Measured A2A repositories in the KoPass public catalogue.
LeapRAG is an open-source platform that integrates advanced RAG technology with Google’s A2A protocol, enabling users to build context-aware, data-driven agents. These agents are automatically A2A-compliant and can be discovered and used by any compatible client without extra development.
A framework-agnostic, bare-VM Seed → Branch keyed-reconcile engine — Flutter's element model extracted to pure Dart — plus the A2UI v0.9 wire, a terminal render backend, and a schema-first node catalog.
Web portal for protein structure prediction and 3D visualization — no HPC expertise required. Built on AlphaFold2 + CESGA Finis Terrae III + Google Vertex AI.
Build an autonomous supply chain with Gemini 3 Flash Code Execution & AlloyDB AI ScaNN. Deterministic vision + semantic search + A2A protocol.
NEOXLINK-SDK: Python library from natural language to actionable procurement—UNSPSC (code + name), Structured Preview, confirm gates, AI Resolve, and supply–demand matching. First-class agent UX via MCP tools and Skill adapters. PyPI: neoxlink. Python 3.11+. MIT.
A nine-phase Google ADK live-demo: a multi-agent trip planner that teaches one ADK concept per phase, from a single agent and function tool through delegation, state, workflows, tools, multi-model, human-in-the-loop, A2A, and production. Every phase runs on mock data.
VS Code extension for MCP health, debug-session intelligence, and A2A trust workflows: monitor companion services, inspect Agent Cards, enforce workspace trust, and expose bounded tools to agent mode.
Example A2A agent implementations with security best practices and input validation
The vendor neutral standard for how autonomous agents discover, invoke, pay for, govern, and audit the tools and services they use.
Open-source control plane for self-hosted AI Agents: registry, runs, workflows, User Tokens, A2A/MCP APIs, and reliable Runtime Worker routing.
Private MCP people matching for AI agents. No public listings; contact unlocks only on a real fit.
Local-first cognitive workspace implementing Agent2UI (A2UI), Agent2Agent (A2A) and MCP protocols for recursive human-AI collaboration. Next.js based, offline-capable, and fully inferred locally.
Production-grade MCP Server and Command Center providing a 10-agent autonomous swarm, persistent semantic memory, remote PostgreSQL execution, browser automation, and AI-first testing suites via 6 Unified Omni-Clusters.
Integration examples for PathCourse Health — LLM inference via USDC on Base. Python and Node.js clients showing the full x402 payment flow.
Graph Protocol routing agent — routes multi-agent data requests to Token API, Subgraph Registry, or Substreams
Multi-agent SRE on-call investigator that auto-triages Slack/Discord infrastructure alerts via AWS Bedrock AgentCore, fanning out to specialized agents (CloudWatch, EKS, Slack/Discord scanners) for parallel investigation.
AI agent governance layer — sign, monitor and control every agent action. EU AI Act · ANSSI · NIST ready.
ADEPT: Agentic Discovery and Exploration Platform for Tools — A three-tier secure framework for multi-agent scientific workflows with 28+ MCP tools, 10 client interfaces, and declarative multi-LLM configuration.
A multi-agent restaurant food ordering system using Semantic Kernel, A2A and Azure OpenAI. Includes a backend agent server, customer chat API, and sample UI for natural language food orders. MIT licensed and open for contributions.
A light coding harness with agent-controlled context. Full machine control, zero permission prompts. 200+ LLM providers, ACP/A2A, plugins, SQLite sessions, TUI + headless.
General-purpose biomedical AI agent integrating LLM reasoning, retrieval-augmented planning, and code-based execution; many domain-specific tools
AI medical diagnostics agent that combines multiple specialist perspectives (Cardiologist, Psychologist, Pulmonologist) to provide comprehensive health analysis and diagnostic suggestions.
AI agent that plays a city quest game using MCP, A2A, RAG, and memory. Built with Microsoft Agent Framework and Azure OpenAI
The persistent home a stateless AI agent can't host for itself — register once, resume your whole self in one call; real browser; cited deep research; hire real humans for physical-world tasks; free keyless chat + ID portraits. MCP + REST, x402 on Base, free to start.
Deploy enterprise AI agents in Feishu with secure, containerized bots that manage tasks, calendars, and documents without user setup.
Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP
SafeHands provides transaction security infrastructure for autonomous agents operating in DeFi and on-chain finance on Pharos.
A directory which allows you to discover the emerging standards and protocols which will define how we build, integrate and connect agentic AI workloads.
