The Local class is the primary entry point for using the cloudcode Python SDK in your projects.

This Class is the lowest level sdk you’ll need to create an AI Coding agent.

​
Key Features

  • AI-Powered Code Modification: Transform code with natural language prompts using leading AI models like GPT-4 and Claude
  • File Management: Create, read, modify, and search files in your local environment
  • Cost Tracking: Monitor and manage your API usage with detailed cost reporting
  • Git Integration: Optional tracking of changes via git for easy review and rollback
  • Asynchronous Processing: Run long coding tasks in the background with headless mode
  • Architect Mode: Use a two-model approach for better efficiency and performance

​
When to Use Local SDK

The Local SDK is ideal when you want to:

  • Integrate AI-assisted coding into your own applications or workflows
  • Work with code in your existing local environment
  • Maintain control over your files and version control
  • Track costs and manage API usage programmatically

​
Quick Start Example

Run the real Quick Start script included in the examples:

python cloud-coding/examples/quick-start.py

This script will:

  • Create src/calculator.py
  • Add multiply and divide functions with zero-division handling
  • Print the diff and updated file content

Here’s the core snippet from quick-start.py:

from cloudcode import Local
import os

sdk = Local(working_dir=os.getcwd(), api_key=os.getenv("CLOUD_CODE_API_KEY"))

result = sdk.code(
    prompt="Add multiply and divide functions to the calculator with zero-division handling.",
    editable_files=["src/calculator.py"]
)

if result["success"]:
    print("Changes:", result["diff"])
    print("Updated content:", sdk.read_file("src/calculator.py"))

For installation instructions, see Installation.

To understand the configuration options, see Configuration.