Skip to main content
Ampersend enables LangChain agents to pay for and use remote AI agent services. Payments are handled transparently via the x402 protocol, with A2A as the communication layer.

​
Overview

​
Integration details

ClassPackageSerializableJS supportVersion
A2AToolkitlangchain-ampersend❌❌PyPI - Version

​
Tool features

  1. a2a_get_agent_details - Get capabilities of the remote agent
  2. a2a_send_message - Send messages to the remote agent (payments handled automatically)

​
Key features

  • Spend controls: Pluggable payment authorization with limits and policies
  • Transparent payments: x402 protocol handles payment negotiation automatically

​
Setup

​
Installation

Install the langchain-ampersend package: 
pip install -U langchain-ampersend

​
Credentials

The toolkit requires a session key and smart account address, which you can obtain from the Ampersend dashboard.
Set up credentials
import os

SESSION_KEY = os.environ.get("AMPERSEND_SESSION_KEY")  # 0x...
SMART_ACCOUNT_ADDRESS = os.environ.get("AMPERSEND_SMART_ACCOUNT_ADDRESS")  # 0x...

​
Instantiation

Initialize toolkit
from langchain_ampersend import (
    A2AToolkit,
    AmpersendTreasurer,
    ApiClient,
    ApiClientOptions,
    SmartAccountConfig,
    SmartAccountWallet,
)

# Setup wallet
wallet = SmartAccountWallet(
    config=SmartAccountConfig(
        session_key=SESSION_KEY,
        smart_account_address=SMART_ACCOUNT_ADDRESS,
    )
)

# Setup treasurer
treasurer = AmpersendTreasurer(
    api_client=ApiClient(
        options=ApiClientOptions(
            base_url="https://api.ampersend.ai",
            session_key_private_key=SESSION_KEY,
        )
    ),
    wallet=wallet,
)

# Create toolkit
toolkit = A2AToolkit(
    remote_agent_url="https://agent.example.com",
    treasurer=treasurer,
)

await toolkit.initialize()

​
Invocation

Send a message to the remote agent:
Send message
tools = toolkit.get_tools()
send_tool = tools[1]  # a2a_send_message
response = await send_tool.ainvoke({"message": "Analyze the sales trends in Q4"})
print(response)

​
Use within an agent

Create agent
from langchain.agents import create_agent
from langchain_anthropic import ChatAnthropic

# Initialize the LLM
llm = ChatAnthropic(model="claude-sonnet-4-20250514")

# Get tools from the toolkit
tools = toolkit.get_tools()

# Create the agent
agent = create_agent(llm, tools)
Example usage:
Run agent
result = await agent.ainvoke({
    "messages": [("user", "What can this agent do, and then ask it to analyze recent trends")]
})

# The agent will call the remote agent and handle payments automatically

​
How payments work

When the remote agent requires payment (HTTP 402), the toolkit:
  1. Receives the payment requirement
  2. Calls the treasurer to authorize the payment
  3. Signs the payment with the configured wallet
  4. Retries the request with the payment attached
This is transparent to your LangChain agent. The AmpersendTreasurer provides managed payment sessions with spend limits and analytics. Alternative treasurer implementations are available in ampersend_sdk.

​
API reference

Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.