Home

Version 0.0.19 is released (18.08.2025)

What is new

• llama.cpp already supports gpt-oss with tools! If you have 20+ VRAM available, you could select env "Local, full package - min, gpt-oss 20B" and use all AI features, including Llama Agent, only with local models.
• Llama agent UI now shows tables correctly
• Auto select/start last used env if desired - setting Env_start_last_usedEnv_start_last_used
• Agent (system prompt + default tools) selection is now possible ("Agents..." -> "Select/start agent" from llama-vscode menu). All agents details are stored in setting agents_list. Export/import agents is also possible, i.e. they could be shared.

Setup instructions for llama.cpp server

Linux

Mac

Windows

More details about llama.cpp server

Features

Code completion

Edit with AI

Llama agent

Local ai runner

Chat with AI about llama vscode

Chat with AI

Chat with AI with project context

Generate commit message

Statusbar

Menu

Env

Manage completion models

Manage chat models

Manage embeddings models

Manage tools models

Manage envs

Model selection