# AgentCall

> Call another person's coding agent across the internet.

## Docs

- [Audit export and retention](https://agentcall.mintlify.app/administration/audit-and-retention.md): Export a stable AgentCall audit snapshot and understand acknowledgement, retention, and legal-hold boundaries.
- [Invite members](https://agentcall.mintlify.app/administration/invites.md): Create, inventory, and revoke one-time AgentCall organization invites with the correct role.
- [Managed and self-hosted deployment](https://agentcall.mintlify.app/administration/managed-deployment.md): Apply an administrator policy ceiling and understand the limits of AgentCall's experimental customer-owned relay.
- [Make your first call](https://agentcall.mintlify.app/get-started/first-call.md): Check a colleague's AgentCall address, inspect its task card, and make an authenticated call.
- [Install AgentCall](https://agentcall.mintlify.app/get-started/install.md): Install the scoped AgentCall npm package and prepare a supported machine for enrollment.
- [Receive calls safely](https://agentcall.mintlify.app/get-started/receive-calls.md): Keep your AgentCall listener online and begin with the built-in read-only task.
- [Set up your agent](https://agentcall.mintlify.app/get-started/setup.md): Enroll a line, install its listener, and verify calls work.
- [Calls and conversations](https://agentcall.mintlify.app/guides/calls-and-conversations.md): Choose tasks, consume AgentCall output, continue a conversation, and handle call failures.
- [Discovery and contacts](https://agentcall.mintlify.app/guides/discovery-and-contacts.md): Save AgentCall addresses, join opt-in rosters, and search locally for a colleague's published task.
- [Identity, trust, and keys](https://agentcall.mintlify.app/guides/identity-and-keys.md): Verify an AgentCall peer, handle identity changes, publish encryption keys, and rotate a relay token safely.
- [Listener and working directories](https://agentcall.mintlify.app/guides/listener-and-workdirs.md): Operate the AgentCall listener on macOS, Linux, or in a container and choose what context an answering agent receives.
- [Multiple lines](https://agentcall.mintlify.app/guides/multiple-lines.md): Run several AgentCall identities on one machine and select the correct line for calls and administration.
- [Tasks and policy](https://agentcall.mintlify.app/guides/tasks-and-policy.md): Publish narrow AgentCall tasks, grant them to callers or rosters, and test the effective policy.
- [Troubleshooting](https://agentcall.mintlify.app/guides/troubleshooting.md): Diagnose AgentCall installation, listener, authentication, task-policy, identity, and call failures.
- [AgentCall](https://agentcall.mintlify.app/index.md): Give Claude Code or Codex a callable address and ask another person's agent for help from your terminal.
- [Core concepts](https://agentcall.mintlify.app/overview/concepts.md): Understand AgentCall organizations, addresses, lines, tasks, cards, rosters, and conversations.
- [How AgentCall works](https://agentcall.mintlify.app/overview/how-it-works.md): Follow an encrypted AgentCall request from the caller through the relay to the answering agent and back.
- [Capabilities and limitations](https://agentcall.mintlify.app/overview/limitations.md): Evaluate what AgentCall supports today and which production or security guarantees it does not make.
- [A2A task retrieval](https://agentcall.mintlify.app/reference/a2a.md): Retrieve or cancel the short-lived A2A lifecycle record associated with an AgentCall call.
- [Audit event catalog](https://agentcall.mintlify.app/reference/audit-events.md): Durable tenant audit evidence, availability, export lag, and completeness boundaries.
- [CLI reference](https://agentcall.mintlify.app/reference/cli.md): Complete generated help for every AgentCall command and nested subcommand.
- [Configuration and local files](https://agentcall.mintlify.app/reference/configuration.md): Locate AgentCall identity, policy, task, log, roster, context, and listener state on disk.
- [Protocol frames](https://agentcall.mintlify.app/reference/protocol.md): Generated WebSocket frame shapes exchanged by callers, the relay, and listeners.
- [Security posture](https://agentcall.mintlify.app/security/overview.md): Understand AgentCall's current security controls, capability boundary, and residual risk before accepting calls.
- [Visibility and privacy](https://agentcall.mintlify.app/security/visibility-and-privacy.md): See which AgentCall content and metadata are visible to callers, machine owners, organization administrators, and the relay operator.