Cheshire Cat AI

Production ready
AI agent framework

Build your AI agent

Imagine you could train your AI with any document
Train with your docs

Upload pdf, txt, markdown,
JSON, web pages.

Interact with the world

Easily connect your agent
to external APIs and apps.

Choose your models

Use commercial or open
LLMs and embedders.

Have a production ready agent to put online and be productive as a service.
Plug & Play

100% dockerized,
with live reload.

A vast plugin ecosystem to extend the skills of your agent, with both community plugins and the possibility to create your own
Easy to Extend

One-click install plugins
from the community registry,
or write your own.

Smart dialogues

Cutting edge conversational skills
with hooks, tools (function calling)
and forms.

Developer experience

services:

  cheshire-cat-core:
    image: ghcr.io/cheshire-cat-ai/core:latest
    container_name: cheshire_cat_core
    ports:
      - 1865:80
    volumes:
      - ./static:/app/cat/static
      - ./plugins:/app/cat/plugins
      - ./data:/app/cat/dataCode language: YAML (yaml)

Docker based

The Cat is a single container, to easily integrate in your architecture alongside:

  • Reverse proxy (Caddy, Nginx)
  • Vector DB (Qdrant)
  • LLM runner (Ollama, Huggingface)
  • Application (Django, WordPress)
Learn more

Admin panel

Manage your installation with the admin panel, availabe at first launch.

  • Chat with your agent with live reload at code changes
  • Install and activate/deactivate plugins
  • Visualize and manage memory contents
  • Configure LLM and embedder
  • Manage your users
Learn more

// Meanwhile, in the browser...

import { CatClient } from 'ccat-api'

const cat = new CatClient({
    baseUrl: 'localhost',
    userId: 'user',
    //... other settings
})

cat.send('Hello kitten!')
Code language: JavaScript (javascript)

Extensive http and websocket API

Our framework is microservice first, the best scenario if you want to add a conversational layer to pre-existing software.

  • Endpoints for LLM, embedder, vector memory, uploads, settings, users
  • Websocket chat with token streaming and notifications
  • Community built clients in most used languages
Learn more

A plugin is just a folder

Focus on your agent, which is already online before you even start coding. Forget the OOP hell you probably experienced with other frameworks.

To create a plugin:

  • Create a folder in `cat/plugins`
  • Create a python file in the folder
  • Add hooks, tools and forms
  • Debug in the admin chat with live reload
Learn more
from cat.mad_hatter.decorators import hook

@hook
def agent_prompt_prefix(prefix, cat):
    prefix = """You are Marvin the socks seller.
You reply with exactly one rhyme.
"""
    return prefixCode language: Python (python)

Hooks

Customize your agent with event callbacks. Things you can do:

  • Change the system prompt
  • Inspect/edit inbound and outbound messages
  • Fully customize the agent
  • Create pipelines for memory and uploads
Learn more

Tools

With tools, you can enable LLM function calling:

  • Manage domotics
  • Call a REST API
  • Query a DB
  • Integrate with a symbolic reasoner
Learn more
from cat.mad_hatter.decorators import tool

@tool
def socks_prices(color, cat):
    """Get socks price. Input is the sock color."""
    prices = {
        "black": 5,
        "white": 10,
        "pink": 50,
    }

    price = prices.get(color, 0)
    return f"{price} bucks, meeeow!"Code language: Python (python)
from pydantic import BaseModel
from cat.experimental.form import form, CatForm

class PizzaOrder(BaseModel):
    pizza_type: str
    phone: int

@form
class PizzaForm(CatForm):
    description = "Pizza Order"
    model_class = PizzaOrder
    start_examples = [ "I want pizza" ]
    stop_examples = [ "not hungry anymore" ]
    ask_confirm = True

    def submit(self, form_data):
        
        # do the actual order here!

        return {
            "output": f"Pizza order on its way"
        }Code language: Python (python)

Forms

Handle goal oriented multi turn conversations,

  • Gather complex information on autopilot
  • Based on pydantic models (types and custom validation)
  • Ask for a final confirmation
  • Custom submit callback
Learn more

Latest from Wonderland

See all blog articles

Join us at the next Meow Event!

Our growing and active community is hosting many furrmidable events in the Discord server.

Don’t miss the chance to take part to the Cheshire Cat community and save the dates! Meeoow!