Connect an AI model for your Unreal Engine code

Ignite Codeworks runs your AI agent with a cloud provider, a local PC model, or the built-in option. You pick the endpoint, test the connection, and in Ask first mode you review each change before it is applied.

Choose your model source

Cloud AI provider

Send prompts to a cloud AI provider through a standard API endpoint. The agent reads your files and sends the context to that provider. Your working folder stays on your PC, but the text leaves the machine. Use this when you need strong reasoning for complex refactors. You control which provider you connect to.

Local PC model

Run a model directly on your Windows PC. Nothing leaves your machine when you use this option. The agent reads files and writes changes locally. This suits privacy-sensitive projects or unstable networks. You manage the model binary and the connection settings yourself. It works with the same tools as cloud mode.

Built-in model

Use the built-in model included with the application. It requires no external configuration or API keys. The agent runs immediately after installation. This option keeps the setup minimal. You can switch to a cloud or local model later.

Verify the connection

Press the Test button to check the endpoint. It shows response time and the context window.

Select the right model size

Use a bigger model for heavy refactors or complex logic. Run hard steps with run_on_model to get better results. Smaller models work well for small edits and quick fixes. Choose based on the complexity of the task. The agent handles the routing automatically.

Quality varies between models and tasks. Always review the diff before accepting changes. Use Ask first to pause before every action that changes something. You see the exact file modifications. This keeps you in control of the codebase.