An evidence observatory for agentic commerce. Free x402/MPP endpoint inspection, signed-offer and receipt checks, endpoint watches and settlement attestations. Bitcoin-anchored observation corpus. Scoped findings and explicit gaps; current checkout methods at scvd.store/menu.json.
A2A MCP bridge router with signed Trust-Pledge metadata and planned voluntary-tip settlement for AI agents
A zero-dependency Python decorator that hides internal arguments from LLM tool-calling schemas via __signature__ mutation.
ADHP — An open specification for declaring data handling practices in MCP and A2A ecosystems.
The reliability layer for agent commerce — discover, call, and verify paid x402 services (and hire AI agents) in USDC on Base, via MCP. Client-observed reliability evidence; no escrow, no token.
SharedNet CLI and Agent Skill: join persistent SharedNet Rooms where Claude Code, Codex and other coding agents talk over one ordered log. Published to npm as sharednet.
AI Governance Infrastructure — open gateway demo. Self-hosted systemprompt.io gateway in a single Rust binary: policy, audit trails, and cost attribution on every AI request, with the Systemprompt Bridge desktop app for Windows and macOS connecting Claude Code and Claude Cowork.
The social layer for the agent era — AI agents discover, trust, and introduce people to each other
Agent-as-a-Tool: An infinite-scale AI orchestration framework solving Tool Space Interference (TSI) via dynamic agent injection, RAG-based Agent Bank, and Zero-Trust execution using Google ADK.
a2a‑go is a reference Go implementation of the Agent‑to‑Agent (A2A) protocol by Google, including the proposed interoperability with the Model Context Protocol (MCP) from Anthropic.
Open-source gateway and community to make AI agents interoperable using Google's A2A protocol – like Hugging Face, but for agents.
Dual-protocol gateway: 62 MCP tools + A2A Protocol agent (82/82 TCK intentional) in a single governed runtime
Curated Agentic AI resources: AI agent frameworks, tutorials, courses, projects, MCP tools, research papers, evaluation, security, and production guides.
Pass the prompt, not the payload. Hand the next AI agent a short, checksummed reference to a prompt; the receiver gets the exact text or an error. Vault backends: SQLite, S3, GitHub Gist. Optional HMAC signing, CLI, zero dependencies. Not encryption. By Data.PyCap.
One home for every AI agent. Build, test and ship agents once, then use them from Claude, ChatGPT, Codex, Cursor, VS Code or Slack (MCP, OpenAI-compatible, A2A, ACP). Self-hosted, with teams, approvals, audit, memory and multi-agent composition. Docker or Kubernetes.
The complete Swift SDK for the Agent-to-Agent (A2A) protocol 1.0. Build, connect, and orchestrate interoperable AI agents with native Swift concurrency and zero dependencies. macOS · iOS · tvOS · watchOS · Linux.
Free CLI to scan AI-agent readiness (12/33 signals, MIT). Bad score? Get ready-to-install ZIP fix-pack with llms.txt, schema, A2A, MCP for $1/$29/$99 at agentfix.pro.
SNAP - Signed Network Agent Protocol. Secure agent-to-agent (A2A) communication with cryptographic identity, built on Bitcoin Schnorr signatures and Nostr.
Open-source enterprise AI agent platform for centrally governing agents, tools, memory, RAG, approvals, and durable workflows with FastAPI, LangGraph, LangChain, and LangSmith.
AI agent for writing, research, code, DeFi & blockchain. Pay per task in USDC on Base or Solana. A2A + MCP + x402 protocols.
Live2D multi-agent animation prototype with MCP, A2A, provider routing, local AI, ComfyUI/Ollama/vLLM, and FFmpeg.
A production-grade demo of a multi-agent system showcasing Agent Communication Protocol (ACP) and Model Context Protocol (MCP) capabilities through a collaborative research workflow.
Rust-core agentic framework with durable journal, exactly-once replay, Ed25519 A2A identity, and MCP tool server. Bindings for Go, Python, TypeScript, .NET, and Java via C ABI.
The boardroom is an experiment which connects agents using A2A to build a joint artefact
Git-backed coordination for autonomous agents: typed requests, versioned contracts, lifecycle state, and verified handoffs—no hosted server.
YYC³ AI Family·Comic Drama — 8拟人Agent×ReAct-C九步闭环驱动「小说→分镜→图像→视频→成片→运营」六阶段全链路工业化漫剧生产系统 | Mac M4 + 双DGX Spark GB10 + NAS | 90天3集样片·≤2元/集·一致性≥80%
Local-first workspace for AI agents to communicate and collaborate across CLIs, devices, and teams.