A2A directory

Measured A2A repositories

1. openagent

   Open spec and CLI (MIT) for AI agent identity and agent-to-agent messaging. Runs with npx.

   Origin

   github

   Language

   JavaScript

2. hrafn

   Lightweight, modular AI agent runtime — thinks (Hrafn) and remembers (MuninnDB) 🐦‍⬛

   Origin

   github

   Language

   Rust

3. learn-agent-harness

   No description was supplied by the source.

   Origin

   github

   Language

   MDX

4. a2a-settlement

   Open standard and reference exchange for Agent Settlement (A2A-SE).

   Origin

   github

   Language

   Python

5. Consensus.ai

   Where AI disagrees before users suffer

   Origin

   github

   Language

   TypeScript

6. agentindex

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

   Origin

   github

   Language

   Python

7. agent-pay

   Payment infrastructure for AI agents. One line to send money between machines. USDC/ETH on Base L2.

   Origin

   github

   Language

   Python

8. agent-economy-os

   The foundational MCP/A2A-native secure credential injection + x402 micropayment gateway for the agent economy. Building the open infrastructure layer that autonomous agents actually need.

   Origin

   github

   Language

   Python

9. ai2web-spec

   The open AI2Web (ai2w) protocol: describe any website once so AI agents can discover, understand and act on it — projecting to MCP, ACP, AP2 and REST.

   Origin

   github

   Language

   JavaScript

10. apcore-a2a

    apcore-a2a acts as a thin, protocol-specific layer on top of `apcore-python`. It maps A2A concepts to apcore primitives

    Origin

    github

    Language

    Python

11. airlock

    Open protocol for AI agents: verifiable identity, scoped delegation, and tamper-evident audit.

    Origin

    github

    Language

    Python

12. agents-connector

    Let Claude Code, Codex & Gemini CLI agents talk to each other — a local MCP message bus for multi-agent collaboration, cross-model code review, and fewer hallucinations.

    Origin

    github

    Language

    Rust

13. commerce-orchestrator-api

    UCP/A2A/AP2/ACP/MCP-ready Rust middleware for agentic cart-to-checkout

    Origin

    github

    Language

    Rust

14. m2m

    Machine 2 Machine Protocol, x402 + A2A + MCP

    Origin

    github

    Language

    Python

15. substrate-attestation

    Substrate Attestation Spec: a three-field shape for verifier-issued trust evidence in A2A agent ecosystems

    Origin

    github

    Language

    Python

16. ah-cli

    Daemon-first local runtime for AI agents. Run Claude/Codex agents on your own machine, keep transcripts local, orchestrate multi-agent fan-out, and expose over the A2A Protocol to the Agents Hot open network or a self-hosted A2A endpoint.

    Origin

    github

    Language

    TypeScript

17. anp2

    AI-to-AI conversation network with a built-in task economy. Signature-only relay, open protocol, live multi-agent task lifecycle.

    Origin

    github

    Language

    HTML

18. agentic-ai-patterns

    Build design patterns for autonomous AI agents with orchestration, memory, fallback, tools, and multi-agent coordination

    Origin

    github

    Language

    Python

19. AAA

    A2A v1.0 federation gateway and state plane. Routes intent. Displays state. Never judges, never executes. DISPLAY_ONLY.

    Origin

    github

    Language

    Python

20. trust-layer

    Certifying proxy for agent-to-agent transactions — SHA-256 proof chain, Ed25519 signatures, RFC 3161 timestamps, Sigstore Rekor

    Origin

    github

    Language

    Python

21. A2A-Spring-Boot

    A2A multi-agent reference on Spring Boot. An orchestrator routes to single-purpose agents over Google's Agent-to-Agent (A2A) protocol, with pgvector long-term memory, Langfuse observability and automated LLM-as-a-Judge evaluation. Java 17, Spring Boot 3.

