QodeAssist — AI coding assistant for Qt Creator

⚠️ Status: winding down

QodeAssist is moving to maintenance-only. No new features, no requests, and at some point I'll likely stop entirely.

Issues and pull requests are closed, and the Discord server is gone. There's no support of any kind, by email or otherwise.

If you need to reach me for something, I'm at palm1r-github-dev@pm.me — no promise of a reply.

The code stays available under its GPL license — fork it freely.

QodeAssist brings a full AI coding workflow to Qt Creator for C++ and QML — smart code completion, multi-panel chat, inline quick refactoring, and project-aware tool calling. It works with local runtimes (Ollama, llama.cpp, LM Studio) and cloud providers (Claude, OpenAI, Google AI, Mistral, Qwen, DeepSeek), can run as an MCP server so other clients reuse its project context, and can also act as an MCP client to consume tools from external MCP servers.

Table of Contents

1. Overview
2. Install Plugin
3. Configuration
4. Features
5. Context Layers
6. QtCreator Version Compatibility
7. Hotkeys
8. Troubleshooting
9. Development Progress
10. Support the Development
11. How to Build

Overview

QodeAssist enhances Qt Creator with AI-powered coding assistance:

• Code Completion — intelligent, context-aware suggestions (FIM and chat models) for C++ and QML, with multiline support
• Chat Assistant — side panel, bottom panel, or detached window; history with auto-save, token monitoring, extended thinking
• Quick Refactoring — inline AI-assisted edits directly in the editor with a searchable custom-instructions library
• Agent Tools — read, search, create and edit files; build the project; run terminal commands; access linter/compiler issues; manage TODOs
• Agent Skills — reusable folders of specialized instructions loaded on demand; discovered from .qodeassist/skills/ and .claude/skills/, invoked automatically, with /skill, or always-on
• MCP Server — expose QodeAssist's project-aware tools to external MCP clients (Claude Code, VS Code, Claude Desktop via bridge)
• MCP Client Hub — connect QodeAssist to external MCP servers and use their tools in Chat and Quick Refactor (authenticated MCP servers are not supported yet)
• File Context — attach files and images to your messages for richer prompts
• Many Providers — Ollama, llama.cpp, LM Studio (Chat + Responses), Claude, OpenAI (Chat + Responses), Google AI, Mistral, Codestral, OpenRouter, Qwen (OpenAI + Responses), DeepSeek, any OpenAI-compatible endpoint
• Reasoning / Thinking — streamed chain-of-thought is shown for reasoning models across Claude, Google, OpenAI Responses, and any OpenAI-compatible endpoint that returns reasoning_content (DeepSeek, Qwen QwQ/Qwen3-Thinking, LM Studio, OpenRouter, …)
• Customizable — per-project and global agent skills, reusable refactor templates, full prompt-template control

Install plugin to QtCreator

Method 1: Using the Extension Registry (Recommended)

You can install and update QodeAssist directly from within Qt Creator by adding the QodeAssist registry as an external extension repository.

1. Open the Extensions page (Qt Creator → Extensions) and switch to the Browser tab
2. Enable Use External Repository
3. Next to Repository URLs, click Add and paste the registry archive URL matching your Qt Creator version:
   • Latest (up to date to QtCreator release): https://github.com/Palm1r/extension-registry/archive/refs/heads/qodeassist.tar.gz
   • QtC 20: https://github.com/Palm1r/extension-registry/archive/refs/heads/qodeassist-qtc20.tar.gz
   • QtC 19: https://github.com/Palm1r/extension-registry/archive/refs/heads/qodeassist-qtc19.tar.gz
   • QtC 18: https://github.com/Palm1r/extension-registry/archive/refs/heads/qodeassist-qtc18.tar.gz

4. Click Apply — QodeAssist will appear in the extensions list, where you can Install it
5. Updates can be installed from the same screen when a new version is published

Note: This is an external repository not maintained by The Qt Company. By adding it you accept responsibility for managing the associated risks, as stated in the Extensions page.

Method 2: Manual Installation

1. Install Latest Qt Creator
2. Download the QodeAssist plugin for your Qt Creator
   • Remove old version plugin if already was installed
     • on macOS for QtCreator 16: ~/Library/Application Support/QtProject/Qt Creator/plugins/16.0.0/petrmironychev.qodeassist
     • on windows for QtCreator 16: C:\Users<user>\AppData\Local\QtProject\qtcreator\plugins\16.0.0\petrmironychev.qodeassist\lib\qtcreator\plugins
3. Launch Qt Creator and install the plugin:
   • Go to:
     • MacOS: Qt Creator -> About Plugins...
     • Windows\Linux: Help -> About Plugins...
   • Click on "Install Plugin..."
   • Select the downloaded QodeAssist plugin archive file

Configuration

Quick Setup (Recommended for Beginners)

The Quick Setup feature provides one-click configuration for popular cloud AI models. Get started in 3 easy steps:

1. Open QodeAssist Settings
2. Select a Preset - Choose from the Quick Setup dropdown:
   • Anthropic Claude (Sonnet 4.5, Haiku 4.5, Opus 4.5)
   • OpenAI (gpt-5.2-codex)
   • Mistral AI (Codestral 2501)
   • Google AI (Gemini 2.5 Flash)
   • Qwen (Qwen3.6 Plus, Qwen3.7 Max)
   • DeepSeek (DeepSeek V4 Flash, DeepSeek V4 Pro)
3. Configure API Key - Click "Configure API Key" button and enter your API key in Provider Settings

All settings (provider, model, template, URL) are configured automatically. Just add your API key and you're ready to go!

Manual Provider Configuration

For advanced users or local models, choose your preferred provider and follow the detailed configuration guide:

Local providers:

• Ollama — native Ollama API
• Ollama (OpenAI-compatible) — Ollama's /v1 endpoint for tool-calling models
• llama.cpp — local llama-server
• LM Studio — OpenAI-compatible Chat API
• LM Studio (Responses API) — newer models that require the Responses endpoint

Cloud providers:

• Anthropic Claude — manual setup guide
• OpenAI — Chat Completions and Responses API
• Mistral AI / Codestral
• Google AI — Gemini
• Qwen (Alibaba) — DashScope OpenAI-compatible Chat and Responses endpoints
• DeepSeek — deepseek-chat and deepseek-reasoner (reasonin