Remote script. ENZO boots the server.js from your prompts, so review generated code before running it outside the preview.
Who it is forA developer who wants a quick working prototype from a prompt and a live preview to check it.
The problemSetting up a new project scaffold and running it by hand takes time before any idea can be tested.
The outcomeA generated project saved in ENZO, running in the preview panel, with ENZO reporting if it is broken.
What you need first
- Docker with Docker Compose, or a free Google account for the Colab route
- At least one provider API key, such as OpenRouter, Google AI Studio or NVIDIA NIM
- A browser to open the app and paste keys into the Vault
Steps
- Start ENZO with
docker compose up -dand open http://localhost:5001 after pasting a provider key. - Open Code-gen and describe the coding project you want.
- Wait for ENZO to write the project, boot it and show it in the live preview.
- Click files in the file strip to inspect the generated code and fix anything ENZO reports as broken.
Prompt for your agent
Using the repo theguysudo/ENZO at http://localhost:5001, use Code-gen to build this project: <project-description>. Expected output: a generated project running in the live preview. Verify the preview loads and that the file strip shows the project files before you accept the result.
Caveat. The README says generated backends run under Node's runtime permission model, and that a failed sandboxed boot retries once unsandboxed, so a boot can run with fewer limits than you expect.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for theguysudo/ENZO and "Generate a coding project and preview it live"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer