polaris

<h1 align="center" style="border-bottom: none">
  <img src="docs/polaris.png" width="150">
</h1>

# `polaris`: A Distributed AI Agent Framework for Function Calling

[![MIT License](https://img.shields.io/github/license/octu0/polaris)](https://github.com/octu0/polaris/blob/master/LICENSE)
[![GoDoc](https://pkg.go.dev/badge/github.com/octu0/polaris)](https://pkg.go.dev/github.com/octu0/polaris)
[![Go Report Card](https://goreportcard.com/badge/github.com/octu0/polaris)](https://goreportcard.com/report/github.com/octu0/polaris)
[![Releases](https://img.shields.io/github/v/release/octu0/polaris)](https://github.com/octu0/polaris/releases)

`polaris` is a Go framework for building **distributed AI agents**.

These agents run as lightweight sidecars alongside your applications, securely exposing system capabilities and local resources (like logs or metrics) via **Function Calling**. This enables AI models (such as Google's Vertex AI Gemini) to intelligently interact with your distributed infrastructure through a unified polaris interface, simplifying complex coordination. This framework is designed for **parallel execution** to handle demanding workloads.

## Features

1.  **Distributed Agent Architecture:** Deploy lightweight `polaris` agents across your infrastructure (servers, containers). Each agent registers specific functions, making local resources or actions available network-wide.
2.  **Access Local Resources via AI:** Enable AI models to securely query log files, fetch system status, execute commands, or interact with other server-local resources through the Function Calls exposed by your distributed agents.
3.  **Parallel Execution:** Handles heavy workloads efficiently by executing incoming Function Call requests in parallel across agents, preventing bottlenecks.
4.  **Simplified JSON Schema:** Define function parameters and responses with a much more concise and readable syntax compared to standard library methods.
5.  **Simple Agent Implementation:** Easily