Back to directory

ChatGPT CLI

A multi-provider command-line interface for OpenAI, Azure, Perplexity, LLaMA and other large language models, with streaming, interactive chat, prompt files, image and audio input, MCP tool calls and an experimental agent mode.

ChatGPT CLI

ChatGPT CLI is a command-line client for working with modern LLMs across several providers, including OpenAI, Azure, Perplexity and LLaMA. It supports streaming responses, an interactive chat mode, reusable prompt files, image and audio input and output, and thread-based context management, where each conversation thread keeps its own history and a sliding window trims older messages once a configurable token limit is reached.

An experimental agent mode, combining ReAct and plan-and-execute styles, runs multi-step tasks with workdir safety limits, budgets and a configurable policy, and can call tools exposed by MCP servers. Prebuilt binaries are available for macOS (Apple Silicon and Intel), Linux, FreeBSD and Windows, and it can also be installed with Homebrew.

Configuration supports multiple named profiles, so a user can switch between providers such as Azure, Perplexity, 302.AI and Atlas Cloud with a --target flag.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.