Installation

Installation Overview

Choose an IDE extension and complete first-run setup for Refact.

Install Refact in your IDE, open the Refact UI, configure at least one provider or local runtime, and choose default models before using chat, agent workflows, or code completion.

VS Code

Install from the Visual Studio Marketplace

Read the VS Code guide

JetBrains IDEs

Install from JetBrains Marketplace

Read the JetBrains guide

First-Run Checklist

1. Open the Refact sidebar or tool window.
2. Confirm the local engine starts in the background.
3. Add a hosted BYOK provider, OAuth-capable provider, local runtime, or custom endpoint in Provider Setup.
4. Enable the models you want Refact to use.
5. Select default models for chat, reasoning, agent work, and code completion.
6. Start a chat, switch to an agent mode, or accept inline completion suggestions.

What Gets Installed

The IDE extension includes the Refact UI and starts the local refact-lsp engine. The engine handles chat sessions, model-provider calls, local context, tool execution, code completion, trajectories, tasks, and knowledge.

What You Still Need

Bring at least one model source:

• A provider key or OAuth flow for hosted providers.
• A running local runtime such as Ollama, LM Studio, or vLLM.
• A custom OpenAI-compatible endpoint with model details.

A separate hosted Refact backend is not part of the setup path.