Start your project with a set of integrated components for building, experimenting, and deploying your application
Build any application in code with complete flexibility
Test your changes locally with our playground UI
Iteratively performance with our experimentation tools
Look under-the-hood of any request with open-telemetry
Deploy your application with docker to any cloud provider
Build a production-ready codebase with type-safety
Swap any component of your application layer for any request to discover what works and what doesn't
Your application comes with Palico Studio, a control panel that runs locally during development, and in the cloud during production
Create an iterative loop for your team to improve accuracy, latency, and the cost of your LLM application
npx palico init <project-name>
© 2024 Palico AI Inc. All rights reserved.