https://github.com/cheshire-cat-ai/core
AI agent microservice
https://github.com/cheshire-cat-ai/core
agent ai assistant bot bot-framework chatbot conversational conversational-forms docker framework function-calling llm plugin python vector-search
Last synced: 13 days ago
JSON representation
AI agent microservice
- Host: GitHub
- URL: https://github.com/cheshire-cat-ai/core
- Owner: cheshire-cat-ai
- License: gpl-3.0
- Created: 2023-02-08T23:41:18.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2025-04-03T14:48:22.000Z (20 days ago)
- Last Synced: 2025-04-06T06:09:46.132Z (18 days ago)
- Topics: agent, ai, assistant, bot, bot-framework, chatbot, conversational, conversational-forms, docker, framework, function-calling, llm, plugin, python, vector-search
- Language: Python
- Homepage: https://cheshirecat.ai
- Size: 11.2 MB
- Stars: 2,710
- Watchers: 31
- Forks: 367
- Open Issues: 40
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Roadmap: ROADMAP.md
Awesome Lists containing this project
- awesome - cheshire-cat-ai/core - AI agent microservice (Python)
- awesome-langchain-zh - Cheshire Cat - cat-ai/core?style=social): 具有即用型聊天集成和插件开发平台的自定义 AGI 机器人。 (开源项目 / 其他聊天机器人)
- awesome-langchain - Cheshire Cat - to-use chat integration and plugins development platform.  (Open Source Projects / Other / Chatbots)
- Awesome-Ollama - Cheshire Cat assistant framework
- StarryDivineSky - cheshire-cat-ai/core
- awesome-homelab - Cheshire-Cat - Cat](https://img.shields.io/github/stars/cheshire-cat-ai/core?style=flat)  | AI agent microservice | (Apps / AI)
- awesome-llmops - Cheshire Cat AI - cat-ai/core.svg?style=flat-square) | (LLMOps / Observability)
README
Cheshire Cat AI
🇮🇹 Stregatto - 🇨🇳 柴郡貓 - 🇮🇳 चेशायर बिल्ली - 🇷🇺 Чеширский кот
## AI agent as a microservice
The Cheshire Cat is a framework to build custom AI agents:
- ⚡️ API first, to easily add a conversational layer to your app
- 💬 Chat via WebSocket and manage your agent with an customizable REST API
- 🐘 Built-in RAG with Qdrant
- 🚀 Extensible via plugins
- 🪛 Event callbacks, function calling (tools), conversational forms
- 🏛 Easy to use admin panel
- 🌍 Supports any language model via langchain
- 👥 Multiuser with granular permissions, compatible with any identity provider
- 🐋 100% dockerized
- 🦄 Active [Discord community](https://discord.gg/bHX5sNFCYU) and easy to understand [docs](https://cheshire-cat-ai.github.io/docs/)
## Quickstart
To make Cheshire Cat run on your machine, you just need [`docker`](https://docs.docker.com/get-docker/) installed:
```bash
docker run --rm -it -p 1865:80 ghcr.io/cheshire-cat-ai/core:latest
```
- Chat with the Cheshire Cat on [localhost:1865/admin](http://localhost:1865/admin)
- Try out the REST API on [localhost:1865/docs](http://localhost:1865/docs)Enjoy the Cat!
Follow instructions on how to run it properly with [docker compose and volumes](https://cheshire-cat-ai.github.io/docs/quickstart/installation-configuration/).## Minimal plugin example
Hooks (events)
```python
from cat.mad_hatter.decorators import hook# hooks are an event system to get finegraned control over your assistant
@hook
def agent_prompt_prefix(prefix, cat):
prefix = """You are Marvin the socks seller, a poetic vendor of socks.
You are an expert in socks, and you reply with exactly one rhyme.
"""
return prefix
```
Tools
```python
from cat.mad_hatter.decorators import tool# langchain inspired tools (function calling)
@tool(return_direct=True)
def socks_prices(color, cat):
"""How much do socks cost? Input is the sock color."""
prices = {
"black": 5,
"white": 10,
"pink": 50,
}price = prices.get(color, 0)
return f"{price} bucks, meeeow!"
```
Conversational Forms
## Conversational form example
```python
from pydantic import BaseModel
from cat.experimental.form import form, CatForm# data structure to fill up
class PizzaOrder(BaseModel):
pizza_type: str
phone: int# forms let you control goal oriented conversations
@form
class PizzaForm(CatForm):
description = "Pizza Order"
model_class = PizzaOrder
start_examples = [
"order a pizza!",
"I want pizza"
]
stop_examples = [
"stop pizza order",
"not hungry anymore",
]
ask_confirm = Truedef submit(self, form_data):
# do the actual order here!# return to convo
return {
"output": f"Pizza order on its way: {form_data}"
}
```## Docs and Resources
- [Official Documentation](https://cheshire-cat-ai.github.io/docs/)
- [Discord Server](https://discord.gg/bHX5sNFCYU)
- [Website](https://cheshirecat.ai/)
- [Tutorial - Write your first plugin](https://cheshirecat.ai/write-your-first-plugin/)## Roadmap & Contributing
Detailed roadmap is [here](./ROADMAP.md).
Send your pull request to the `develop` branch. Here is a [full guide to contributing](./CONTRIBUTING.md).We are committed to openness, privacy and creativity, we want to bring AI to the long tail. If you want to know more about our vision and values, read the [Code of Ethics](./CODE-OF-ETHICS.md).
Join our [community on Discord](https://discord.gg/bHX5sNFCYU) and give the project a star ⭐!
Thanks again!🙏## License and trademark
Code is licensed under [GPL3](./LICENSE).
The Cheshire Cat AI logo and name are property of Piero Savastano (founder and maintainer).## Which way to go?
```
"Would you tell me, please, which way I ought to go from here?"
"That depends a good deal on where you want to get to," said the Cat.
"I don't much care where--" said Alice.
"Then it doesn't matter which way you go," said the Cat.(Alice's Adventures in Wonderland - Lewis Carroll)
```