“Ollama”

MCP Ollama Manager

Internetics

Manage MCP Ollama Python server from VS Code - start, stop, configure and monitor your Ollama MCP server

Ollama View

OswaldoDantas

Manage local Ollama models

Ollama Autocoder

10Nates

A simple to use Ollama autocompletion engine with options exposed and streaming functionality

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.

Syntax highlighting for Ollama Modelfiles

BkCode — AI Code Assistant & Agent (Ollama, local LLM)

bismarkvargas

Asistente de código IA y agente autónomo 100% local con Ollama (Gemma, Qwen, DeepSeek, Llama): chat, autocompletado inline, RAG, mapa de código, dictado por…

RB Ollama Agents

RobinBakshi

Free chat sidebar for VS Code & Antigravity.

Ollama / OpenAI Chat for GitLab Web IDE

wolkie

Chat with Ollama, llama.cpp, or any OpenAI-compatible LLM server from the GitLab Web IDE.

Opilot

selfagency

Run Ollama models with full tool and vision support in GitHub Copilot Chat.

Llamit - AI Commit Messages

Crstian

Generate semantic commit messages using Ollama or any OpenAI-compatible endpoint.

Commit Sage

VizzleTF

Free AI commit messages using Gemini, OpenRouter, Groq, Claude, DeepSeek, xAI, Ollama, or any OpenAI-compatible LLM

UsageDock

anshuman55a

Track your AI usage across Cursor, Claude, Copilot, Codex, Windsurf, Antigravity, and Ollama — usage limits, quotas, and resets in one sidebar.

Abbenay Provider

Red Hat

Use any LLM with any VS Code extension - OpenAI, Anthropic, Google, Ollama & more.

Bandit Stealth

Burtson Labs

Free, local-first coding agent for VS Code — run Ollama models (Gemma, Qwen, Devstral) with tool use, diff approvals, and voice.

Local tab agent

moego0

A local coding agent for VS Code with Ollama-powered repo analysis, ChatGPT browser tab bridging, and reviewable code changes.

OmniPilot

anindra

AI autocomplete, selection-edit and chat for any backend: local Ollama (offline) or OpenAI-compatible APIs — Groq, OpenRouter, DeepSeek, Mistral, Together…

Local Model Provider

Lotte Innovate

VS Code extension to connect to local LLM inference servers (Ollama, llama.cpp, LocalAI, LM Studio, vLLM) via OpenAI API compatible endpoints.

LAITA - Local AI Text Assistant

sylvaticus

Proofread and rewrite text with a language model running locally in Ollama.

Jotflow

enavarre

Chat with local LLMs (LM Studio / OpenAI-compatible or Ollama) inside VS Code, LM Studio style.

Suprabhat AI - Autonomous Coding Copilot

suprabhat-agent

Agentic AI coding assistant with multi-provider LLM support (OpenAI, Claude, Gemini, Groq, DeepSeek, OpenRouter, Ollama), diff reviews, and autonomous…

GPU & VRAM Monitor (Local LLM / MCP / NVIDIA)

hector-horta

Real-time GPU load, VRAM tracking, and active AI models (Ollama, LM Studio, vLLM, MCP) in the status bar.

MORPH-AI Cesium2

ram1234598766

MORPH-AI v6 (Cesium2) chat assistant in VS Code - animated UI, streaming responses, powered by your local Ollama model.

A universal language model chat provider for VS Code — supports OpenAI, Anthropic, Gemini, Ollama and any OAI-compatible endpoint.

SocratiCode

giancarloerra

Codebase context engine for VS Code's native MCP host.