CLI

Run 150+ AI apps via the inference.sh CLI with JSON inputs.

577|62|Updated May 15, 2026
One-click install
npx skills add https://github.com/agentic-in/elephant-agent --skill cli-agentic-in
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: CLI
Source: https://github.com/agentic-in/elephant-agent/tree/main/packages/skills/builtin_packages/devops/cli
Command: npx skills add https://github.com/agentic-in/elephant-agent --skill cli-agentic-in

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Managing dozens of AI apps across providers is slow and error-prone; developers duplicate credential handling, app-id lookups, and context switching.

Core Features & Use Cases

  • Unified CLI access to 150+ AI apps via inference.sh (infsh) for cloud-based execution
  • No GPU required and consistent, script-driven workflows for images, video, text, search, and automation
  • Simple, repeatable start-to-finish tasks: discover, run, monitor, and route outputs with JSON
  • Use Case: a developer can launch a batch of image generations or videos without juggling multiple provider consoles

Quick Start

Install the infsh CLI and start running apps with a command like infsh app run <app-id> --input '<json>'.

Frequently Asked Questions about CLI

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple AI apps from different providers using a single command-line interface?

The inference.sh CLI unifies access to over 150 AI apps for image generation, video creation, and text processing. It eliminates the need to manage individual provider APIs by using script-driven workflows with JSON inputs.

What do I need to authenticate and execute AI apps via the command line?

Executing AI apps via the command line requires an installed infsh CLI and user authentication. You provide app parameters as JSON-formatted inputs, enabling the CLI to handle credential management and route outputs automatically without managing multiple provider consoles.

Do I need a local GPU to generate images and videos through a CLI?

No local GPU is required to generate images and videos through the inference.sh CLI. The CLI executes cloud-based app workflows, allowing you to launch batch generations and automation tasks on standard local machines without dedicated hardware.

How does a unified CLI simplify automation workflows for AI apps?

A unified CLI simplifies AI automation workflows by providing consistent, script-driven execution for discovering, running, and monitoring apps. This removes duplicated credential handling and context switching, enabling repeatable start-to-finish tasks using a single command structure.

Can I batch generate AI images without juggling multiple provider consoles?

You can batch generate AI images without juggling multiple provider consoles by using the inference.sh CLI. It routes JSON inputs to cloud-based apps, enabling developers to discover, run, and monitor batch image or video generations through a single command interface.