Kindly Logo

Kindly

Sign inGet started

ATE CLI Documentation

Complete guide to using the FoodforThought command-line interface

Get Started

New to ATE CLI? Start here to install and configure your environment.

Installation Guide

API Keys

Create and manage API keys for CLI authentication.

Manage API Keys

Installation

Install ATE CLI on your system

macOS (Homebrew)

brew install kindly/tap/ate

Linux (pip)

pip install foodforthought-cli

Windows (winget)

winget install Kindly.ATE

Configuration

Set up authentication and API endpoint

1. Get your API Key

Create an API key from your account settings.

2. Set Environment Variables

export ATE_API_URL="https://kindly.fyi/api"
export ATE_API_KEY="your-api-key-here"

💡 Tip: Add these to your ~/.zshrc or ~/.bashrc to make them persistent.

Commands

Available CLI commands and their usage

ate init
Repository

Initialize a new repository in the current directory.

ate init my-robot-skill -d "Description" -v public
ate clone
Repository

Clone an existing repository to your local machine.

ate clone <repository-id> [target-directory]
ate commit
Repository

Create a commit with staged changes.

ate commit -m "Commit message" [files...]
ate push
Repository

Push commits to the remote repository.

ate push [-b branch-name]
ate compatibility
Skills

Check compatibility of a skill between two robot models.

ate compatibility <source-robot> <target-robot> [-r repo-id]
ate adapt
Skills

Generate an adaptation plan for transferring a skill between robots.

ate adapt <source-robot> <target-robot> [-r repo-id] [--analyze-only]
ate test
Testing

Run skills in a simulation environment.

ate test [-e environment] [-r robot] [--local]
ate validate
Safety

Validate safety and compliance of your skill.

ate validate [-c checks] [--strict] [-f files...]

Examples

Common workflows and use cases

Create and Push a New Skill

# Initialize a new repository
ate init pick-and-place -d "Pick and place skill for UR5" -v public
# Add your files...
# Commit and push
ate commit -m "Initial implementation"
ate push

Check Skill Compatibility

# Check if a skill can be transferred from UR5 to Franka Panda
ate compatibility ur5 franka-panda

Adapt a Skill Between Robots

# Generate adaptation plan
ate adapt ur5 franka-panda --analyze-only
# Apply adaptation
ate adapt ur5 franka-panda

Cursor IDE Integration (MCP)

Use FoodforThought directly in Cursor IDE

FoodforThought supports Model Context Protocol (MCP), allowing you to access all CLI capabilities directly from Cursor IDE.

Installation

  1. Visit the FoodforThought homepage to get your MCP configuration
  2. Copy or download the mcp.json configuration
  3. Place it in ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-specific)
  4. Set your ATE_API_KEY environment variable
  5. Restart Cursor to load the MCP server

Available MCP Tools

  • ate_init - Initialize a new repository
  • ate_clone - Clone a repository
  • ate_list_repositories - List available repositories
  • ate_list_robots - List robot profiles
  • ate_compatibility - Check skill compatibility
  • ate_adapt - Generate adaptation plans
Get MCP Configuration

Resources

Additional resources and links

GitHub RepositoryInstallation PageAPI Keys