Ranger Documentation

Build, deploy, and scale intelligent infrastructure with the speed of light. Explore guides, API references, and architecture blueprints for the agentic future.

bolt

Quick Start

info

Introduction

Fundamental concepts of Ranger's orchestration layer and how it manages agentic workloads across distributed nodes.

Read Overview arrow_forward

sync_alt

Migration from GitHub Actions

Step-by-step guide to porting your existing workflows. Reduce execution costs by up to 60% with Ranger's native runners.

Get the Script arrow_forward

developer_board

Configuring Runners

Define execution environments using YAML or our intuitive CLI. Support for ARM64, NVIDIA H100s, and bare-metal nodes.

Setup Runner arrow_forward

psychology

AI Quality Engine

Implement automated observability for LLMs. Monitor hallucination rates and response latency in real-time pipelines.

Configure QA arrow_forward

auto_awesome

Featured Guides

High-Performance Caching

Learn how to implement multi-tier caching for global agent deployments using Ranger Edge.

Live Debugging

Using the Ranger CLI to inspect running agent containers in real-time without interrupting production flow.

code

API Reference

GET /v1/agents/{agent_id}/status

v1.2

{
  "id": "ag_01hx882",
  "status": "healthy",
  "compute": {
    "utilization": 42.5,
    "region": "us-east-1"
  }
}

POST /v1/deployments

v1.2

// Header
Authorization: Bearer <TOKEN>

// Body
{
  "model": "gpt-4-turbo",
  "replicas": 3,
  "scaling": "auto"
}