An AI-friendly Python skill for sending, receiving, and threading emails via the agentmail.to API using structured JSON data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install python-agentmail-send-receive
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install python-agentmail-send-receive 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 Python Agentmail Send & Receive?
This skill provides a specialized interface for AI agents to interact with email accounts through the agentmail.to service. Unlike traditional IMAP/SMTP setups, it uses a modern API that is highly compatible with automated workflows, allowing agents to process messages as structured JSON data.
By integrating this into Openclaw Skills, developers can grant their agents a persistent email identity to communicate with humans or other services. The skill handles the complexities of authentication and message formatting, enabling agents to focus on content processing and automated decision-making. It is specifically designed to be lightweight, using local Python scripts and environment variables for secure configuration.
Python Agentmail Send & Receive Use Cases
- Automated customer support where an AI agent handles incoming inquiries via email.
- Notifying human users of task completion or system alerts with automated outbound messages.
- Processing incoming data, reports, or logs sent to a dedicated agent inbox.
- Building human-in-the-loop systems where an agent requests clarification or approval via email threads.
- Enabling cross-agent communication through a standardized email protocol.
How Python Agentmail Send & Receive Works
- The agent executes the check_mail.py script to fetch unread messages from the agentmail.to API.
- Unread messages are downloaded and saved into the local workspace as individual JSON files with a timestamped naming convention.
- The AI agent parses the JSON files to extract metadata such as sender, subject, and the plain-text or HTML body.
- To respond, the agent utilizes the send_email.py script or a custom reply function to maintain conversation threads via message IDs.
- Once processed, the agent can clean up the workspace by deleting the JSON files, ready for the next polling cycle.
Python Agentmail Send & Receive Setup
Deploy the Skill
Run the following commands to set up the workspace and install dependencies within Openclaw Skills:
DEST=~/.openclaw/workspace/agentmail
mkdir -p "$DEST"
# Copy scripts to the destination and navigate there
cd "$DEST"
# Create a virtual environment and install requirements
python3 -m venv venv
source venv/bin/activate
pip install agentmail python-dotenv
Configuration
Create a .env file in the workspace directory with your API key:
echo "AGENTMAIL_API_KEY=your_api_key_here" > ~/.openclaw/workspace/agentmail/.env
Python Agentmail Send & Receive Data Schema & Taxonomy
The skill organizes emails into local JSON files named MAIL.<TIMESTAMP>.<SEQUENCE>.
| Key | Description |
|---|---|
message_id |
Unique identifier for the specific email. |
thread_id |
Identifier used to group related messages. |
from |
The sender's display name and email address. |
subject |
The email subject line. |
text |
The plain-text version of the email body. |
html |
The HTML version of the email body. |
labels |
Array of tags such as "received" or "unread". |
Python Agentmail Send & Receive Advanced Features
- Context-aware threading: Use the
reply()method with amessage_idto keep conversations organized in a single thread. - Robust error handling: Detailed exit codes (0-3) allow agents to diagnose API errors or missing credentials autonomously.
- JSON-first architecture: Designed specifically for LLMs to easily parse and generate content without complex MIME handling.
- Headless operation: Designed to run in CLI environments and containerized AI agent workflows within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Shield
A comprehensive security audit engine designed to identify vulnerabilities, secret leaks, and misconfigurations in your OpenClaw setup.
Daily AI News Briefing
An automated news aggregator that scans top tech publications and research papers to deliver a structured daily briefing on the AI industry.
Fathom
A powerful integration for retrieving meeting intelligence, including transcripts and action items, directly from Fathom AI.
launchthatbot-git-team-ops
A role-based GitOps skill that assigns junior or senior operating modes to AI agents for secure, governed GitHub repository management.
bili-summary
An AI-powered tool for downloading, transcribing, and generating detailed summaries from Bilibili videos using Google Gemini and Whisper.
IELTS Test Data Extraction Skill
A specialized skill designed to programmatically extract IELTS reading articles and question sets from Cambridge PDF materials into structured JSON format.
Featured*
