Skip to main content
Workshop comes in two products that share the same AI agent but differ in where your code runs and what you can do with it.

​
Feature Comparison

FeatureWorkshop CloudWorkshop Desktop
Runs inBrowser (any device)Native app (macOS, Windows, Linux)
Setup requiredNone — sign up and goDownload and install
Tech stackHTML + Python, Streamlit, or BlankAny language, any framework
ComputeManaged sandbox (up to 4 CPU, 16 GB RAM)Your local machine (unlimited)
Session limits2-hour active session, 10-min idle timeoutNo limits
File systemCloud sandbox (persistent across sessions)Full local file system access
Live previewBuilt-in preview paneRun dev servers locally
PublishingOne-click publish with shareable URLDeploy anywhere (Vercel, AWS, Docker, etc.)
Local AI modelsNot availableConnect to llama.cpp, Ollama, or any compatible server
MCP serversNot availableBuilt-in directory + custom servers
GitHub integrationLink and sync projectsImport repos, push/pull sync
TerminalCloud terminal in sandboxLocal terminal on your machine
ConnectorsFull connector libraryFull connector library
Plan / Build modesYesYes
AI connectorsAnthropic, OpenAI, GeminiAnthropic, OpenAI, Gemini
CheckpointsYesYes
Context managementYesYes
Custom instructionsYesYes
Thinking modeYesYes

​
Workshop Cloud

Workshop Cloud is designed for speed and simplicity. Everything runs in your browser — no local environment to configure, no dependencies to install, no ports to manage. How it works: Your project runs in a managed cloud sandbox with up to 4 CPU cores and 16 GB RAM. Workshop writes and executes code inside this sandbox, and you see results in a live preview pane. When you’re done, publish with one click to get a shareable URL. Templates available:
  • HTML + Python — Python backend with an HTML/CSS/JS frontend. The default and most flexible option for dashboards, data apps, and interactive tools.
  • Streamlit — Python-native framework for data apps with built-in charts, tables, and UI components.
  • Blank — Empty project with no pre-installed dependencies. Choose your own direction.
Connectors: Connect to PostgreSQL, MySQL, MongoDB, Supabase, Neon, BigQuery, Snowflake, MSSQL, TiDB, TigerGraph, Tableau, Google Sheets, Google Drive, and AWS S3 — plus AI model connectors for Anthropic, OpenAI, and Gemini.
Cloud sessions have a 2-hour active timeout and a 10-minute idle timeout. Your files persist across sessions — when you return, the sandbox restarts with your project intact.

​
Workshop Desktop

Workshop Desktop is a native application that runs on your local machine. There are no sandbox restrictions — you have full access to your file system, any installed tools, and your local network. How it works: Workshop creates a project directory on your machine and works with your files directly. It runs commands in local terminals, installs packages with your system’s package managers, and starts dev servers on your ports. You own everything. Key capabilities beyond Cloud:
  • Any tech stack — React, Vue, Svelte, Next.js, Django, Rails, Flutter, Swift, Rust, Go — if it runs on your machine, Workshop can build with it.
  • Local AI models — Connect to locally-running language models via any Anthropic Messages API-compatible server (llama.cpp, Ollama with adapter). Develop with zero API costs.
  • MCP servers — Extend Workshop with Model Context Protocol servers. Browse the built-in directory of popular servers, add custom stdio or HTTP servers, or install via deep links from tools like Smithery.
  • GitHub import — Import existing repositories directly into Workshop. Link projects to GitHub repos for bidirectional push/pull sync.
  • No session limits — Work as long as you need. No timeouts, no restarts.

​
Which Should I Choose?

  • You want to start building immediately without any setup
  • You’re building dashboards, data apps, or internal tools with Python
  • You want one-click publishing with a shareable URL
  • You’re working from a tablet, Chromebook, or shared computer
  • You don’t need a specific framework or tech stack
  • You want a managed environment so you don’t have to think about infrastructure
Not sure? Start with Workshop Cloud. It’s the fastest path from idea to working app. If you hit a limitation — need a different framework, want local models, or need to deploy somewhere specific — switch to Desktop. Your skills transfer directly since both use the same Plan and Build modes.

​
What They Share

Both products are powered by the same AI agent and share these core capabilities:
  • Plan Mode — Scope requirements, ask clarifying questions, and create structured development plans before any code is written
  • Build Mode — Write, execute, and debug code in real time with a live view of progress
  • AI Connectors — Bring your own API keys for Anthropic (Claude), OpenAI (GPT), and Google (Gemini) to use as the underlying model
  • Checkpoints — Snapshot your project at any point and restore previous states
  • Context Management — Attach files, connectors, and secrets to guide the AI with relevant information
  • Custom Instructions — Persistent instructions that shape how Workshop’s agent approaches your projects
  • Thinking Mode — Extended reasoning mode with four depth levels for complex problems
  • Data Connectors — Connect to databases, data warehouses, cloud storage, and SaaS tools

​
Moving Between Cloud and Desktop

Your Workshop account works across both products. While projects don’t automatically sync between Cloud and Desktop, you can:
  1. Export from Cloud — Push your Cloud project to GitHub, then import it into Desktop
  2. Start in Cloud, continue in Desktop — Prototype quickly in Cloud, then move to Desktop when you need more flexibility
  3. Use both — Keep data apps in Cloud for easy publishing, and use Desktop for full-stack projects