SourceHarbor
Models

Choose your AI model

02

SourceHarbor connects to an external cloud provider via a standard API endpoint, a model running locally on your PC, or the built-in model. Each option changes privacy, speed, and cost. You pick the one that fits your workflow.

SourceHarbor→API endpoint→Model

Three ways to run intelligence

Cloud AI provider

Connect to a cloud AI provider through a standard API endpoint. The prompt and file text travel to that provider, so your code leaves the machine. Privacy depends on the provider’s data retention policy. You may pay for usage.

Local PC model

With a local model nothing leaves the PC.

Built-in model

Use the built-in model for simple edits and quick checks. This option requires no external configuration or API keys. It is ready to use without your own endpoint. The model handles routine tasks.

Verify your connection

Press the Test button to check your endpoint. The tool shows the response time and context window size. This confirms the model is reachable and ready. You can adjust settings before starting work.

Select the right model size

Use a bigger model for complex refactors and hard logic steps. Send these steps to a larger model using run_on_model.

Quality varies between models and runs. Always review the diff in Ask first mode. This mode pauses before actions that change something. You see the exact file changes before accepting. This prevents unwanted modifications to your code. Trust the diff to confirm the agent’s intent.

SourceHarbor for Windows

Start scanning your code now

Download SourceHarbor ↗