llm-cli

Access OpenAI, Anthropic, Google Gemini, and Ollama through a unified command-line interface.

345|52|Updated Oct 25, 2025
One-click install
npx skills add https://github.com/glebis/claude-skills --skill llm-cli-glebis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-cli
Source: https://github.com/glebis/claude-skills/tree/main/llm-cli
Command: npx skills add https://github.com/glebis/claude-skills --skill llm-cli-glebis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The LLM CLI Skill unifies access to OpenAI, Anthropic, Google Gemini, Ollama, and other models through a single command-line interface, simplifying cross-provider experimentation and deployment.

Core Features & Use Cases

  • Unified provider support with intelligent model selection for both interactive and non-interactive workflows.
  • Persistent configuration across sessions, including last-used model and available providers.
  • Open integration points including slash-command support and Claude Code integration for CLI workflows.

Quick Start

Install the llm CLI, run /llm --setup to detect providers, and start processing text with your chosen model.

Frequently Asked Questions about llm-cli

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

FAQPage Schema
How do I use a single CLI to interact with multiple LLM providers like OpenAI and Anthropic?

You can interact with multiple LLM providers by using a unified command-line interface that supports OpenAI, Anthropic, Google Gemini, and Ollama. It handles provider detection automatically, allowing you to seamlessly query different models from one terminal session.

Can I run LLM queries non-interactively from the command line?

Yes, you can run LLM queries non-interactively from the command line. The interface supports both non-interactive and interactive workflows, allowing you to pipe multi-format input directly into your chosen model for automated processing.

Does the multi-provider CLI remember my last-used model across sessions?

The multi-provider CLI remembers your last-used model across sessions through persistent configuration. It stores available providers and your model selection locally, ensuring your environment remains configured without needing repeated setup.

How do I setup and detect available LLM providers in a command-line environment?

To setup and detect available LLM providers, you run the setup command to automatically identify installed models. This initialization process configures your environment and prepares intelligent model selection for immediate text processing.

What is the best way to switch between local Ollama models and cloud providers in a terminal?

The best way to switch between local Ollama models and cloud providers is using a unified CLI with model aliasing. It allows you to easily select and switch between local and remote models within an interactive session.

Can I integrate slash commands into my LLM command-line workflows?

Yes, you can integrate slash commands into your LLM command-line workflows. The interface offers open integration points for slash-command support and Claude Code integration, streamlining your interactive text processing.