agentmail-toolkit

Add email capabilities to AI agents using popular frameworks. Provides pre-built tools for TypeScript and Python frameworks including Vercel AI SDK, LangChain, Clawdbot, OpenAI Agents SDK, and LiveKit Agents. Use when integrating AgentMail with agent frameworks that need email send/receive tools.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "agentmail-toolkit" with this command: npx skills add agentmail-to/agentmail-skills/agentmail-to-agentmail-skills-agentmail-toolkit

AgentMail Toolkit

Pre-built email tools for popular agent frameworks. Instantly add inbox management, sending, receiving, and email automation to your agents.

Installation

# TypeScript/Node
npm install agentmail-toolkit

# Python
pip install agentmail-toolkit

Configuration

Set your API key as an environment variable:

export AGENTMAIL_API_KEY=your-api-key

Get your API key from console.agentmail.to.


TypeScript Frameworks

Vercel AI SDK

import { AgentMailToolkit } from "agentmail-toolkit/ai-sdk";
import { streamText } from "ai";
import { openai } from "@ai-sdk/openai";

const toolkit = new AgentMailToolkit();

const result = await streamText({
  model: openai("gpt-4o"),
  messages,
  system: "You are an email agent that can send and receive emails.",
  tools: toolkit.getTools(),
});

LangChain

import { createAgent, HumanMessage, AIMessage } from "langchain";
import { AgentMailToolkit } from "agentmail-toolkit/langchain";

const agent = createAgent({
  model: "openai:gpt-4o",
  tools: new AgentMailToolkit().getTools(),
  systemPrompt: "You are an email agent that can send and receive emails.",
});

const result = await agent.stream({ messages }, { streamMode: "messages" });

Clawdbot (Pi Agent)

For Clawdbot/Pi Agent integration.

import { AgentMailToolkit } from "agentmail-toolkit/clawdbot";

const toolkit = new AgentMailToolkit();
const tools = toolkit.getTools();

// Each tool has: name, label, description, parameters, execute
for (const tool of tools) {
  agent.registerTool(tool);
}

Python Frameworks

OpenAI Agents SDK

from agentmail_toolkit.openai import AgentMailToolkit
from agents import Agent

agent = Agent(
    name="Email Agent",
    instructions="You can send, receive, and manage emails.",
    tools=AgentMailToolkit().get_tools(),
)

LangChain

from langchain.agents import create_agent
from agentmail_toolkit.langchain import AgentMailToolkit

agent = create_agent(
    model="gpt-4o",
    system_prompt="You are an email agent that can send and receive emails.",
    tools=AgentMailToolkit().get_tools(),
)

result = agent.stream({"messages": messages}, stream_mode="messages")

LiveKit Agents

For voice AI agents with email capabilities.

from livekit.agents import Agent
from agentmail_toolkit.livekit import AgentMailToolkit

agent = Agent(
    name="Voice Email Agent",
    tools=AgentMailToolkit().get_tools(),
)

Available Tools

The Node and Python toolkits ship different tool sets. The Node toolkit includes drafts; the Python toolkit does not.

ToolDescriptionNodePython
create_inboxCreate a new email inbox
list_inboxesList all inboxes
get_inboxGet inbox details
delete_inboxDelete an inbox
send_messageSend an email
reply_to_messageReply to an email
forward_messageForward an email
update_messageUpdate message labels
list_threadsList email threads
get_threadGet thread details
get_attachmentDownload an attachment
create_draftCreate a draft message
list_draftsList drafts in an inbox
get_draftGet a draft by ID
update_draftUpdate a draft
send_draftSend a previously-created draft
delete_draftDelete a draft without sending

Node toolkit: 17 tools. Python toolkit: 11 tools. If you need draft support from Python, call client.inboxes.drafts.* directly on the AgentMail SDK client.


Custom Configuration

Both toolkits take an existing SDK client as their only constructor argument — they do NOT accept apiKey / api_key directly. If you need a custom API key, construct the SDK client with the key first, then pass the client to the toolkit.

TypeScript

import { AgentMailClient } from "agentmail";
import { AgentMailToolkit } from "agentmail-toolkit/ai-sdk";

// With a custom API key
const client = new AgentMailClient({ apiKey: "your-api-key" });
const toolkit = new AgentMailToolkit(client);

// Or omit the argument to auto-read AGENTMAIL_API_KEY from env
const defaultToolkit = new AgentMailToolkit();

Python

from agentmail import AgentMail
from agentmail_toolkit.openai import AgentMailToolkit

# With a custom API key
client = AgentMail(api_key="your-api-key")
toolkit = AgentMailToolkit(client=client)

# Or omit the argument to auto-read AGENTMAIL_API_KEY from env
default_toolkit = AgentMailToolkit()

Framework Summary

FrameworkTypeScript ImportPython Import
Vercel AI SDKfrom 'agentmail-toolkit/ai-sdk'-
LangChainfrom 'agentmail-toolkit/langchain'from agentmail_toolkit.langchain import AgentMailToolkit
Clawdbotfrom 'agentmail-toolkit/clawdbot'-
OpenAI Agents SDK-from agentmail_toolkit.openai import AgentMailToolkit
LiveKit Agents-from agentmail_toolkit.livekit import AgentMailToolkit

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

agentmail

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

agentmail-cli

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

agentmail-mcp

No summary provided by upstream source.

Repository SourceNeeds Review
Web3

tcm-constitution-recognition-analysis

Determines nine TCM constitution types including Yin deficiency, Yang deficiency, Qi deficiency, phlegm-dampness, and blood stasis through facial features and physical signs, and provides personalized health preservation and conditioning suggestions. | 中医体质识别分析技能,通过面部特征与体征判别阴虚、阳虚、气虚、痰湿、血瘀等九种中医体质类型,给出个性化养生调理建议

Archived SourceRecently Updated