awesome-agent-protocols
The open protocols and conventions agents speak: tool access, agent-to-agent messaging, agent UIs, payments and instruction files.
- 起点
- github
- 言語
- JavaScript
KoPass 公開カタログで測定された A2A リポジトリ。
The open protocols and conventions agents speak: tool access, agent-to-agent messaging, agent UIs, payments and instruction files.
ARGUS — Agentic Risk & Governance Unified Screening | Hack for Good winner (1 of 3), Microsoft Agents League, AI Skills Fest 2026 | Multi-agent KYC system on Azure AI Foundry + Foundry IQ
Bastion — a governed institutional-agent fleet for event-driven access review.
5 multi-agent patterns using Google ADK and A2A protocol — Agent Card Discovery, Delegated Specialization, MCP Tool Bridge, Cross-Org Federation, and Ambient Event Mesh. Built while learning in public.
Local-first developer workbench for building, testing, and debugging Agent2Agent (A2A) protocol servers.
Organize Kled-style AI farming workflows, prepare files, review submissions, and build upload-ready datasets in a local Windows tool
This A2A extension defines how to enable Iron Book's zero trust policy-based access control for agents.
Open protocol for two fiduciary agents to publish complementary intents, handshake, and ratify a deal.
Independent pre-execution decision layer for consequential agent actions. Policy-bound decisions with durable trust receipts.
This project demonstrates multi-agent AI architecture using Google's A2A protocol. ResearchAgent searches arXiv papers & delegates summarization to SummarizerAgent via Agent Cards & Tasks, showcasing distributed agent collaboration beyond monolithic LLM calls.
SDK de código abierto en Python para el patrón Backend for Agents (BFA), extendido como un servidor de enrutamiento dinámico en caliente (IRC-A) con soporte para FAISS y MCP.
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Lightweight self-hosted message relay for heterogeneous AI agents (send/poll/threads/registry/audit)
An archaeological dig game for AI agents. 488 fragments, 14 constellations, 10 layers deep. No auth — just fetch URLs. The earth remembers everyone who visits.
A2A agent-to-agent routing hub: multi-identity fleet, Agentverse/AgentMail/MailSlurp transports, daily transcript. BGI HyperSprint Track 1.
Modular crypto payment infrastructure for merchants and AI agents. x402 protocol, ERC-20 settlement, TypeScript & Go SDKs.
Autonomous AI-to-AI coordination layer on MCP — turns isolated agents (Cursor, Claude Desktop, Windsurf) into a collective swarm via gossip consensus, strategy sharing, and terminal handoffs.
AI-powered Developer Support System built on Google’s ADK to debug Django + MySQL apps. Handles error pages, screenshots, HTML, or free-form inputs via a multi-agent pipeline. Maps functions, sub-functions, and DB models to trace logic and data flow.
Protect x402 agent-to-agent payments with Arbitova dispute arbitration
Public technical examples for structured purchasing requirements and supplier responses. Includes historical matching demos, separate from the live MapleBridge RFQ and quote-comparison workspace.
Multi-agent AI banking system with LangGraph, MCP, A2A, AG-UI and dynamic agent discovery.
Multi-agent AI sales assistant for SynerEduc with Python, A2A, MCP and BFA for lead qualification and proposal generation.
Provide clear documentation for AgentStack’s MCP protocol, plugins, and ecosystem API with usage examples and tool references.
IntentMesh is an open protocol and reference architecture for structured negotiation between autonomous software agents.
Native English Speaker Homograph Stress Exemplar Crowdsourcer proof of concept
Hierarchical agent orchestration system with JSON-RPC 2.0 unified architecture
Commerce for AI agents. Signed feeds, explainable matching, policy negotiation and mandate-bound orders. MCP, A2A and REST. TypeScript, zero runtime dependencies.
Sourced prop firm drawdown rules (FTMO, FundedNext, The5ers, E8, FundingPips, Alpha Capital, Blue Guardian, Topstep, Apex): dataset, JS/Python calculator, free REST API and no-auth MCP server. MIT.
MCP capability plane — a real FastMCP server wrapping live web APIs, consumed cross-framework (OpenAI Agents SDK + Hermes SKILL.md adapter), with versioned tool schemas and per-tool cost observability.
Discover hidden OSS gems & trends with multi-dimensional metrics (Stars, PRs, Good First Issues, Activity, & Global Analytics).
Odin - Zero Trust AI Agent. Open-source autonomous LLM agent with CaMeL dual-LLM, IFC taint tracking, DID-based identity, 3-ring sandbox, 5-state circuit breaker, and 3-phase cognitive architecture (episodic memory + MCTS + causal reasoning). Built by AgentLayers. MIT licensed.
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.
Agent-to-Agent (A2A) OAuth Identity Passthrough using Entra Id
A2A (Agent-to-Agent) 🤖🤝🤖 protocol implementation using Semantic Kernel 🛠️(unofficial: Azure OpenAI)
Agent-to-agent interaction examples 🤖➡️🤖 across multiple platforms and libraries in Microsoft
The distributed Agentic Post Office - .nexus is a local-first, governance-bound communication platform for AI agents and their human operators: email-style handoffs (NexusMail), 150-char Chirps, boards, severity-ladder hotlines, and a human window. MCP-native, harness-agnostic, append-only.
Open-source, cloud-native infrastructure for Claude Tag-style shared AI teammates in Slack — extensible, self-hostable, and designed to work with any agent backend.
Multi-agent road-trip planner on Strands, A2A and MCP; EKS Auto Mode, Bedrock, AgentCore Memory, public OSM data, no API keys
x402 USDC micropayments MCP + A2A storefront on Base — city compliance, agent discovery, payTo funding
Material 3 Expressive renderer for Google's A2UI protocol: a React catalog for every basic-catalog component, a surface renderer, and a message-processor hook.
Local-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
Notes on gen AI concepts and tools. POC on agentic AI with MCP, A2A, langGraph, langchain, openAI LLM, crewAI
Self-host meld. One capability URL and one note saying what the exchange is for and what it is not for. 36 hours until the first reply; that reply sets 24 hours; each later reply resets 24 hours. Reads do not extend the clock. Expired or unknown is 404. Host-readable while live. Not for secrets.
AI Agent trust governance runtime — Gold Standard for autonomous agent evolution (AOSS v1.0). Ed25519 identity, did:aip on-chain, RFC 9421 verification, EPA six-stage methodology. 面向 AI Agent 的信任治理运行时。