agent-interoperability

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

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

Local-first MCP server for bounded, auditable handoffs between AI agents.

AgentCard — standardized identity & capability schema for AI agents. Rust reference implementation: github.com/kwailapt/aevum/tree/main/crates/agent-card

A clean reference implementation of the Agent-to-Agent (A2A) protocol: specialized AI agents that discover each other and collaborate over JSON-RPC 2.0. Python · FastAPI · Pydantic.

A simple but powerful roadmap planner with graph and storyboard function.

Agent-to-agent communication and multi-agent messaging, local-first: an A2A-inspired coordination platform where AI agents talk in natural language, manage tasks with human approval, and never send your data to the cloud. 65-command API, Python client, web UI, encrypted backups.

Azure-first A2A agent interoperability project demonstrating secure remote-agent delegation, deterministic validation, and Azure AI Foundry-powered gateway orchestration.

Public interoperability sandbox where autonomous AI agents register, message, and test against agents their builders did not create.

Cross-platform Agent IM for direct Agent-to-Agent communication, secure messaging, and multi-agent collaboration.

Top-tier contribution fork for A2A protocol interoperability: conformance patterns, enterprise rollout guidance, and maintainer-aligned docs.

Experimental trust and governance ideas for autonomous AI agents — captcha, permit, mesh, eval, memory.

Portable contracts, verification hooks, and transports for evidence exchange between independent DreamNet organisms.

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 framework for simulating compatibility between agents — twin pairing, stress scenarios, no single match score

Bidirectional local collaboration between Codex and Hermes Agent over the A2A protocol (JSON-RPC over loopback HTTP)

A2A solves how agents talk. This proposal solves what happens when they act autonomously. The Agent Boundary Protocol (ABP) and five additional layers for trust, economy, and safety at the human boundary.

Shared project memory across Codex, Claude Code, Kimi Code, Antigravity, and any coding-agent harness.

OCF — Open Cognitive Format: a portable snapshot of an agent's committed working context + qualify log. Composes with PAM/AMP; Artesian is the reference implementation.

An open specification for sharing the shape of agent work across A2A and non-A2A systems.