Back to directory

llama.vscode

A VS Code extension that adds local, LLM-assisted code completion, chat and an agentic coding assistant backed by llama.cpp.

llama.vscode

llama.vscode is a Visual Studio Code extension that adds local, LLM-assisted text completion, chat and an agentic coding assistant backed by llama.cpp. It suggests completions as you type, offers separate shortcuts to accept a whole suggestion, only its first line, or just the next word, and can draw on a ring of context from open and edited files and recently yanked text so large contexts still work on modest hardware.

The extension can install and upgrade llama.cpp itself on macOS, Windows and Linux, and lets users add, remove and switch between local and external models for completion, chat, embeddings and tool use, including MCP servers already installed in VS Code. Predefined model and environment presets bundle common combinations for different workflows.

Other features include a built-in Llama Agent for agentic coding, reachable from a phone through a Telegram bot, and the ability to search for and download models from Hugging Face inside the editor.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.