Introduction

Piri is a spatial database built for AI agents. It exposes a full geospatial toolkit over the Model Context Protocol, so LLM agents get deterministic spatial tools — proximity search, geofencing, polygon intersection, H3 indexing — without hallucination.

Overview

Introduction is framed as an execution surface instead of a generic article. Use it when you need direct context, concise operational detail, and a fast path into getting started.

Concepts

download

Installation

Requires Go 1.25+.

rocket_launch

Quick Start

Get up and running with Piri in 5 minutes.

travel_explore

R-tree Indexing

High-performance spatial indexing for fast geographic and geometric queries.

Agentic Tools

getting_started.json

{
  "tool_name": "getting_started",
  "scope": "Getting Started",
  "description": "Piri is a spatial database built for AI agents. It exposes a full geospatial toolkit over the Model Context Protocol, so LLM agents get deterministic spatial tools — proximity search, geofencing, polygon intersection, H3 indexing — without hallucination.",
  "parameters": {
    "workspace": "default",
    "surface": "getting-started",
    "focus": "Introduction",
    "mode": "reference"
  }
}

Implementation

docs_getting_started.ts

import { PiriClient } from '@piri/sdk'

const client = new PiriClient({
  apiKey: process.env.PIRI_API_KEY!,
  baseUrl: process.env.PIRI_BASE_URL!,
})

async function runDocsFlow() {
  const result = await client.request('/v1/bootstrap', {
    method: 'POST',
    body: {
      page: 'Introduction',
      section: 'Getting Started',
      intent: 'load'
    }
  })

  return result
}

runDocsFlow().then(console.log)