Skip to main content

langchain-paylobster

LangChain integration for PayLobster - AI agent payment escrow on Base.

Installation

pip install langchain-paylobster

Quick Start

from langchain_paylobster import (
    PayLobsterCreateEscrow,
    PayLobsterReleaseEscrow,
    PayLobsterCheckReputation,
    PayLobsterRegisterAgent,
    PayLobsterGetBalance,
)
from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI

# Initialize tools
tools = [
    PayLobsterCreateEscrow(),
    PayLobsterReleaseEscrow(),
    PayLobsterCheckReputation(),
    PayLobsterRegisterAgent(),
    PayLobsterGetBalance(),
]

# Create agent
llm = ChatOpenAI(temperature=0, model="gpt-4")
agent = initialize_agent(
    tools, 
    llm, 
    agent=AgentType.OPENAI_FUNCTIONS, 
    verbose=True
)

# Use the agent
response = agent.run(
    "Check the reputation of agent 0x742d35Cc6634C0532925a3b844Bc9e7595f0bEb"
)
print(response)

Available Tools

PayLobsterCreateEscrow

Create a payment escrow that locks USDC funds until work is completed.

Parameters:

  • worker_address: Ethereum address of the worker
  • amount_usdc: Amount in USDC (e.g., 100.50)
  • deadline_hours: Hours until deadline (default: 24)
  • description: Description of the work
  • private_key: Your private key (client)

PayLobsterReleaseEscrow

Release payment to the worker after work is completed.

Parameters:

  • escrow_id: ID of the escrow to release
  • private_key: Your private key (must be the client)

PayLobsterCheckReputation

Check an agent's reputation score and task history.

Parameters:

  • agent_address: Ethereum address of the agent

PayLobsterRegisterAgent

Register your agent on the PayLobster identity system.

Parameters:

  • metadata: JSON string with agent info (capabilities, contact, etc.)
  • private_key: Your agent's private key

PayLobsterGetBalance

Check USDC balance of any address on Base.

Parameters:

  • address: Ethereum address to check

Example: Negotiating Agent

See examples/negotiating_agent.py for a complete example of an agent that can:

  • Negotiate work terms
  • Create escrow for agreed payment
  • Track reputation of potential workers
  • Release payment upon completion

Contract Addresses (Base Mainnet)

  • Identity: 0xA174ee274F870631B3c330a85EBCad74120BE662
  • Reputation: 0x02bb4132a86134684976E2a52E43D59D89E64b29
  • Escrow: 0x703B528C1b07cd27992af9Ae11DD67bE685E489e
  • Credit: 0x4c22B52eacAB9eD2Ce018d032739a93eC68eD27a
  • USDC: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913

Security

⚠️ Never hardcode private keys in production! Use environment variables or secure key management:

import os
private_key = os.environ.get("AGENT_PRIVATE_KEY")

License

MIT

Metadata

Release files for langchain-paylobster 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for langchain-paylobster 0.1.0
File Size Uploaded
langchain_paylobster-0.1.0.tar.gz 6.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for langchain-paylobster 0.1.0
File Interpreter ABI Platform
langchain_paylobster-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 13.7 kB

Release files / langchain_paylobster-0.1.0.tar.gz

Download URL langchain_paylobster-0.1.0.tar.gz
Size 6.6 kB
Tags Source
SHA-256 checksum
How to use checksums
d920a0058146216f947db48a4025882115e7db6da5da0d163483b901584a2fb9
BLAKE2b-256 checksum
How to use checksums
1631889fc0e97c67b20dd9685c8017d56c9d69891e7f0d93fcd98ddc4e99e5b4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.6

Release files / langchain_paylobster-0.1.0-py3-none-any.whl

Download URL langchain_paylobster-0.1.0-py3-none-any.whl
Size 7.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
96f9cb86e9fab9c65a4d2a5216dae283cac913ef4fed254f62ec542b1c6e64eb
BLAKE2b-256 checksum
How to use checksums
d61859f0c1bb5df58526a1cbc06c115f9bedf14e41a6a34fbe20c2b6a4a01ad0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.6

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page