llama.vscode review

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

For developers who prefer to keep coding inside VS Code, llama.vscode brings inline completions, AI chat, selected-code editing, and agentic coding into one extension. It is free and open source, with support for Windows, macOS, and Linux. Its emphasis on local models makes it a fit for people working with llama.cpp or self-hosted endpoints, while external model endpoints give users another way to connect models.

The model and context controls are central to the extension. Users can select models for completion, chat, embeddings, and tools, and configure how much code around the cursor or from open and edited files informs a suggestion. Inline suggestions can be accepted by word, line, or all at once. For broader codebase context, optional project-file indexing uses RAG; indexing can be disabled when the extension is used only for completion. Hugging Face model search and downloads are available within the extension, and integrations include OpenRouter and VS Code MCP servers.

The agent interface can use internal tools as well as MCP server tools installed in VS Code, making this more than an autocomplete-only extension. The extension itself is free, though external model providers may charge separately. Support is through documentation and community, and the product is limited to VS Code rather than spanning multiple editor platforms. Choose llama.vscode if local model execution, configurable context, and agent tools matter in your VS Code workflow. Consider another option if you need a different editor or want model usage and costs bundled into a paid plan.

llama.vscode pros and cons

• Where it wins
  • Runs models locally through llama.cpp or connects to external endpoints
  • Combines inline suggestions, chat, selected-code editing, and agent tools
  • Optional project indexing and in-extension Hugging Face model search
• Where it doesn't
  • Limited to Visual Studio Code
  • External model providers may charge separately
  • Support channels are documentation and community

llama.vscode fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. How we rank.

Last updated 21 Oct 2026 · How we research and update