Skip to main content
Workshop Desktop is a native application for macOS, Windows, and Linux. It gives you full access to your local file system, any programming language or framework, local AI models, MCP servers, and integrated terminals.

​
Step-by-Step

1

Download and install

Go to workshop.ai and download the installer for your platform:
  • macOS — .dmg installer (Apple Silicon and Intel)
  • Windows — .exe installer
  • Linux — .AppImage or .deb package
Run the installer and launch Workshop Desktop. Sign in with your account or create one.
2

Create a new project

Click New Project and give it a name. Unlike Workshop Cloud, Desktop starts with a blank project by default — no template restrictions. You can build with any language and any framework.Workshop creates a project directory on your local file system. You can open this folder in any editor or file manager at any time.
Have an existing codebase? You can Import from GitHub directly using the GitHub import button, or paste any Git URL to clone a repository into a new project.
3

Describe what you want to build

Workshop starts in Plan Mode. Describe your project in plain language:
I want to build a React app with a Node.js backend that manages
a task list with due dates, priorities, and categories.
Workshop will ask about scope, design decisions, and technical preferences. Once the plan looks good, follow the prompt to switch to Build Mode.
You don’t need to specify a tech stack upfront. Workshop will recommend one based on your requirements, but you can always override its suggestions.
4

Build and iterate

In Build Mode, Workshop writes code, installs packages, creates files, and runs your application — all on your local machine. Watch the progress in the chat and interact with the result.Ask for changes naturally:
Add a dark mode toggle to the settings page.
The task list should sort by due date by default.
Workshop has full access to your project files and terminal. It can run dev servers, install dependencies, execute scripts, and debug issues directly.
5

Deploy anywhere

Since your project lives on your local file system, you have complete flexibility for deployment:
  • Push to GitHub and deploy with Vercel, Netlify, Railway, or any CI/CD pipeline
  • Build Docker containers and deploy to any cloud
  • Use platform CLIs (AWS, GCP, Azure, Fly.io) directly
  • Run locally for personal tools and internal use
You can also ask Workshop to help with deployment:
Help me deploy this to Vercel. Set up the configuration and walk me through it.

​
Desktop-Only Features

Local AI Models

Connect to locally-running LLMs (llama.cpp, Ollama, or any Anthropic Messages API-compatible server) for zero API cost development. Configure in Settings → Agent → Local Model Setup.

MCP Servers

Extend Workshop with Model Context Protocol servers. Browse the built-in directory, add custom servers, or install via deep links. Access tools, data, and capabilities from any MCP-compatible service.

GitHub Integration

Import repositories directly from GitHub. Link existing projects to GitHub repos for push/pull sync. Workshop handles authentication through the GitHub App.

Terminal Access

Workshop runs commands in integrated terminals on your local machine. You see exactly what it’s doing and can interact with the terminal yourself at any time.

​
Configuring the Agent

Access agent settings through the wrench icon in the interface:
  • Code Execution — Choose manual approval or automatic execution for each code block
  • Max Turns — Limit how many actions Workshop takes before checking with you (1–25)
  • Thinking Mode — Enable extended reasoning with adjustable depth (Light, Balanced, Deep, Max)
  • Custom Instructions — Give Workshop persistent context about your preferences, coding style, or project constraints

​
Tips for Better Results

Plan Mode helps Workshop understand your full vision before writing code. This leads to better architecture decisions and fewer rewrites. Switch to Build Mode once the plan captures what you want.
Workshop can read files you drag into the conversation — PDFs, images, data files, design mockups. Use this to give it reference material, existing specs, or visual inspiration.
Start with core functionality, verify it works, then add features:
  1. “Set up the project with React and Express”
  2. “Create the task list with add/edit/delete”
  3. “Add categories and filtering”
  4. “Add the dark mode toggle”
Ask Workshop to initialize Git and commit at logical milestones. This gives you safety nets to roll back if needed:
Initialize git for this project and commit our current progress.

​
Next Steps