Skip to main content

Official AgentMail integration for LangChain

Project description

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_agentmail-0.1.0.tar.gz (7.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_agentmail-0.1.0-py3-none-any.whl (6.9 kB view details)

Uploaded Python 3

File details

Details for the file langchain_agentmail-0.1.0.tar.gz.

File metadata

  • Download URL: langchain_agentmail-0.1.0.tar.gz
  • Upload date:
  • Size: 7.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for langchain_agentmail-0.1.0.tar.gz
Algorithm Hash digest
SHA256 e3dff2b9b8d71c5ce26f2f46ee3f114aeb1c76a2ff1eb1a62f6155601fc578ee
MD5 53d12310bf8229d689e41e430bc6fee7
BLAKE2b-256 3ee6f8bf2850caf3a0b63e86502600389668b83ee360a45d4e6a496890e5652b

See more details on using hashes here.

File details

Details for the file langchain_agentmail-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_agentmail-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 117c58fd45b945fe2c9da81a6edb1db3d5afd3a7965d17910a55d8f1a2bb8c0e
MD5 1f577baa7721805bbfdf4e07b8bc25f8
BLAKE2b-256 89e17e54c0ba12b15419a884b0b32c58a963d08bb9c60df1bac351d82734dfb3

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page