multiai

multiai is a Python library and command-line tool designed to interact with text-based generative AI models from the following providers:

AI Provider	Web Service	Models Available
OpenAI	ChatGPT	GPT Models
Anthropic	Claude	Claude Models
Google	Gemini	Gemini Models
Perplexity	Perplexity	Perplexity Models
Mistral	Mistral	Mistral Models
DeepSeek	DeepSeek	DeepSeek Models
xAI	xAI	xAI Models
Local LLM	Ollama	Ollama Models

Key Features

Interactive Chat: Communicate with AI directly from your terminal.
Multi-Line Input: Supports multi-line prompts for complex queries.
Pager for Long Responses: View lengthy responses conveniently using a pager.
Continuation Handling: Automatically handle and request continuations if responses are cut off.
Automatic Chat Logging: Automatically save your chat history for future reference.
File Attachments: Attach files as additional context.

Usage

Install multiai, then configure your API keys for your chosen AI providers as environment variables or in a user-setting file. Once that's done, you can start interacting with the AI.

To send a simple query:

ai hi

You should see a response like:

gpt-4o-mini>
Hello! How can I assist you today?

For an interactive session, enter interactive mode:

ai

In this mode, you can continue the conversation:

user> hi
gpt-4o-mini>
Hello! How can I assist you today?
user> how are you
gpt-4o-mini>
I'm just a program, so I don't have feelings, but I'm here and ready to help you! How about you? How are you doing?
user>

To see a list of all command-line options, use:

ai -h

For more detailed documentation, please refer to the manual.

Using `multiai` as a Python Library

multiai can also be used as a Python library. Here’s a simple example:

import multiai

# Initialize the client
client = multiai.Prompt()
client.set_model('openai', 'gpt-4o')  # Set model
client.temperature = 0.5  # Set temperature

# Send a prompt and get a response
answer = client.ask('hi')
print(answer)

# Continue the conversation with context
answer = client.ask('how are you')
print(answer)

# Clear the conversation context
client.clear()

The manual includes the following sample codes:

A script that translates a text file into English.
A local chat app that allows you to easily select from various AI models provided by different providers and engage in conversations with them.

Metadata

Release files for multiai 1.6.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for multiai 1.6.2
File	Size	Uploaded
multiai-1.6.2.tar.gz	23.9 kB	Sep 6, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for multiai 1.6.2
File	Interpreter	ABI	Platform	Reset
multiai-1.6.2-py3-none-any.whl 21.1 kB Sep 6, 2026	Python 3	none	any	Details

Total release size: 45.0 kB

Release files / multiai-1.6.2.tar.gz

Download URL	multiai-1.6.2.tar.gz
Size	23.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`2b9c4ad904d1327c787fa5bf9b50338fde61dc61da6a907a39ad2c355e002e75`
BLAKE2b-256 checksum How to use checksums	`efa2daa10ed885d702ebf9c7c5d61208349017490f7f7c0197cd779ef22425ec`
Upload date	Sep 6, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.14.6`

Release files / multiai-1.6.2-py3-none-any.whl

Download URL	multiai-1.6.2-py3-none-any.whl
Size	21.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`87f176242ef366fd611d5e8397475e668ffecb3ab2512c2afae336f052797365`
BLAKE2b-256 checksum How to use checksums	`09adbd7ac104aecbf1a43d7de683bf79724954ee451a10511ba81e9c2574c736`
Upload date	Sep 6, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.14.6`