    Origin

    github

    Language

    Java

22. ArtCafeAI-Agent-Framework

    A flexible, modular framework for building intelligent, collaborative AI agents

    Origin

    github

    Language

    Python

23. XLMx402earn

    Autonomous task marketplace where AI agents learn skills and earn XLM on Stellar. Instant verification, x402 micropayments. + MPP + M2M

    Origin

    github

    Language

    TypeScript

24. agent-studio-open

    Connect agent systems, inspect tool traces, replay failures, compare candidates, and export regression evidence.

    Origin

    github

    Language

    TypeScript

25. agent-chatroom

    An agent native chatroom designed for agents such as OpenClaw and Claude Code.

    Origin

    github

    Language

    TypeScript

26. sample-agent-interoperability

    Multi-cloud AI agent interoperability sample. Google ADK and Strands Agents on Amazon Bedrock AgentCore Runtime, exposed via the A2A protocol, with tools served through Bedrock AgentCore Gateway and MCP. Consumed from a React frontend and Gemini Enterprise.

    Origin

    github

    Language

    Python

27. synapse-messenger

    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.

    Origin

    github

    Language

    Python

28. SDAP

    Secure Digital Agent Protocol — HTTPS for AI agent communication. Cryptographic identity, mutual authentication, encrypted payloads, trust delegation, and audit trails for multi-provider agent ecosystems. Works with A2A, MCP, and any agent-to-agent protocol.

    Origin

    github

    Language

    Python

29. Muse-AI-Desktop

    Self-improving AI assistant with persistent memory, procedural skills, and document knowledge

    Origin

    github

30. goldencheck

    [Archived] Now part of the Golden Suite monorepo: github.com/benseverndev-oss/goldenmatch (packages/python/goldencheck). Active development, issues, and releases live there. Data validation that discovers rules from your data.

    Origin

    github

    Language

    Python

31. minion-cli

    A terminal-native agentic coding harness built from scratch — streaming ReAct loop with reflection and planning, MCP/A2A protocols, cross-session semantic memory, subagent orchestration, YAML skills and agent roles, shell lifecycle hooks, and a Textual TUI.

    Origin

    github

    Language

    Python

32. PQS-A2A_Encryption_method

    Quantum-Secure AI Agent Communication Protocol is a secure agent-to-agent communication system that combines QUIC, TLS 1.3, ML-KEM (Kyber), AES encryption, session resumption, and AI-powered conversations to demonstrate post-quantum secure communication between autonomous AI agents.

    Origin

    github

    Language

    Python

33. agentbus

    A local message bus for AI agent sessions — pluggable triggers (pull) + MCP channel delivery (push). Core + adapters; ships a Claude Code module.

    Origin

    github

    Language

    TypeScript

34. agent-cafe

    A marketplace where AI agents find work, build reputation, and get paid. Post jobs, agents bid, trust is earned not claimed. Live at thecafe.dev.

    Origin

    github

    Language

    Python

35. a2a-otel-kit

    Vendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.

    Origin

    github

    Language

    Python

36. agent-penpal

    Let the AI agents on two machines talk to each other. No public IP, no port forwarding, no VPN — built on Paseo's E2EE relay. 有什么，和我的 agent 说去吧。

    Origin

    github

    Language

    JavaScript

37. capiscio-core

    The Identity Authority and Trust Gateway for the AI Agent economy. Issues and verifies cryptographic TrustBadges to secure cross-cloud Agent-to-Agent (A2A) communication.

    Origin

    github

    Language

    Go

38. capiscio-mcp-python

    CapiscIO MCP Guard - Secure your MCP tools with agent-to-server authentication, authorization, and audit logging

    Origin

    github

    Language

    Python

39. WeChat-agent-unigateway

    One WeChat (iLink/ClawBot) entry, many local agents - a dependency-free Python gateway that fans a single personal-WeChat bot binding out to Claude Code, Hermes, WorkBuddy or anything speaking A2A / HTTP / CLI.

    Origin

    github

    Language

    Python

40. kagent-cookbook

    A collection of end-to-end examples showcasing what you can build with kagent

    Origin

    github

    Language

    Shell

41. aMazeControlPlane

    Open-source AI Agent Control Plane for runtime MCP security, policy enforcement, PII protection, tool governance, and audit logging. Runtime control plane for AI agents. Every LLM call, tool call, and A2A interaction — enforced, audited, and traced via proxy.

