docs: add mxcli playground links to README and docs site

Add "Try it in the Playground" link to the main README header and a
new "Playground (zero install)" section as the first installation
option in the mdbook tutorial docs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: ako

README.md

@@ -4,7 +4,7 @@
 
 A command-line tool that enables AI coding assistants ([Claude Code](https://claude.ai/claude-code), Cursor, Continue.dev, Windsurf, Aider, and others) to read, understand, and modify Mendix application projects.
 
-**[Read the documentation](https://mendixlabs.github.io/mxcli/)**
+**[Read the documentation](https://mendixlabs.github.io/mxcli/)** | **[Try it in the Playground](https://codespaces.new/mendixlabs/mxcli-playground)** -- no install needed, runs in your browser
 
 ## Why mxcli?
 

docs-site/src/tutorial/installation.md

@@ -1,6 +1,28 @@
 # Installation
 
-Pick whichever method suits your situation. If you're planning to use mxcli with an AI coding assistant, skip ahead to the [Dev Container](#dev-container-recommended) section -- it's the smoothest experience.
+Pick whichever method suits your situation. If you just want to try mxcli without installing anything, start with the [Playground](#playground-zero-install). If you're planning to use mxcli on your own project with an AI coding assistant, skip to the [Dev Container](#dev-container-recommended) section.
+
+## Playground (zero install)
+
+The fastest way to try mxcli. The [mxcli Playground](https://github.com/mendixlabs/mxcli-playground) is a GitHub repository with a pre-configured Mendix project, example scripts, and tutorials. Open it in a Codespace and start using mxcli immediately -- nothing to install on your machine.
+
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/mendixlabs/mxcli-playground)
+
+The Codespace comes with mxcli, a JDK, Docker-in-Docker, Claude Code, and a sample Mendix 11.x project ready to explore and modify. It includes:
+
+- **5 example scripts** -- explore, create entities, microflows, pages, and security
+- **Step-by-step tutorials** -- from first steps through linting and testing
+- **AI tool configs** -- pre-configured for Claude Code, Cursor, Windsurf, Continue.dev, and Aider
+
+Once the Codespace is running:
+
+```bash
+./mxcli -p App.mpr -c "SHOW STRUCTURE"          # Explore the project
+./mxcli exec scripts/01-explore.mdl -p App.mpr   # Run an example script
+./mxcli                                           # Start interactive REPL
+```
+
+When you're ready to work on your own Mendix project, use one of the installation methods below.
 
 ## Binary download
 

docs-site/src/tutorial/setup.md

@@ -10,11 +10,12 @@ This chapter walks you through all three.
 
 ## Installation methods
 
-There are three ways to get mxcli running:
+There are four ways to get started with mxcli:
 
-- **Binary download** -- grab a pre-built binary from GitHub Releases. Quickest path if you just want to try it out.
+- **[Playground](installation.md#playground-zero-install)** -- open the [mxcli Playground](https://github.com/mendixlabs/mxcli-playground) in a GitHub Codespace. Zero install, runs in your browser with a sample Mendix project, tutorials, and example scripts. Best way to try mxcli for the first time.
+- **Binary download** -- grab a pre-built binary from GitHub Releases. Quickest path if you want to use mxcli on your own project.
 - **Build from source** -- clone the repo and run `make build`. Useful if you want the latest unreleased changes or plan to contribute.
-- **Dev Container** (recommended) -- run `mxcli init` on your Mendix project, open it in VS Code, and reopen in the container. This gives you mxcli, a JDK, Docker-in-Docker, and Claude Code all pre-configured in a sandboxed environment. This is the recommended approach, especially when pairing with AI coding assistants.
+- **Dev Container** (recommended for your own projects) -- run `mxcli init` on your Mendix project, open it in VS Code, and reopen in the container. This gives you mxcli, a JDK, Docker-in-Docker, and Claude Code all pre-configured in a sandboxed environment. This is the recommended approach, especially when pairing with AI coding assistants.
 
 The next few pages cover each method, then walk you through opening a project and using the REPL.