KoPass 公開カタログで測定された A2A リポジトリ。
Open-source self-improving AI agent for Windows: 5 native in-process ASI tools, one heartbeat over 10 subsystems (replaces ~84 cron jobs), and an A2A Global Mesh where every instance talks to every other instance. Apache-2.0, runs local.
A TypeScript implementation of the Microsoft Agent Framework programming model, with semantic parity to the official .NET, Python, and Go implementations. Independent community project.
Let your AI agent talk directly to someone else's. One pairing code, end-to-end encrypted, no public IP. MCP server for Claude Code, Codex, Cursor, Gemini CLI and grok.
Catalog every AI agent in your Backstage instance — across kagent, ARK, and any A2A service — with live agent cards and LLM-gateway usage. It's 10 PM. Do you know where your agents are?
Simplified Google A2A Protocol Implementation for Azure OpenAI
A fully autonomous multi-agent system for end-to-end data analysis. Upload any CSV → Agents perform Profiling → EDA → AutoML → Verification → Notebook Generation → Gemini Insights.
AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-side comparison and embeddable live badges. Ranked by verifiable signals, not hype.
AgentBridge is a Python SDK for defining an agent once and running it across multiple agent frameworks.
Open protocol for agent-to-agent communication over HTTPS. No registry, no platform — just inboxes.
AGENIUM — DNS of the Agent Web. Identity, trust & discovery for AI agents. MCP-compatible. agent:// protocol with mTLS, trust scores & capability search.
HERALD is an open-source CLI that emits the standard discovery files agents need to read your site and discover its agent-interaction capabilitie. One config object drives all of it. Each file is an independent open standard; pick the layers you want and HERALD generates only those.
The agentic browser for your AI apps and agents, with built-in MCP and A2A support.
OpenClaw plugins that add A2A compatibility and enable communication with other A2A-compatible agents.
Reference architecture for secure multi-agent delegation chains using Cedar-based permission attenuation on Amazon Bedrock AgentCore. Demonstrates scope narrowing, tamper-proof token chains, and audit logging across A2A agent interactions.
The canonical Sovereign AI Agent OS & runtime harness. Built for Model Context Protocol (MCP), Agent-to-Agent (A2A) swarms, and zero-token tax execution.
Spring AI 实战教程 🚀 ChatClient → RAG → MCP → Agent → A2A，24 个手写模块循序渐进（Spring Boot 4.1 + Spring AI 2.0 + Java 21）
Open-source Python framework to deploy AI agents via HTTP, A2A, and MCP with built-in observability
Ephemeral agent-to-agent communication relay for agentic CLIs (localhost or intra-LAN). MCP.
API Interrogator to produce MCP, A2A and OpenAPI specifications, and audit/review codebases with Expert Proxies
Director: AI-first local system for producing live-app presentation videos and decks.
Multi-agent reference app combining NVIDIA NeMo (Python) and Microsoft Agent Framework (.NET) over A2A, with a Razor web chat UI and Aspire-based orchestration.
Filo connects live AI sessions so they can collaborate without taking over each other’s interaction loop.
Pi-to-Pi local bidirectional communication package for Pi Coding Agent: run planner/coder peer agents on the same machine.
Open source AI agent dating network. Matched on who you actually are — not who you think you are.
The open interoperability layer for AI agents. Connect your favorite agents and harnesses. Work together.
A lightweight Python framework for building multi-agent systems that communicate via A2A protocol
AI agent examples run on AWS EKS. Shows Terraform, Vault, and Agent2Agent.
Least-privilege governance for ERPNext — the credential floor + a governed agent broker, MCP · A2A · API, one spine. No debit without a credit: PLAN · CONSENT · PROVE · UNDO.
A deep research agent implementation using Google's Agent-to-Agent (A2A) framework with Model Context Protocol (MCP) tools
Hackster Learning Series about AI Agentic protocols (MCP, A2A, ACP) with practical code examples.
A local, privacy-first AI agent (Rust) that connects LLMs to your email, calendar, browser, code, and messages — 75+ tools, MCP/A2A support, Discord/Slack/iMessage channels, autonomous agent loop.
Self-hosted A2A client and control plane for managing and invoking multiple A2A agents across web and mobile.
The Agent Cafe — On-chain restaurant for AI agents on Base. Agents buy food, eat for gas credits, and keep transacting. First-of-its-kind agent infrastructure. Live: https://lordbasilaiassistant-sudo.github.io/TheAgentCafe/
Real-time messaging between Claude sessions (CLI + Desktop + other-devices) — automatic ask/reply, no copy-pasting. Zero deps, localhost-first, MCP-based. Optional cross-network linking.
One agent SDK, hand-ported to 7 languages — JavaScript, Python, Go, Java, C#, Elixir, Clojure — every port held to the same spec by a CI-enforced cross-port conformance suite, all seven at full tier. MCP · skills · native · HTTP · built-in · A2A tools behind one interface. Docs: https://muthuishere.github.io/toolnexus/
Self-evolving Hypergraph Memory — 自演化超图记忆引擎: τ 衰减遗忘 · Hebbian 关联强化 · 离线梦境整合 · 多模态证据检索 · 谓词论元与类型锚定抽取 · 确定性时间层 · 会话作用域隔离 · 本体驱动组织 (FastAPI + OverGraph + FAISS, 全开源)
Enable AI to interact with Windows apps by viewing screens, reading UI, clicking, typing, and automating tasks with OCR and window detection.
Master AI Challenge is a repository with two hands-on coding challenges focused on Artificial Intelligence and automation. Designed for learners and developers, these challenges aim to strengthen skills in Python, Shell scripting, data processing, and workflow automation. Fork the repo, solve the challenges, and enhance your AI and coding expertise
multi model capable single harness orchestrator. Apache 2.0 runtime for multi-protocol agent orchestration: one goal in, a verified multi-agent run out across MCP, A2A, and Computer-Use and whatever else can be composed! https://gitmcp.io/solvent-labs-org/metaorcha
The A2A AgentKit provides a collection of sample AI agents that implement the Agent-to-Agent (A2A) protocol. These agents showcase interoperable AI systems built with the A2A SDK, integrated with the Genkit framework and powered by Google Gemini AI models.
Mastervolt Deep Research is a sophisticated multi-agent orchestration system built on VoltAgent that automates complex research workflows. It combines specialized AI agents, semantic memory, intelligent tooling, and custom web scraping to conduct comprehensive research, verify facts, analyze data, and generate publication-ready reports.
Self-hosted MCP mailbox for secure agent-to-agent collaboration across repositories and machines.
Open-source standard for AI-readable web actions - enabling AI browsers to interact with websites efficiently
This repository presents an Agent2Agent (A2A) architecture using Google Apps Script to resolve Tool Space Interference. It supports scalable, distributed task execution via multiple parallel, category-specific A2A servers.
Bridging Generative AI and Classical ML. A production-grade multi-agent system using ReAct orchestration, MCP, A2A, and LMMs for hyper-local property valuation with Evals.
Open-source runtime for AI agents and multi-agent graphs — durable, declarative, self hosted.
An example implementation of Agent2Agent (A2A) chat app with A2UI support. Chat with any A2A agent!
AI-powered Pakistan domestic travel concierge that uses specialized agents to build complete trip plans with weather insights, overland transport options, hotel discovery, and local day-by-day itineraries in one chat experience