This project provides a suite of command-line tools for interacting with AI services directly from the terminal. It targets users who prefer a CLI environment for AI tasks, offering functionalities like chatting with models, asking questions, managing context, text completion, audio transcription, translation, and text-to-speech.

How It Works

The shell acts as an interface to AI models, currently relying on connections to the OpenAI API. Future iterations aim to integrate with self-hosted services developed in the susi_api project. The core interaction model involves commands like run for interactive chat, ask for direct queries, and others for specific AI tasks, supporting both interactive and batch (stdin/stdout) usage.

Quick Start & Requirements

• Primary install / run command: ./susi_shell.sh
• Non-default prerequisites and dependencies: Requires a working connection to the OpenAI API. The say command is macOS-specific by default.
• Links: susi_api project

Highlighted Details

• CLI-native interface for AI model interaction.
• Supports interactive and batch processing modes.
• Planned integration with self-hosted AI services.
• Includes commands for chat, Q&A, context management, transcription, translation, and TTS.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels are provided in the README.

Licensing & Compatibility

The README does not specify a license.

Limitations & Caveats

Current functionality heavily relies on the OpenAI API. The say command has platform-specific limitations (macOS default). The project is described as having commands "all to be implemented," indicating a work-in-progress status.