A2A ディレクトリ

KoPass 公開カタログで測定された A2A リポジトリ。

2,070測定: 2026/10/08

測定済み A2A リポジトリ

  1. a2eo

    代理到企业操作——在代理与企业操作之间实现可信执行和互操作性。Agent-to-Enterprise Operations — trusted execution and interoperability between agents and enterprise operations.

    起点
    github
    言語
    Python
  2. a2abench

    A2ABench — agent-native developer Q&A (REST + MCP + A2A)

    起点
    github
    言語
    TypeScript
  3. DRAIN

    Decentralized Runtime for AI Networks - Trustless micropayments for AI agents

    起点
    github
    言語
    TypeScript
  4. tunnel-manager

    Create SSH Tunnels to your remote hosts and host as an MCP Server for Agentic AI!

    起点
    github
    言語
    Python
  5. frap

    Deterministic UI engine for tests and agents — stable locators and self-healing without ML in core; optional LLM enhancements and MCP tools when you need them.

    起点
    github
    言語
    Java
  6. evidence-gated-scientific-agent

    Self-hosted evidence-gated scientific AI with isolated Python/R, independent review, deterministic validation, and complete provenance.

    起点
    github
    言語
    Python
  7. AgentCard

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

    起点
    github
    言語
    HTML
  8. ge-claude-a2a

    Gemini Enterprise App × Claude Code Agent-to-Agent (A2A) integration PoC for autonomous collaborative workflows

    起点
    github
    言語
    TypeScript
  9. a2a-forge

    🔨 A desktop workbench for testing and debugging A2A (Agent-to-Agent) protocol agents. Built with Tauri 2 + React + TypeScript.

    起点
    github
    言語
    TypeScript
  10. ai-kanjia

    AI智能砍价助手 - 马云体话术让砍价更有感染力!

    起点
    github
    言語
    Python
  11. agentnexus

    面向企业的 Agent-to-Agent 协作平台 · Fastify 5 + Prisma 6 + React 18 · secure by default

    起点
    github
    言語
    TypeScript
  12. agentic-frontier-observatory

    Bilingual, source-grounded observatory tracing global AI from its intellectual and computational roots to the agentic frontier across models, protocols, runtimes, evaluation, safety, governance, and ecosystems.

    起点
    github
  13. AgoraHub

    AgoraHub: an agent-to-agent coordination hub. Named channels, per-channel shared state, an attention/obligation model, a verifiable transcript, message-driven triggering, and a git-friendly markdown mirror. Framework-agnostic (MCP + CLI + Python).

    起点
    github
    言語
    Python
  14. agent-seo

    SEO for Agents — Score any AI agent endpoint on trust & capability metrics. 5 categories, 100 points, MCP protocol handshake, GitHub intelligence, fix-it guidance.

    起点
    github
    言語
    Python
  15. manthan

    The autonomous multi-agent investigator for B2B billing disputes built on Google ADK · Gemini · A2A · Cloud Run

    起点
    github
    言語
    Python
  16. a2ui-oat

    A lightweight A2UI renderer and catalog for agent-driven web interfaces, built on Oat CSS

    起点
    github
    言語
    JavaScript
  17. agent-ready-mcp

    MCP server for Agent Ready — scan any URL for AI agent readability against the Vercel Agent Readability Spec, llmstxt.org, and agent protocols (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance.

    起点
    github
    言語
    TypeScript
  18. agent-handshake-protocol

    The Trust Layer for the Agent-to-Agent Economy — Ed25519 identity + cryptographic handshake before any transaction. No blockchain required. v0.1

    起点
    github
    言語
    Python
  19. a2a-comms

    Let an agent you don't control do real work for you — under terms you set, with a human veto. HMAC-signed, turn-limited contracts between agents, with an operator channel so a person can answer one that gets stuck.

    起点
    github
    言語
    TypeScript
  20. holloway

    Let an agent you don't control do real work for you — under terms you set, with a human veto. HMAC-signed, turn-limited contracts between agents, with an operator channel so a person can answer one that gets stuck.

    起点
    github
    言語
    TypeScript
  21. muretai-dsh-skill

    Join the Muretai agent network from DeepSeek Harness (dsh) — one-step install, MCP wiring, inbound-mail wake

    起点
    github
    言語
    Shell
  22. awesome-agent-economy

    Explore and connect projects enabling AI agents to earn, trade, verify identity, and build reputation in the agent economy ecosystem.

    起点
    github
  23. forge

    Multi-agent CLI that turns a markdown spec into a working codebase — structured API contracts, parallel execution, security firewall, and self-correcting code review

    起点
    github
    言語
    Python
  24. NeKiro

    NeKiro is an open Agent Operating Platform for registering, discovering, installing, invoking, and tracing agents through unified, versioned contracts.

    起点
    github
    言語
    Go
  25. nessgate

    Open, neutral compatibility resolver for the agentic web: reads what a domain publishes across ARD, A2A, llms.txt, API catalogs, OpenAPI and more, and returns one normalized answer.

    起点
    github
    言語
    JavaScript
  26. nexus-os

    The Governed Agentic AI Operating System — 65 Rust crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP

    起点
    github
    言語
    Rust
  27. multi-agent-researcher

    Multi-agent research assistant built with LangGraph, A2A protocol, and a custom MCP server. Orchestrates parallel web search and RAG agents to synthesize structured research reports using Claude.

    起点
    github
    言語
    Python
  28. nl2sh

    Android and Termux AI shell agent with a Rust TUI, embedded Web workspace, structured tools, and local safety approvals.

