AgentMail: AI Agent Email Inbox for Openclaw

AgentMail provides AI agents with dedicated email addresses to send, receive, and manage digital communications programmatically.

rimelucci
v1.0.0
Feb 5, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install agent-mail-cli

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install agent-mail-cli using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is AgentMail: AI Agent Email Inbox?

AgentMail is a specialized email infrastructure designed specifically for the AI era. It allows developers to provision unique @agentmail.to addresses for their autonomous agents, enabling them to interact with human users and legacy systems through standard email protocols. By integrating AgentMail into your Openclaw Skills collection, you give your agents a persistent identity and a reliable communication channel.

This skill eliminates the need for agents to use personal human email accounts, providing a secure and isolated environment for automated messaging. Whether your agent needs to verify an account, send a report, or monitor an inbox for instructions, AgentMail offers the programmatic interface necessary to bridge the gap between AI agents and the global email network.

AgentMail: AI Agent Email Inbox Use Cases

  • Automating account signups by verifying email addresses and handling OTPs.
  • Receiving real-time notifications and alerts from external monitoring systems.
  • Sending professional outbound communications and status updates as an autonomous agent.
  • Monitoring marketplaces and job boards for specific keyword-based opportunities.
  • Providing a secure channel for human-to-agent communication via Openclaw Skills.

How AgentMail: AI Agent Email Inbox Works

  1. The user creates an inbox and generates an API key through the AgentMail console.
  2. The Openclaw Skills environment is configured with the API key and assigned email address stored in a secure local config file.
  3. The agent utilizes the Python SDK to authenticate with the AgentMail REST API.
  4. For inbound processing, the agent polls the inbox or receives webhook triggers to fetch new message objects.
  5. For outbound communication, the agent constructs message payloads and dispatches them through the send endpoint.

AgentMail: AI Agent Email Inbox Setup

First, install the required Python library:

pip install agentmail

Next, create a secure configuration directory and store your credentials:

mkdir -p ~/.agentmail
chmod 700 ~/.agentmail
cat > ~/.agentmail/config.json << 'EOF'
{
  "apiKey": "YOUR_API_KEY",
  "email": "[email protected]"
}
EOF
chmod 600 ~/.agentmail/config.json

AgentMail: AI Agent Email Inbox Data Schema & Taxonomy

The skill manages configuration and email data using the following structure:

Attribute Type Description
apiKey String The authentication token starting with am_.
email String The agent's specific @agentmail.to address.
inbox_id String The identifier used for API operations (usually the email).
messages Array A collection of objects containing from_address, subject, and text.
config.json File Local storage for credentials with restricted permissions.

AgentMail: AI Agent Email Inbox Advanced Features

  • Scheduled inbox polling using Openclaw Skills cron integration for regular updates.
  • Real-time notification support via AgentMail webhooks for instant agent reactivity.
  • Programmatic inbox creation allowing for dynamic multi-agent deployments.
  • CLI helper scripts for manual inbox checks and rapid testing of email flows.
  • REST API compatibility for integrating with non-Python workflows within the Openclaw Skills ecosystem.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*