Cheshire Cat AI is an open-source framework for building custom AI agents as microservices. It targets developers seeking to integrate conversational AI into applications via APIs, offering features like WebSocket chat, REST API management, built-in RAG with Qdrant, and extensibility through plugins. The project aims to democratize AI by providing a flexible and user-friendly platform.

How It Works

The core architecture is API-first, supporting both WebSocket for real-time chat and a REST API for agent management. It integrates Langchain for broad LLM compatibility and includes built-in RAG capabilities powered by Qdrant. Extensibility is a key design principle, allowing custom logic through event callbacks, function calling (tools), and conversational forms.

Quick Start & Requirements

• Install/run via Docker: docker run --rm -it -p 1865:80 ghcr.io/cheshire-cat-ai/core:latest
• Prerequisites: Docker.
• Access: Chat at localhost:1865/admin, API docs at localhost:1865/docs.
• Documentation: Official Documentation

Highlighted Details

• API-first design with WebSocket and REST interfaces.
• Built-in RAG with Qdrant integration.
• Extensible via plugins, event hooks, function calling, and conversational forms.
• Supports any language model via Langchain.
• 100% Dockerized for easy deployment.

Maintenance & Community

• Active Discord community.
• Roadmap and contribution guidelines available.

Licensing & Compatibility

• License: GPL3.
• Trademark: Cheshire Cat AI name and logo are property of Piero Savastano.

Limitations & Caveats

The project is licensed under GPL3, which may impose copyleft restrictions on derivative works, potentially impacting commercial or closed-source integrations.