---
title: "Use a local and open source code assistant"
description: "Closed or cloud-based coding assistants can expose work to external services, so the article presents a local, open-source alternative built around OpenCode. OpenCode is an AI coding agent—not an LLM—that runs as a terminal interface, desktop application, or IDE extension and connects to models through the Model Context Protocol (MCP). The setup installs OpenCode, selects a local model runtime such as Ollama for AMD/NVIDIA GPUs or OpenVINO Model Server with INT4 Qwen3-8B for Intel integrated graphics, then configures opencode.jsonc and an editor plug-in. Examples cover Qwen3:14b with Ollama, Podman-based OpenVINO serving, and NetBeans integration; the resulting assistant can answer queries and edit files after permission is granted, although local inference may be slow and generated advice can be unreliable."
---

# Use a local and open source code assistant

[Red Hat](https://yomu.fyi/company/red-hat) · Seth Kenlon · Sep 9, 2026

**Type:** Tutorial

## Summary

Closed or cloud-based coding assistants can expose work to external services, so the article presents a local, open-source alternative built around OpenCode. OpenCode is an AI coding agent—not an LLM—that runs as a terminal interface, desktop application, or IDE extension and connects to models through the Model Context Protocol (MCP). The setup installs OpenCode, selects a local model runtime such as Ollama for AMD/NVIDIA GPUs or OpenVINO Model Server with INT4 Qwen3-8B for Intel integrated graphics, then configures opencode.jsonc and an editor plug-in. Examples cover Qwen3:14b with Ollama, Podman-based OpenVINO serving, and NetBeans integration; the resulting assistant can answer queries and edit files after permission is granted, although local inference may be slow and generated advice can be unreliable.

## Context

Many coding assistants are closed source or send development data to cloud services for processing. The stated goal is to use an open coding assistant and an open source IDE while keeping processing local, including when working without an internet connection.

## Approach / What changed

Install OpenCode locally, provide it with a separately installed LLM runtime, configure the model endpoint in ~/.config/opencode/opencode.jsonc, and connect it to an editor through a coding assistant plug-in. The examples use Ollama for AMD or NVIDIA GPUs and OpenVINO Model Server in Podman for Intel integrated graphics.

## Takeaways

- OpenCode is an interface and coding agent rather than an LLM, allowing users to select a model that may be local, organization-private, or subscription-based.
- Ollama is presented for AMD and NVIDIA GPUs, while OpenVINO Model Server with INT4-compressed Qwen3-8B targets Intel integrated graphics.
- The assistant can suggest code and edit files after permission is granted, but local inference on integrated graphics can be slow and generated responses can be unfounded.

**Tags:** [MCP](https://yomu.fyi/topic/mcp), [Ollama](https://yomu.fyi/topic/ollama), [Open Source](https://yomu.fyi/topic/open-source), [OpenVINO](https://yomu.fyi/topic/openvino)

- Source: [Red Hat](https://developers.redhat.com/articles/2026/09/09/use-local-and-open-source-code-assistant)
- Source URL: https://developers.redhat.com/articles/2026/09/09/use-local-and-open-source-code-assistant
- Ingested by Yomu: 2026-09-09T16:05:31.562Z

[Read original post](https://developers.redhat.com/articles/2026/09/09/use-local-and-open-source-code-assistant)