Text of docs.docker.com › ai › model-runner › ide-integrations as Styx crawled it on Nov 18, 2026. The page may have changed since. Only its words are kept, without pictures or layout, and only the first part of a long page.

Open the live page

IDE and tool integrations | Docker Docs

Start a new chat Answers are generated based on the documentation. Manuals Get started Guides Reference IDE and tool integrations Table of contents Docker Model Runner can serve as a local backend for popular AI coding assistants and development tools. This guide shows how to configure common tools to use models running in DMR. Prerequisites Before configuring any tool: Enable Docker Model Runner in Docker Desktop or Docker Engine.

Enable TCP host access: Docker Desktop: Enable host-side TCP support in Settings > AI, or run: $ docker desktop enable model-runner --tcp 12434 Docker Engine: TCP is enabled by default on port 12434. Pull a model: $ docker model pull ai/qwen2.5-coder Tip The default context size for many models (such as gpt-oss ) is 4,096 tokens, which is limiting for coding tasks. You can repackage it with a larger context window: $ docker model pull gpt-oss $ docker model package --from ai/gpt-oss --context-size 32000 gpt-oss:32k Alternatively, models like ai/glm-4.7-flash, ai/qwen2.5-coder, and ai/devstral-small-2 come with 128K context by default and work without repackaging.

Cline (VS Code) Cline is an AI coding assistant for VS Code. Configuration Open VS Code and go to the Cline extension settings. Select OpenAI Compatible as the API provider. Configure the following settings: Setting Value Base URL http://localhost:12434/engines/v1 API Key not-needed (or any placeholder value) Model ID ai/qwen2.5-coder (or your preferred model) Important The base URL must include /engines/v1 at the end.

Do not include a trailing slash. Troubleshooting Cline If Cline fails to connect: Verify DMR is running: $ docker model status Test the endpoint directly: $ curl http://localhost:12434/engines/v1/models Check that CORS is configured if running a web-based version: In Docker Desktop Settings > AI, add your origin to CORS Allowed Origins Continue (VS Code / JetBrains) Continue is an open-source AI code assistant that works with VS Code and JetBrains IDEs.

Configuration Edit your Continue configuration file ( ~/.continue/config.json ): { "models" : [ { "title" : "Docker Model Runner" , "provider" : "openai" , "model" : "ai/qwen2.5-coder" , "apiBase" : "http://localhost:12434/engines/v1" , "apiKey" : "not-needed" } ] } Using Ollama provider Continue also supports the Ollama provider, which works with DMR: { "models" : [ { "title" : "Docker Model Runner (Ollama)" , "provider" : "ollama" , "model" : "ai/qwen2.5-coder" , "apiBase" : "http://localhost:12434" } ] } Cursor Cursor is an AI-powered code editor.

Configuration Open Cursor Settings (Cmd/Ctrl + ,). Navigate to Models > OpenAI API Key . Configure: Setting Value OpenAI API Key not-needed Override OpenAI Base URL http://localhost:12434/engines/v1 In the model drop-down, enter your model name: ai/qwen2.5-coder Note Some Cursor features may require models with specific capabilities (e.g., function calling). Use capable models like ai/qwen2.5-coder or ai/llama3.2 for best results.

Zed Zed is a high-performance code editor with AI features. Configuration Edit your Zed settings ( ~/.config/zed/settings.json ): { "language_models" : { "openai" : { "api_url" : "http://localhost:12434/engines/v1" , "available_models" : [ { "name" : "ai/qwen2.5-coder" , "display_name" : "Qwen 2.5 Coder (DMR)" , "max_tokens" : 8192 } ] } } } Open WebUI Open WebUI provides a ChatGPT-like interface for local models. See Open WebUI integration for detailed setup instructions.

