Cheshire Cat (Stregatto)

TypeScript version of the Cheshire Cat AI framework originally made in Python.

Check out the linked project for more information on what's being worked on.

📜 For the full list of changes, please read the changelog file.

👥 If you want to contribute, please read the contributing file.

📃 To be sure to respect everything, please read the code of conduct file.

Why use the cat?

• ⚡️ API first, so you get a microservice to easily add a conversational layer to your app
• 🐘 Remembers conversations and documents and uses them in conversation
• 🚀 Extensible via plugins
• 🏛️ Event callbacks, function calling (tools), conversational forms
• 🌍 Supports any language model (works with OpenAI, Google, Ollama, HuggingFace, custom services and many others)
• 🐋 Production ready - 100% dockerized

Features

• Granular plugins folder reload
• Sync/Async ingestion endpoints
• New built-in LLMs and Embedders
• Instant tool call hook
• Granular management of procedures (forms and tools)
• Supports cron jobs (without saving to memory)
• Rate limiter
• Database query executor
• Supports streaming both in WebSocket and HTTP
• Tokens usage visible through model interactions
• Cache support for LLM and Embedder responses
• External plugins registry support
• Built-in CLI
• Supports multimodality

Pre-requisites

• Bun (>= 1.1.19)
• Docker

Installation

# (for development)
bun install
rm -f .git/hooks/pre-commit && ln -s ../../pre-commit .git/hooks/pre-commit

# (for production)
docker compose build --no-cache

How to run

# (for development)
docker run -p 6333:6333 qdrant/qdrant
bun run dev
# OR
docker compose build -f compose.dev.yml --no-cache # (if you want to use Docker for development)

# (for production)
docker compose up

How to test

bun run test
# OR
docker compose -f compose.dev.yml exec ccat-ts-dev bun run test

License

This project is licensed under the GPL-3.0 License - see the LICENSE file for details.