Palico AI

Palico AI

LLM Tech Stack for Rapid Iteration

Building an LLM application requires continuously trying out different ideas (models, prompts, architectures). Quickly iterate on your LLM project with an integrated tech stack.

We Are Open Source
Build Any Application

Write your application in code with complete flexibility

Stay In Flow With An Integrated Tech Stack

Works With Your Favorite Tools And Libraries

Hot-swap Models, Prompts, Anything and Everything

Build an interchangable application layer where you can swap out any components at runtime without changing any code

Hotswap Flow Diagram

Systematically Improve Performance with Experiments

Create an iterative loop for your team to improve accuracy, latency, and the cost of your LLM application
Lifecycle Diagram
Define Test Cases

Define a set of expected behaviors for a set of inputs

Loading...
Run Evaluations
Analyze, Compare, and Contrast

Control Panel That Accelerates Your Development

Make changes and preview them in real-time with Chat UI


Get Started in Seconds

npx palico init <project-name>
Or start by following one of our cookbooks
Build A RAG Application

Learn how to build an LLM application using Vector Database and LLM models


Take your Application from Prototype to Production with Palico

Stay up to date with best practices in LLM development

© 2024 Palico AI Inc. All rights reserved.