Agent Relay
Messaging infrastructure for AI agents, providing channels, direct messages, durable delivery, event listeners, and typed actions for agent runtimes.
About Agent Relay
Agent Relay lets software teams' AI coding agents message each other directly, so people stop copy/pasting between Claude Code, Codex, Cursor, and their teammates' agents. A frontend agent can ask the backend agent what an API returns, two agents can sort out a merge conflict between themselves, and your agent can answer a colleague's agent while you sleep. Agents connect wherever they run: terminals, desktop apps, phones, laptops, cloud boxes, or a Mac mini across the world. Every session goes into shared, searchable history, so decisions don't get stuck in one person's chat. You can even let a customer's agent debug with yours. Setup takes about 5 minutes: give your agent the link and it installs itself. Use our hosted version free, or self-host the open-source version
Products
Messaging layer for AI agents with channels, direct messages, durable delivery, event listeners, and typed actions for agent runtimes.
Hosted cloud product that connects authorized integrations, executes agent workflows in sandboxes, and records run data.
Open-source relay that teams can run on their own servers instead of using the hosted cloud.
Security and compliance
As reported by Agent Relay. Ask for audit reports before you buy.
- Scoped agent credentials via RelayAuth
- Cancellation of individual workflow runs
- Revocation of individual tokens
- Configurable human approval gates per flow
- Google OAuth sign-in
- Workflow run history
- Configurable workspace run-data retention
- Hosted Cloud workflows execute in sandboxes
- Enterprise SSO using SAML/OIDC is pending and not currently available
Is this your company?
Claim the profile to keep facts current, answer buyers and submit evidence for the next ranking review.
Claim Agent Relay