#local llm
LM Studio Code
cgaspard
Agentic coding panel for your local LM Studio models. A Claude Code / Codex–style chat experience powered by the open-source OpenCode agent, running entirely against your local models.
LM Studio (BYOM)
cgaspard
Bring-your-own-model provider that exposes local LM Studio models to GitHub Copilot Chat and other VS Code language model consumers.
NIM Code
vijayjanakiraman
AI coding assistant and autonomous agent for VS Code. Free Auto mode — no API key needed. Multi-provider: NVIDIA NIM, OpenAI, Anthropic Claude, Google Gemini, Groq, Sarvam AI, or any OpenAI-compatible endpoint, including fully offline local models via Ollama, LM Studio, llama.cpp and vLLM. Agent mod
Ollama Code
cgaspard
Agentic coding panel for your local Ollama models. A Claude Code / Codex–style chat experience powered by the open-source OpenCode agent, running entirely against your local models.
Selfcoder - Ollama, LM Studio & vLLM Local AI Coding Agent
coderoom
Local coding agent powered by Ollama, LM Studio or vLLM — Qwen, DeepSeek, Gemma, Llama, Kimi, GLM and more. A self-hosted Copilot alternative.
Abbenay Provider
redhat
Use any LLM with any VS Code extension - OpenAI, Anthropic, Google, Ollama & more. The open alternative to Copilot.
vLLM-Copilot
System-Sciences
You use vLLM and want its AI models in Copilot? This is what you need. The full Copilot integration for vLLM models — *all* features supported. Optimized for robust hosting of local AI with fully configurable model modes, supporting every vLLM parameter with full UI configuration. Supports multiple
AI.duino
NikolaiRadke
AI-powered assistance for Arduino for API-, local- and process providers.
Claude Provider Switcher
AlekseiLobanov
Switch the Claude Code extension between API providers/gateways (LiteLLM, DeepSeek, MiniMax, local models, native subscription) with a sidebar UI, menu, hotkeys, and a status bar indicator.
Blink - Local AI Code Completions
Lojell
Lightning-fast inline AI completions (ghost text), local-first and BYOK: GGUF models in-process via llama.cpp, or any OpenAI-compatible endpoint.
Modelfile Syntax for Ollama
ahnafnafee
Syntax highlighting, an 18-rule linter, hover docs, autocomplete, and snippets for Ollama Modelfiles. Works in VSCode, VSCodium, Cursor, Windsurf, and vscode.dev.
DeskAI — Local AI Coding Assistant
AbhishekMishra9454
100% offline AI coding assistant. Full project generation, agentic file editing & terminal control powered by local LLMs (Qwen3, DeepSeek-Coder) running entirely on your machine. Works on Windows, macOS and Linux. No API keys.