llama.vscode is a Visual Studio Code extension that provides AI-assisted coding features powered primarily by locally running language models. The extension is designed to be lightweight and efficient, enabling developers to use AI tools even on consumer-grade hardware. It integrates with the llama.cpp runtime to run language models locally, eliminating the need to rely entirely on external APIs or cloud providers. The extension supports common AI development features such as code completion, conversational chat assistance, and AI-assisted code editing directly within the IDE. Developers can select and manage models through a configuration interface that automatically downloads and runs the required models locally. The extension also supports agent-style coding workflows, where AI tools can perform more complex tasks such as analyzing project context or editing multiple files.
Features
- VS Code extension for AI-assisted coding and development
- Local model execution using the llama.cpp inference runtime
- Inline code completion and AI-powered editing features
- Integrated chat interface for asking questions within the IDE
- Agent-style coding workflows with project context awareness
- Optional support for external model endpoints and APIs