LangChain tools for AgentPayment Network — autonomous agent-to-agent payments
Project description
langchain-agentpayment
LangChain tools for AgentPayment Network — autonomous agent-to-agent payments across crypto, card, and ACH.
Installation
pip install langchain-agentpayment
Quick Start
from langchain_agentpayment import AgentPaymentToolkit
from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
# Initialize toolkit
toolkit = AgentPaymentToolkit(api_key="apn_your_key_here")
tools = toolkit.get_tools()
# Create agent
llm = ChatOpenAI(model="gpt-4o")
prompt = ChatPromptTemplate.from_messages([
("system", "You are an autonomous agent that can send and receive payments."),
("human", "{input}"),
("placeholder", "{agent_scratchpad}"),
])
agent = create_tool_calling_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
# Run
executor.invoke({"input": "Create an invoice for agent_abc for $5 for API usage"})
executor.invoke({"input": "Set a billing rule to auto-pay up to $10 from provider_xyz via crypto"})
executor.invoke({"input": "Set a circuit breaker with max $100/day spend limit"})
Available Tools
| Tool | Description |
|---|---|
create_invoice |
Bill a consumer agent for services rendered |
approve_invoice |
Manually approve and pay a pending invoice |
set_billing_rule |
Auto-approve invoices from a provider |
check_invoice_status |
Check status of an invoice |
list_invoices |
List sent/received invoices |
create_recurring_billing |
Set up recurring billing (Model A or B) |
set_circuit_breaker |
Set daily spend/transaction limits |
Pricing
Volume-based, dual-sided:
- 0–10k requests/month: 1% consumer + 1% provider
- 10k–20k: 0.9% each side
- 20k+: 0.8% each side
Links
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file langchain_agentpayment-0.1.0.tar.gz.
File metadata
- Download URL: langchain_agentpayment-0.1.0.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ab3deddbdc60f15e1d0839b903b44b429cba2e468444b343703065d5dcf9bca6
|
|
| MD5 |
ccfc71939aeaa25527858439de3c4068
|
|
| BLAKE2b-256 |
645551f57a68d8d1f7207f1f0b0cba515e537823dd67b5b650f26a067632770a
|
File details
Details for the file langchain_agentpayment-0.1.0-py3-none-any.whl.
File metadata
- Download URL: langchain_agentpayment-0.1.0-py3-none-any.whl
- Upload date:
- Size: 5.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1d46d57d278d732f18e7de2dad4ce8794834d37d9756ccd89734d0b557264e22
|
|
| MD5 |
d7798e42beac08807493bdf7c29f827a
|
|
| BLAKE2b-256 |
4546a17170a3138c119b9c487054522945eb0f960fa4ed5a7e53ec092996bd4c
|