lumide_swiftly

🍄 An OpenAI-compatible code autocomplete and inline completion plugin for the Lumide IDE.

Features

• Fast Autocomplete: Low-latency token streaming with early halting.
• Context-Aware: Uses recently opened files and editor selections to improve suggestions.
• Smart Cache: Local prefix cache with LRU eviction and deferred disk writes.

Setup

Navigate to Lumide -> Settings -> Lumide Swiftly under Plugins and configure:

• Provider URL: The base URL of your OpenAI-compatible endpoint.
• API Key: Your API key (if required).
• Model: The model name to use for completion.

Then click on AI Completion provider icon under Status Bar -> choose Lumide Swiftly.

How to Use

• Trigger: Suggestions appear automatically as gray "ghost text" as you type.
• Accept: Press Tab to insert.
• Dismiss: Press Esc or continue typing.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Built with ❤️ by SoFluffy.

Happy Coding 🦊