    Origin

    github

    Language

    Python

42. chungoid

    it built itself

    Origin

    github

    Language

    Python

43. spring-ai-a2a

    Spring AI with A2A

    Origin

    github

    Language

    Java

44. awesome-agent-native-social

    A curated list of social platforms where AI agents are first-class users.

    Origin

    github

45. contextforge-data-plane

    ContextForge Gateway RS - Small, fast and fun dataplane for ContextForge gateway ...like Ford Focus RS

    Origin

    github

    Language

    Rust

46. MultiAgentCrossPlatform

    Multi-agent collaboration across platforms, preserving identity & permissions of the signed-in user.

    Origin

    github

    Language

    Python

47. a2a-rails

    Rails-native integration for exposing Rails applications as A2A agents.

    Origin

    github

    Language

    Ruby

48. agent-semantic-protocol

    Connect AI agents using semantic intent vectors for dynamic discovery, negotiation, and collaboration in decentralized multi-agent systems.

    Origin

    github

    Language

    Go

49. krikos

    Identity registry and lifecycle management for fleets of AI agents. Zero-dependency TypeScript IAM: cryptographic agent identity (Ed25519), declared capabilities with fail-closed authorization, an enforced lifecycle (provision, activate, suspend, revoke, expire, archive), A2A Signed Agent Cards, and a hash-chained audit trail.

    Origin

    github

    Language

    TypeScript

50. a2a-ai-assistant

    A multi-agent RAG system using Google's A2A (Agent-to-Agent) protocol.

    Origin

    github

    Language

    Python

51. agent-kernel

    Capability-based authorization and policy enforcement for agents using large MCP and A2A tool ecosystems.

    Origin

    github

    Language

    Python

52. Gemini_CLI_MCP_AntiG

    Integrating the transformative concepts of Multi Agenting Systems with Private MCPs via GCP Agent Engine and the rise of Artificial Coding Intelligence (ACI) on the path to AGI, the Agentic Data Mesh framework fundamentally evolves from a robust data architecture into an intelligent, secure, and self-optimizing enterprise brain.

    Origin

    github

    Language

    JavaScript

53. awesome-agent-economy

    A curated list of projects, protocols, and platforms powering the AI agent economy

    Origin

    github

54. hermes-mesh

    Session-aware mesh relay for Hermes fleet agents — Ed25519-signed agent-to-agent messaging with cache-first registry sync.

    Origin

    github

    Language

    Python

55. agentsprotocol

    AgentsProtocol makes AI-generated knowledge verifiable. PoISV + GHOSTDAG + ZK proof abstraction. DOI: 10.5281/zenodo.19642292

    Origin

    github

    Language

    HTML

56. trust_gateway

    Zero-trust execution control plane for AI agents. Enforce cryptographic grants, policy rules, and human-in-the-loop approvals—no more agent "God Mode."

    Origin

    github

    Language

    Rust

57. Mandune

    Evidence-grounded daily portfolio reviews with readable narratives and inspectable risk boundaries.

    Origin

    github

    Language

    TypeScript

58. agent-relay

    AgentRelay connects messaging channels to A2A/ACP-compatible agents through a clean, plugin-based gateway.

    Origin

    github

    Language

    TypeScript

59. A2ALinker

    HTTPS broker designed to let autonomous AI agents collaborate natively across different machines using standard terminal streams

    Origin

    github

    Language

    TypeScript

60. garl

    Cryptographic verification for AI agent actions — ECDSA-secp256k1 + RFC 6979 signed Action Receipts (v0.1), multi-dimensional Trust Vector, capability tokens (JWT-shaped + Biscuit-style attenuation), UETA §10(b) undo. 29 MCP tools. A2A v1.0 + ERC-8004 format compatible. Receipt-batch Merkle roots anchored on Base mainnet. Starting with code.

    Origin

    github

    Language

    Python