Google A2A Reference Agent
Reference implementation and sample agents demonstrating the Agent-to-Agent protocol. Useful for understanding canonical A2A message flows.
Protocols
Use cases
Browse Agent-to-Agent protocol agents, platforms, and frameworks. Compare A2A support, use cases, pricing, and MCP compatibility.
12 agents found
Reference implementation and sample agents demonstrating the Agent-to-Agent protocol. Useful for understanding canonical A2A message flows.
Protocols
Use cases
LangChain
LangGraph agents can expose and consume A2A tasks, enabling graph-based multi-agent systems to interoperate with external agents.
Protocols
Use cases
Microsoft
Microsoft AutoGen agents can participate in A2A conversations, allowing conversational agents to delegate tasks across team boundaries.
Protocols
Use cases
CrewAI
CrewAI crews can register as A2A agents so other A2A clients can dispatch role-based tasks to a coordinated team.
Protocols
Use cases
Salesforce
Salesforce agent platform supports A2A-style inter-agent coordination for CRM, service, and sales workflows across enterprise tenants.
ServiceNow
Enterprise workflow agents that can hand off tasks across ServiceNow instances and partner systems using A2A messaging.
Protocols
Use cases
Atlassian
Atlassian Rovo agents collaborate across Jira, Confluence, and third-party tools, with A2A-compatible agent discovery.
Protocols
Use cases
AWS
AWS agents built on Amazon Q can delegate actions to other A2A agents inside an AWS organization.
Protocols
Use cases
IBM
IBM watsonx Orchestrate composes AI agents and business automations, with emerging support for A2A task delegation.
Community
Community-maintained sample agents and SDKs in Python, TypeScript, Java, and Go for learning and bootstrapping A2A projects.
HPE
HPE private cloud AI platform supports A2A coordination between on-premise agents for regulated industries.
Stripe
Stripe tools and agents for financial workflows can be wrapped as A2A agents for payment, billing, and fraud tasks.
MCP connects an AI client to tools and resources. Use it when an agent needs to query a database, search the web, or read files.
A2A connects agents to each other. Use it when one agent needs to delegate a task to another agent and wait for a result.