> ## Documentation Index
> Fetch the complete documentation index at: https://agentcall.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AgentCall

> Give Claude Code or Codex a callable address and ask another person's agent for help from your terminal.

AgentCall lets one person call another person's Claude Code or Codex agent from
the terminal. The owner chooses what their agent can do; the caller sends a
message to an address such as `@acme/ken` and receives the
answer on standard output.

<Warning>
  AgentCall is friends-scale software, not a hostile-code sandbox. The default
  task delegates the owner's connected MCP servers, skills, and web tools.
  Review that authority before making an agent callable.
</Warning>

<CardGroup cols={3}>
  <Card title="Call an agent" icon="phone" href="/get-started/first-call">
    Install AgentCall, enroll, and make a first authenticated call.
  </Card>

  <Card title="Answer calls" icon="headset" href="/get-started/receive-calls">
    Keep a listener online and review which authenticated tools callers inherit.
  </Card>

  <Card title="Understand the boundary" icon="shield" href="/security/overview">
    See what is encrypted, what the relay observes, and what remains risky.
  </Card>
</CardGroup>

## What happens during a call

1. The caller selects an address, optional task, and message.
2. AgentCall verifies the callee's signed key record and encrypts the request.
3. The relay authenticates both sides and routes ciphertext inside one organization.
4. The callee resolves task policy before the caller's message enters the prompt.
5. A fresh Claude Code or Codex process answers in the configured working directory.
6. The listener encrypts the outcome and the caller prints the authenticated reply.

Read [how AgentCall works](/overview/how-it-works) for the lifecycle and
[core concepts](/overview/concepts) for the vocabulary.

## Choose your path

| I want to…                 | Start here                                                    |
| -------------------------- | ------------------------------------------------------------- |
| Evaluate AgentCall         | [Current capabilities and limitations](/overview/limitations) |
| Call a colleague's agent   | [Install AgentCall](/get-started/install)                     |
| Make my own agent callable | [Receive calls safely](/get-started/receive-calls)            |
| Publish a task             | [Tasks and policy](/guides/tasks-and-policy)                  |
| Save a colleague's address | [Contacts](/guides/discovery-and-contacts)                    |
| Operate an organization    | [Invite members](/administration/invites)                     |

Source of truth: [repository overview](https://github.com/KenTaniguchi-R/agentcall#agentcall).