Build inference.sh apps with AI coding assistants like Claude Code, Cursor, or Windsurf.

Setup

1. Install CLI

1curl -fsSL https://cli.inference.sh | sh2infsh login

2. Create App

1infsh app init my-app2cd my-app

This creates your app with all the files needed, including skills that teach your coding agent how to build inference.sh apps.

Skills Included

When you run infsh app init, the CLI creates a skills/ directory containing guidance for AI coding assistants:

How It Works

1. You describe what you want — Tell your coding agent what app to build
2. Agent reads skills — The agent uses the skills to understand inference.sh patterns
3. Agent writes code — Creates inference.py, updates inf.yml, adds dependencies
4. Test locally — Run infsh app run to verify
5. Deploy — Run infsh app deploy to publish

Example Prompts

1Create an image resizing app that takes an image and dimensions, 2and returns the resized image.

1Build an LLM app that calls OpenAI's API. 2It should track token usage for billing.

1Make a YouTube audio downloader that extracts audio from videos 2and returns MP3 files.

Supported Agents

The skills work with any AI coding assistant that supports project-level context:

• Claude Code — Reads skills from .claude/skills/ or project files
• Cursor — Uses project context
• Windsurf — Uses project context
• GitHub Copilot — Uses project context

Next

→ CLI Setup — Manual CLI installation

→ Creating an App — Manual app creation