Connect an AI model for your machine learning project

Model Ledger lets you choose how the agent talks to a language model. You can pick a cloud provider through a standard API endpoint, run a model locally on your PC, or use the built-in model. This choice affects privacy and speed.

Choose your model source

Cloud AI provider

Use a cloud AI provider through a standard API endpoint. Your prompt and file content leave your machine. You control which provider you pick and pay for their usage. The agent sends data to that specific endpoint only.

Local PC model

Run a model directly on your PC. This keeps all your data inside your computer. Your prompts and file contents never leave the machine. This is ideal for sensitive projects or strict privacy rules. You manage the model files and hardware resources yourself.

Built-in model

A built-in model is available as an option.

Test your connection

Press the Test button to check your endpoint. The tool shows the response time and the context window size.

Pick the right model for the task

Use a bigger model for refactors or complex logic. Use a smaller model for small edits. The run_on_model tool sends hard steps to a bigger model.

Quality varies between models and settings. Always review the diff before accepting changes. Use Ask first to pause before every action that changes something. You see the exact file changes and can decide if they are correct.