AutoGen + AgentMail
Official AgentMail integration for AutoGen / AG2. Give your agents real email inboxes — send, receive, reply, forward, and organize messages via the AgentMail API.
Install
pip install autogen-agentmail
Quick Start
1. Set your API key
export AGENTMAIL_API_KEY=your_key_here
2. Create an inbox for your agent
from autogen_agentmail import create_inbox
inbox = create_inbox(name="My Agent")
print(inbox["email"]) # e.g. agent-abc123@agentmail.to
3. Send an email
from autogen_agentmail import send_email
send_email(
to="bob@example.com",
subject="Hello from my agent",
body="This is an automated message.",
from_inbox_id=inbox["id"],
)
4. Wait for a reply
from autogen_agentmail import wait_for_message
msg = wait_for_message(inbox_id=inbox["id"], timeout=60)
print(msg["body"])
5. Register all tools with an AutoGen agent
import autogen
from autogen_agentmail import register_agentmail_tools
agent = autogen.ConversableAgent(
name="EmailBot",
llm_config={"config_list": [{"model": "gpt-4o"}]},
)
register_agentmail_tools(agent)
# Agent can now create_inbox, send_email, list_messages, etc.
Available Tools
| Tool | Description |
|---|---|
create_inbox |
Create a new email inbox |
send_email |
Send an email from an inbox |
list_messages |
List messages in an inbox |
get_message |
Get a single message by ID |
reply_to_email |
Reply to a message |
forward_email |
Forward a message to another recipient |
wait_for_message |
Long-poll for new messages |
search_messages |
Search messages by keyword |
create_label |
Create a label/tag |
apply_label |
Apply a label to a message |
delete_inbox |
Delete an inbox and its messages |
Example
See example.py for a full demo of two agents communicating via email with inboxes, send, wait, and cleanup.
Configuration
| Variable | Description | Default |
|---|---|---|
AGENTMAIL_API_KEY |
Your AgentMail API key | — |
api_key param |
Per-call override | env var |
base_url param |
Custom API base URL | https://api.agentmail.to |
License
MIT
Metadata
Release files for autogen-agentmail 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| autogen_agentmail-0.1.0.tar.gz | 7.4 kB | Without provenance | Details for autogen_agentmail-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| autogen_agentmail-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for autogen_agentmail-0.1.0-py3-none-any.whl |
Total release size: 14.7 kB
Release files / autogen_agentmail-0.1.0.tar.gz
| Download URL | autogen_agentmail-0.1.0.tar.gz |
|---|---|
| Size | 7.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bad3a4cb08bb878b835cda95a67d44f08fbbab5a06292ac496dc35c8c79c43f6
|
|
BLAKE2b-256 checksum How to use checksums |
19ca682aefa1acd3695c984afb696ff373c8b7cec6111357a46678dc942081da
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / autogen_agentmail-0.1.0-py3-none-any.whl
| Download URL | autogen_agentmail-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
27d03edf0b1de4d13ef8e9cb683ea4cd2842531f1f0ad260ad211c316bf51916
|
|
BLAKE2b-256 checksum How to use checksums |
c08887021db9401c9d86471f9387b4c64c11577d930baf9fcf9792a0ae7ccb80
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for autogen-agentmail 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.