LangChain + AgentMail
Official AgentMail integration for LangChain. Give your AI agents the ability to create email inboxes, send and receive emails, and automate email-based workflows like OTP verification.
Install
pip install langchain-agentmail
Quick Start
from langchain_agentmail import AgentMailToolkit
# Uses AGENTMAIL_API_KEY env var by default
toolkit = AgentMailToolkit()
tools = toolkit.get_tools()
Create an Inbox
result = tools[0].invoke({"name": "test-inbox"}) # CreateInbox
print(result) # {"inbox_id": "...", "email": "..."}
Send and Read Emails
# Send an email
tools[1].invoke({"to": "user@example.com", "subject": "Hello", "body": "Hi there!", "from": "inbox_abc123"})
# Wait for a reply (blocks up to 60s)
msg = tools[6].invoke({"inbox_id": "inbox_abc123", "timeout": 60})
Use with a LangGraph Agent
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
from langchain_agentmail import AgentMailToolkit
toolkit = AgentMailToolkit()
agent = create_react_agent(ChatOpenAI(model="gpt-4o-mini"), toolkit.get_tools())
result = agent.invoke({"messages": [{"role": "user", "content": "Create an inbox and wait for a verification email"}]})
See example.py for a full OTP-automation agent.
Environment Variables
| Variable | Description |
|---|---|
AGENTMAIL_API_KEY |
Your AgentMail API key (required) |
Tools
| Tool | Description |
|---|---|
CreateInbox |
Create a new email inbox |
SendEmail |
Send an email |
ListMessages |
List messages in an inbox |
GetMessage |
Get a single message by ID |
ReplyToEmail |
Reply to a message |
ForwardEmail |
Forward a message |
WaitForMessage |
Block until a new message arrives |
SearchMessages |
Search messages by query |
CreateLabel |
Create an organizational label |
ApplyLabel |
Apply a label to a message |
DeleteInbox |
Delete an inbox permanently |
License
MIT
Metadata
Release files for langchain-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 |
|---|---|---|---|---|
| langchain_agentmail-0.1.0.tar.gz | 7.0 kB | Without provenance | Details for langchain_agentmail-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| langchain_agentmail-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for langchain_agentmail-0.1.0-py3-none-any.whl |
Total release size: 13.8 kB
Release files / langchain_agentmail-0.1.0.tar.gz
| Download URL | langchain_agentmail-0.1.0.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e3dff2b9b8d71c5ce26f2f46ee3f114aeb1c76a2ff1eb1a62f6155601fc578ee
|
|
BLAKE2b-256 checksum How to use checksums |
3ee6f8bf2850caf3a0b63e86502600389668b83ee360a45d4e6a496890e5652b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / langchain_agentmail-0.1.0-py3-none-any.whl
| Download URL | langchain_agentmail-0.1.0-py3-none-any.whl |
|---|---|
| Size | 6.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
117c58fd45b945fe2c9da81a6edb1db3d5afd3a7965d17910a55d8f1a2bb8c0e
|
|
BLAKE2b-256 checksum How to use checksums |
89e17e54c0ba12b15419a884b0b32c58a963d08bb9c60df1bac351d82734dfb3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for langchain-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.