In prototyping AI applications I have a strong hunch that one can go quite far by starting off with a command line interface (CLI) as the initial front end. No need to fire up a web browser, and deal with JavaScript programming, to have conversations with agents. So I’m on the hunt for some robust, flexible frameworks with a solid community.
This may become the seed of a collection turns into its own page. Herewith, in no particular order
clai
clai from Pydantic AI
Pydantic AI comes with a CLI, clai (pronounced “clay”) which you can use to interact with various LLMs from the command line. It provides a convenient way to chat with language models and quickly get answers right in the terminal.
We originally developed this CLI for our own use, but found ourselves using it so frequently that we decided to share it as part of the Pydantic AI package.
We plan to continue adding new features, such as interaction with MCP servers, access to tools, and more.
I like Pydantic.AI’s design sensibility so I’m favorable to solutions that build on top of their framework.
chatlas
chatlas is from the fine folks at Posit. The tagline:
Your friendly guide to building LLM chat apps in Python with less effort and more clarity.
Based upon documentation looks like a well designed framework that’s independent of the major Python AI client frameworks.
AIChat
AIChat is more shrink wrapped but if extensible enough could provide a polished foundation.
AIChat is an all-in-one LLM CLI tool featuring Shell Assistant, CMD & REPL Mode, RAG, AI Tools & Agents, and More.
gptme
gptme seems similar in spirit to AIChat but leans a bit more extensible
gptme is a personal AI assistant and agent platform that runs in your terminal and browser, equipped with powerful tools to execute code, edit files, browse the web, and more - acting as an intelligent copilot for your computer.
…
gptme is a chat-CLI for LLMs, empowering them with tools to run shell commands, execute code, read and manipulate files, and more.