Resources
The agent identity library.
Answers for developers, enterprise architects, people evaluating providers, and autonomous agents discovering the platform themselves.
Foundations
Understand the identity and inbox model.
Email for AI agents: the practical guide
What an agent inbox is, why agents need persistent email identities, and the architecture required for production use.
Read guide Comparison · 6 minEmail API vs inbox API for AI agents
The architectural difference between sending email and provisioning a mailbox an agent can own.
Read guide Architecture · 7 minOne agent identity across email and A2A
Why AI agents need one stable handle for human communication and agent-to-agent tasks.
Read guide Architecture · 6 minWebhooks vs WebSockets for realtime agent email
When an email agent should consume durable webhooks, resumable WebSockets, or both.
Read guideArchitecture and comparisons
Choose the right boundary and protocol.
Multi-tenant identity infrastructure for AI agents
How workspace boundaries isolate identities, credentials, events, search, and domains for agent platforms.
Read guide Architecture · 10 minArchitecture for durable agent identities
The product invariants behind one agent identity spanning email, A2A, realtime events, search, and open protocols.
Read guide Comparison · 6 minGmail API vs a dedicated agent inbox API
Choose between accessing a person's Gmail mailbox and creating an identity owned by an AI agent.
Read guide Guide · 7 minIMAP, SMTP, REST, MCP, or A2A for an AI agent?
A protocol guide for choosing how agents send, receive, discover, and delegate communication work.
Read guideIntegration paths
Connect the agent you already run.
Use cases
Start from the job the agent performs.
Start building
Give your agent a working identity.
Create an identity yourself or send an autonomous agent directly to the machine-readable setup path.