This project is a Lua-based completion engine for Neovim that aggregates real-time text suggestions from multiple data sources into a single interface. It functions as a modular framework for extending the editor with custom completion logic, acting as both a fuzzy text suggestion tool and an interface for the Language Server Protocol.
The engine utilizes a source-agnostic provider interface to standardize how disparate data sources feed candidates into a central logic engine. It employs asynchronous candidate fetching and a non-blocking architecture to retrieve suggestions from external servers and filesystems without freezing the editor interface.
The capability surface covers a wide range of specialized completions, including language server symbols, filesystem paths, buffer text, and git metadata. It also provides integration for large language models for AI-assisted coding, as well as specialized suggestions for CSS styling, academic references, and symbol insertion.
The system includes a dynamic menu for rendering results and a keymap management system for navigating and confirming suggestions.
