PaymanAI

PaymanAI provides functionality to send and receive payments (fiat and crypto) on behalf of an AI Agent. To get started:

Sign up at app.paymanai.com to create an AI Agent and obtain your API Key.
Set environment variables (PAYMAN_API_SECRET for your API Key, PAYMAN_ENVIRONMENT for sandbox or production).

This notebook gives a quick overview of integrating PaymanAI into LangChain as a tool. For complete reference, see the API documentation.

Overview

The PaymanAI integration is part of the langchain-community (or your custom) package. It allows you to:

Send payments (send_payment) to crypto addresses or bank accounts.
Search for payees (search_payees).
Add new payees (add_payee).
Request money from customers with a hosted checkout link (ask_for_money).
Check agent or customer balances (get_balance).

These can be wrapped as LangChain Tools for an LLM-based agent to call them automatically.

Integration details

Class	Package	Serializable	JS support	Version
PaymanAI	`langchain-payman-tool`	❌	❌	[PyPI Version]

If you’re simply calling the PaymanAI SDK, you can do it directly or via the Tool interface in LangChain.

Setup

Install the PaymanAI tool package:

pip install langchain-payman-tool

uv add langchain-payman-tool

Install the PaymanAI SDK:

pip install paymanai

uv add paymanai

Set environment variables:

export PAYMAN_API_SECRET="YOUR_SECRET_KEY"
export PAYMAN_ENVIRONMENT="sandbox"

Your PAYMAN_API_SECRET should be the secret key from app.paymanai.com. The PAYMAN_ENVIRONMENT can be sandbox or production depending on your usage.

Instantiation

Here is an example of instantiating a PaymanAI tool. If you have multiple Payman methods, you can create multiple tools.

from langchain_payman_tool.tool import PaymanAI

# Instantiate the PaymanAI tool (example)
tool = PaymanAI(
    name="send_payment",
    description="Send a payment to a specified payee.",
)

Invocation

Invoke directly with args

You can call tool.invoke(...) and pass a dictionary matching the tool’s expected fields. For example:

response = tool.invoke({
    "amount_decimal": 10.00,
    "payment_destination_id": "abc123",
    "customer_id": "cust_001",
    "memo": "Payment for invoice #XYZ"
})

Invoke with ToolCall

When used inside an AI workflow, the LLM might produce a ToolCall dict. You can simulate it as follows:

model_generated_tool_call = {
    "args": {
        "amount_decimal": 10.00,
        "payment_destination_id": "abc123"
    },
    "id": "1",
    "name": tool.name,
    "type": "tool_call",
}
tool.invoke(model_generated_tool_call)

Using the Tool in a Chain or Agent

You can bind a PaymanAI tool to a LangChain agent or chain that supports tool-calling.

Quick Start Summary

Sign up at app.paymanai.com to get your API Key.

Install dependencies:

pip install paymanai langchain-payman-tool

Export environment variables:

export PAYMAN_API_SECRET="YOUR_SECRET_KEY"
export PAYMAN_ENVIRONMENT="sandbox"

Instantiate a PaymanAI tool, passing your desired name/description.
Call the tool with .invoke(...) or integrate it into a chain or agent.

快速开始

核心组件

进阶使用

在生产环境使用

Overview

Integration details

Setup

Instantiation

Invocation

Invoke directly with args

Invoke with ToolCall

Using the Tool in a Chain or Agent

Quick Start Summary

​Overview

​Integration details

​Setup

​Instantiation

​Invocation

​Invoke directly with args

​Invoke with ToolCall

​Using the Tool in a Chain or Agent

​Quick Start Summary

Overview

Integration details

Setup

Instantiation

Invocation

Invoke directly with args

Invoke with ToolCall

Using the Tool in a Chain or Agent

Quick Start Summary