{"name":"Cheshire Cat AI Core: An AI Agent Microservice Framework","description":"Cheshire Cat AI Core is an open-source framework designed for building custom AI agents as microservices. It offers an API-first approach, enabling easy integration of conversational layers into applications with WebSocket chat and a customizable REST API. Key features include built-in RAG with Qdrant, extensibility via plugins, function calling, and full Dockerization for straightforward deployment.","github":"https://github.com/cheshire-cat-ai/core","url":"https://osrepos.com/repo/cheshire-cat-ai-core","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/cheshire-cat-ai-core","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/cheshire-cat-ai-core.md","json":"https://osrepos.com/repo/cheshire-cat-ai-core.json","topics":["AI Agent","Microservice","Python","LLM","Chatbot","Framework","Docker","RAG"],"keywords":["AI Agent","Microservice","Python","LLM","Chatbot","Framework","Docker","RAG"],"stars":null,"summary":"Cheshire Cat AI Core is an open-source framework designed for building custom AI agents as microservices. It offers an API-first approach, enabling easy integration of conversational layers into applications with WebSocket chat and a customizable REST API. Key features include built-in RAG with Qdrant, extensibility via plugins, function calling, and full Dockerization for straightforward deployment.","content":"## Introduction\n\nCheshire Cat AI Core is a robust, API-first framework for developing custom AI agents as microservices. Written in Python, it provides a comprehensive toolkit for integrating conversational AI capabilities into any application. The framework supports WebSocket for chat interactions and offers a customizable REST API for agent management, making it highly versatile for various use cases.\n\nKey features include built-in Retrieval Augmented Generation (RAG) with Qdrant, a powerful plugin system for extensibility, and support for event callbacks, function calling (tools), and conversational forms. It also boasts an easy-to-use admin panel, multi-user support with granular permissions, and compatibility with any identity provider and language model via Langchain. The entire system is 100% Dockerized for effortless deployment.\n\n## Installation\n\nGetting Cheshire Cat AI Core up and running on your machine is straightforward, requiring only [Docker](https://docs.docker.com/get-docker/ \"Docker\") to be installed.\n\nTo quickly start the latest version, use the following command:\n\nbash\ndocker run --rm -it -p 1865:80 ghcr.io/cheshire-cat-ai/core:latest\n\n\nOnce running, you can interact with the Cheshire Cat:\n\n*   Chat with the Cheshire Cat on [localhost:1865/admin](http://localhost:1865/admin \"Admin Panel\")\n*   Explore the REST API on [localhost:1865/docs](http://localhost:1865/docs \"REST API Docs\")\n\nFor a more persistent setup with Docker Compose and volumes, refer to the [official documentation](https://cheshire-cat-ai.github.io/docs/quickstart/installation-configuration/ \"Installation and Configuration\").\n\n## Examples\n\nCheshire Cat AI Core provides powerful mechanisms for customizing agent behavior, including hooks, tools, and conversational forms.\n\n### Hooks (Events)\n\nHooks are an event system that allows for fine-grained control over your assistant's behavior at various stages of a conversation.\n\npython\nfrom cat.mad_hatter.decorators import hook\n\n@hook\ndef agent_prompt_prefix(prefix, cat):\n    prefix = \"\"\"You are Marvin the socks seller, a poetic vendor of socks.\\nYou are an expert in socks, and you reply with exactly one rhyme.\\n\"\"\"\n    return prefix\n\n\n### Tools (Function Calling)\n\nInspired by Langchain, tools enable your AI agent to perform specific actions or retrieve information by calling external functions.\n\npython\nfrom cat.mad_hatter.decorators import tool\n\n@tool(return_direct=True)\ndef socks_prices(color, cat):\n    \"\"\"How much do socks cost? Input is the sock color.\"\"\"\n    prices = {\n        \"black\": 5,\n        \"white\": 10,\n        \"pink\": 50,\n    }\n\n    price = prices.get(color, 0)\n    return f\"{price} bucks, meeeow!\" \n\n\n### Conversational Forms\n\nConversational forms allow you to guide goal-oriented conversations, collecting specific data from the user in a structured manner.\n\npython\nfrom pydantic import BaseModel\nfrom cat.experimental.form import form, CatForm\n\n# data structure to fill up\nclass PizzaOrder(BaseModel):\n    pizza_type: str\n    phone: int\n\n# forms let you control goal oriented conversations\n@form\nclass PizzaForm(CatForm):\n    description = \"Pizza Order\"\n    model_class = PizzaOrder\n    start_examples = [\n        \"order a pizza!\",\n        \"I want pizza\"\n    ]\n    stop_examples = [\n        \"stop pizza order\",\n        \"not hungry anymore\",\n    ]\n    ask_confirm = True\n\n    def submit(self, form_data):\n        \n        # do the actual order here!\n\n        # return to convo\n        return {\n            \"output\": f\"Pizza order on its way: {form_data}\"\n        }\n\n\n## Why Use Cheshire Cat AI Core?\n\nCheshire Cat AI Core stands out as an excellent choice for building AI agents due to several compelling reasons:\n\n*   **API-First Design:** Easily integrate conversational layers into existing applications with its robust WebSocket and REST APIs.\n*   **Extensibility:** Customize and extend functionality through a powerful plugin system, hooks, and function calling capabilities.\n*   **Built-in RAG:** Leverage integrated Retrieval Augmented Generation with Qdrant for enhanced knowledge retrieval and context awareness.\n*   **LLM Agnostic:** Supports any language model via Langchain, offering flexibility in choosing your preferred AI backend.\n*   **Simplified Deployment:** Being 100% Dockerized, it ensures consistent and easy deployment across different environments.\n*   **Active Community:** Benefit from an active [Discord community](https://discord.gg/bHX5sNFCYU \"Discord Server\") and comprehensive [documentation](https://cheshire-cat-ai.github.io/docs/ \"Official Documentation\").\n\n## Links\n\nExplore more about Cheshire Cat AI Core through these official resources:\n\n*   [Official Documentation](https://cheshire-cat-ai.github.io/docs/ \"Official Documentation\")\n*   [Discord Server](https://discord.gg/bHX5sNFCYU \"Discord Server\")\n*   [Website](https://cheshirecat.ai/ \"Cheshire Cat AI Website\")\n*   [Tutorial - Write your first plugin](https://cheshirecat.ai/write-your-first-plugin/ \"Plugin Tutorial\")","metrics":{"detailViews":2,"githubClicks":3},"dates":{"published":null,"modified":"2026-02-15T00:00:47.000Z"}}