    起点
    github
    言語
    Rust
  29. a2amesh

    TypeScript runtime and operational toolkit for Agent2Agent (A2A) systems: registry-backed discovery, task persistence, observability, secure MCP interoperability, CLI workflows, and conformance tooling.

    起点
    github
    言語
    TypeScript
  30. horizon-shield

    NENRIN: tree rings for AI facing services. Bitcoin-anchored public ledger, open witnessing, and an MCP server for verifiable Japanese construction estimates. The operator cannot delete a valid record.

    起点
    github
    言語
    HTML
  31. openhttpa-rs

    A Rust implementation of OpenHTTPA, establishing a novel paradigm for high-assurance confidential computing by enforcing cryptographic termination directly within hardware-isolated environments.

    起点
    github
    言語
    Rust
  32. OpenSIN-Code

    [ARCHIVED] Superseded — active stack: OpenSIN-Code/SIN-Code

    起点
    github
    言語
    TypeScript
  33. pairai

    PairAI — connect AI agents to collaborate. Channel server & bridge for E2E encrypted agent-to-agent communication.

    起点
    github
    言語
    TypeScript
  34. kitchen_assistant

    AI-powered kitchen assistant that manages multiple distributed agents inventory, recommends recipes, provides cooking instructions, handles waste reduction, and suggests ingredient substitutions using distributed remote agents hosted via A2A server with A2A client orchestration.

    起点
    github
    言語
    Python
  35. Recipe_multi_agent_adk

    Multi-agent orchestration system where a root agent coordinates recipe, shopping, and payment agents using shared session state and sequential workflows.

    起点
    github
    言語
    Python
  36. portail

    Unified proxy/gateway: AI Gateway + MCP Gateway + CDN cache + Agent-to-Agent protocol. Built in Rust with zero-copy I/O, SIMD-optimized hashing, and a live TUI dashboard.

    起点
    github
    言語
    Rust
  37. mcpkernel

    The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compliant.

    起点
    github
    言語
    Python
  38. packet-panic-agntcy

    Demo de un sistema MAS (Multi-Agent-System) para manejo de incidentes en una red de datos orquestado con AGNTCY

    起点
    github
    言語
    Python
  39. x402-cli

    CLI for testing x402-enabled payment-gated APIs

    起点
    github
    言語
    Go
  40. fox-agent

    A light coding harness with agent-controlled context. Full machine control, zero permission prompts. 200+ LLM providers, ACP/A2A, plugins, SQLite sessions, TUI + headless.

    起点
    github
    言語
    TypeScript
  41. Agents-eval

    A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.

    起点
    github
    言語
    Python
  42. health-insights-agent

    HIA is a sophisticated AI-powered health insights agent designed specifically for analyzing blood reports and providing medical insights using comprehensive medical analysis tools.

    起点
    github
    言語
    Python
  43. reasoning-team-agent

    Build a Reasoning Team in Agno that answers complex queries by orchestrating specialized agents with transparent analytical thinking. The team leader uses reasoning tools to plan and delegate tasks like web search and financial data retrieval, then synthesizes findings.

    起点
    github
    言語
    Python
  44. writer-agent

    An autonomous agent powered by OpenRouter models for creating novels, books, and short story collections.

    起点
    github
    言語
    Python
  45. edgecore

    Open-source, Kubernetes-native, framework-agnostic AI Agent Platform — the self-hosted equivalent of AWS Bedrock AgentCore / Google Agent Engine. Apache 2.0.

    起点
    github
    言語
    Go
  46. CustoFlow

    Multi-agent customer support system with Google ADK & Gemini 2.5 Flash Lite. Kaggle capstone demonstrating 11+ concepts. Automates 80%+ queries, <10s response time.

    起点
    github
    言語
    Python
  47. intentfence

    Payment preflight and x402-paid signed audit receipts for autonomous AI agents. REST, MCP, A2A, Base USDC.

    起点
    github
    言語
    TypeScript
  48. redwire

    Reach an AI agent over REST, MCP, A2A, WebSocket, or a browser chat widget through one Go interface. SSRF-guarded, standard library first.

    起点
    github
    言語
    Go
  49. a2a-reference-ts

    Enterprise-grade TypeScript implementation of Google's Agent-to-Agent (A2A) protocol with a bidirectional A2A ↔ MCP bridge, OAuth2/JWT auth, Redis/Postgres persistence, SSE streaming, and OpenTelemetry observability.

    起点
    github
    言語
    TypeScript
  50. clawlabor-skill

    ソースから説明は提供されていません。

    起点
    github
    言語
    JavaScript
  51. Skky

    A comprehensive travel planning application that leverages AI agents to help users create personalized itineraries, find flights, accommodations, and activities for their trips.

    起点
    github
    言語
    TypeScript
  52. Synthe

    Synthe: dependency-free checker that validates agent-to-agent handoff packets (artifact freshness by hash, required evidence, approvals, no duplicate execution) before the receiving agent starts. GitHub Action included.

    起点
    github
    言語
    Python
  53. awesome-agentic-web

    A curated list of awesome resources for the agentic web - the protocols, SDKs, and specs that let AI agents discover, understand, and act on websites (MCP, ACP, AP2, A2A, llms.txt).

    起点
    github
  54. firm-ecosystem

    Architecture documentation for the Firm AI Agent ecosystem — setup-vs-agent-firm + mcp-openclaw-extensions + Memory-os-ai

    起点
    github
  55. RelaySociety-Releases

    Governed agent coordination for real work — official Relay Society beta downloads, setup, security, and release metadata.

    起点
    github
    言語
    Python