CLI tool for terminal-based AI chatbots, no API key needed for some providers
Top 17.7% on sourcepulse
tgpt is a versatile command-line interface tool enabling users to interact with various AI chatbots directly from their terminal, eliminating the need for API keys for many providers. It supports a wide range of text and image generation models from services like Ollama, Groq, Gemini, and OpenAI, catering to developers and power users who prefer terminal-based workflows.
How It Works
tgpt acts as a unified client, abstracting the complexities of different AI provider APIs. It allows users to specify providers, models, and parameters via command-line flags or environment variables. This approach offers flexibility, enabling users to switch between services like Phind (default, developer-focused), Groq (fast inference), or local Ollama models without altering their workflow. Experimental features for shell command generation and execution are also included.
Quick Start & Requirements
curl -sSL https://raw.githubusercontent.com/aandrew-me/tgpt/main/install | bash -s /usr/local/bin
(Linux/macOS), scoop install https://raw.githubusercontent.com/aandrew-me/tgpt/main/tgpt.json
(Windows/Scoop), choco install tgpt
(Windows/Chocolatey), or go install github.com/aandrew-me/tgpt/v2@latest
.Highlighted Details
-c
) and shell command generation/execution (-s
).Maintenance & Community
The project is actively maintained by andrew-me. Community channels are not explicitly mentioned in the README.
Licensing & Compatibility
The project appears to be licensed under the MIT License, allowing for broad commercial and closed-source use.
Limitations & Caveats
Shell command execution is marked as experimental and may require confirmation. Not all provider-specific options are supported across all services, and unsupported options are ignored.
16 hours ago
1 day