---
id: chatlas
version: "0.21.1"
license: MIT
license_treatment: permissive
maintenance: active
---

# chatlas — A simple and consistent interface for chatting with LLMs

License: permissive · Maintenance: active · Downloads: 131.5K/mo

## What it is and what it does

Chatlas is a Python library that abstracts away the differences between LLM providers (OpenAI, Anthropic, and others) by offering a single, consistent Chat client interface. Instead of learning each provider's API separately, you instantiate a Chat client for your chosen model, set a system prompt, register tools, and call a single chat() method. The library handles credential management, message formatting, and tool calling under the hood.

It's built on top of widely-used dependencies like httpx, pydantic, and openai, and targets developers building multi-turn conversational applications who want to avoid vendor lock-in or easily swap providers. The package is in active development (released 2026-08-12, last commit 2026-08-14) and supports Python 3.10 through 3.14.

Use it for:

- Build a chatbot that can switch between OpenAI and Anthropic models without rewriting client code.
- Register Python functions as tools so the LLM can call them autonomously during conversation.
- Prototype LLM applications quickly without learning each provider's specific API and authentication patterns.
- Manage multi-turn conversations with consistent message history and system prompt handling across providers.
- Deploy chat applications that abstract provider details, making it easier to migrate or A/B test models.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Chatlas provides a unified Python interface for building LLM chat applications across multiple model providers with tool registration and message management.

Yes. Chatlas is actively maintained, has low install friction, carries no known vulnerabilities, and solves a real problem—provider abstraction for LLM chat apps. MIT licensing is permissive. The 11 dependencies are all stable, widely-used packages. Install it if you're building multi-provider LLM chat applications or want to avoid vendor lock-in.

## Install

pip install chatlas
uv add chatlas
poetry add chatlas

## Installing chatlas

Before you install: Low install friction with a pure Python wheel. Active maintenance with a release 2 days old and last commit on 2026-08-14. Depends on 11 runtime packages including httpx, openai, pydantic, and rich—all widely used and stable.

License in practice: MIT license (permissive) means you can use, modify, and distribute chatlas freely in commercial and private projects with minimal restrictions.

Quickstart:

pip install chatlas

from chatlas import ChatOpenAI

chat = ChatOpenAI(
    model="gpt-4-mini",
    system_prompt="You are a helpful assistant."
)

chat.chat("Hello, how are you?")

Requires Python 3.10 or later. You must provide API credentials (e.g., OPENAI_API_KEY environment variable) for the chosen model provider.

Verify before relying:

- Whether all 11 runtime dependencies are strictly required or if some are optional for specific providers.
- Performance characteristics and latency overhead compared to direct provider SDK calls.
- Exact scope of tool registration and function calling support across different providers.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 131.5K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

llm chat interface python, multi-provider language model client, openai anthropic chat wrapper, python llm tool calling, unified llm api abstraction, chat application framework, llm provider abstraction layer, llm-abstraction, multi-provider, tool-calling

[View on SkillFed](https://skillfed.io/packages/chatlas) · [View on PyPI](https://pypi.org/project/chatlas/)