agent AI systems — the missing vocabulary between Enterprise Integration Patterns and the agentic era.

A2A implementation in Healthcare

A Go-native framework for LLM agents, with OpenTelemetry observability built in.