Aider Aider is an AI pair programming tool for the terminal. Configuration Set environment variables or use command-line flags: export OPENAI_API_BASE = http://localhost:12434/engines/v1 export OPENAI_API_KEY = not-needed aider --model openai/ai/qwen2.5-coder Or in a single command: $ aider --openai-api-base http://localhost:12434/engines/v1 \ --openai-api-key not-needed \ --model openai/ai/qwen2.5-coder LangChain Python from langchain_openai import ChatOpenAI llm = ChatOpenAI ( base_url = "http://localhost:12434/engines/v1" , api_key = "not-needed" , model = "ai/qwen2.5-coder" ) response = llm . invoke ( "Write a hello world function in Python" ) print ( response . content ) JavaScript/TypeScript import { ChatOpenAI } from "@langchain/openai" ; const model = new ChatOpenAI ({ configuration : { baseURL : "http://localhost:12434/engines/v1" , }, apiKey : "not-needed" , modelName : "ai/qwen2.5-coder" , }); const response = await model . invoke ( "Write a hello world function" ); console . log ( response . content ); LlamaIndex from llama_index.llms.openai_like import OpenAILike llm = OpenAILike ( api_base = "http://localhost:12434/engines/v1" , api_key = "not-needed" , model = "ai/qwen2.5-coder" ) response = llm . complete ( "Write a hello world function" ) print ( response . text ) OpenCode OpenCode is an open-source coding assistant designed to integrate directly into developer workflows.

It supports multiple model providers and exposes a flexible configuration system that makes it easy to switch between them. See Use OpenCode with Docker Model Runner for a task-focused guide that walks through model setup, configuration, and troubleshooting. Configuration Install OpenCode (see docs ) Reference DMR in your OpenCode configuration, either globally at ~/.config/opencode/opencode.json or project specific with a opencode.json file in the root of your project { "$schema" : "https://opencode.ai/config.json" , "provider" : { "dmr" : { "npm" : "@ai-sdk/openai-compatible" , "name" : "Docker Model Runner" , "options" : { "baseURL" : "http://localhost:12434/v1" }, "models" : { "ai/qwen2.5-coder" : { "name" : "ai/qwen2.5-coder" }, "ai/llama3.2" : { "name" : "ai/llama3.2" } } } } } Select the model you want in OpenCode You can find more details in this Docker Blog post Claude Code Claude Code is Anthropic's command-line tool for agentic coding.

It lives in your terminal, understands your codebase, and executes routine tasks, explains complex code, and handles Git workflows through natural language commands. See Use Claude Code with Docker Model Runner for a task-focused guide that walks through model setup, configuration, and inspecting requests. To run Claude Code in an isolated Docker Sandbox against a local model, see Run Claude Code in a Docker Sandbox with Docker Model Runner .

Configuration Install Claude Code (see docs ) Use the ANTHROPIC_BASE_URL environment variable to point Claude Code at DMR. On Mac or Linux, you can do this, for example if you want to use the gpt-oss:32k model: ANTHROPIC_BASE_URL = http://localhost:12434 claude --model qwen2.5-coder On Windows (PowerShell) you can do it like this: $env:ANTHROPIC_BASE_URL = "http://localhost:12434" claude - -model gpt-oss : 32k Tip To avoid setting the variable each time, add it to your shell profile ( ~/.bashrc , ~/.zshrc , or equivalent): export ANTHROPIC_BASE_URL = http://localhost:12434 You can find more details in this Docker Blog post Note While the other integrations on this page use the OpenAI-compatible API , DMR also exposes a Anthropic-compatible API used here.

Common issues "Connection refused" errors Ensure Docker Model Runner is enabled and running: $ docker model status Verify TCP access is enabled: $ curl http://localhost:12434/engines/v1/models Check if another service is using port 12434. If you run your tool in WSL and want to connect to DMR on the host via localhost , this might not directly work. Configuring WSL to use mirrored networking can solve this. "Model not found" errors Verify the model is pulled: $ docker model list Use the full model name including namespace (e.g., ai/qwen2.5-coder , not just qwen2.5-coder ).

Slow responses or timeouts For first requests, models need to load into memory. Subsequent requests are faster. Consider using a smaller model or adjusting the context size: $ docker model configure --context-size 4096 ai/qwen2.5-coder Check available system resources (RAM, GPU memory). CORS errors (web-based tools) If using browser-based tools, add the origin to CORS allow

The rest of this page is on the live site.