Getting Started with AgentForge

Learn how to set up, configure, and deploy your first AI agent in under 5 minutes.

Quick Start

AgentForge is a framework for building, testing, and deploying autonomous AI agents. It provides a unified API across multiple LLM providers — OpenAI, Anthropic, Google, and open-source models — so you can switch providers without changing your agent code.

To get started, install the CLI:

npm install -g @agentforge/cli
agentforge init my-agent
cd my-agent
agentforge dev

This creates a new agent project with a default configuration, a hello-world agent, and a development server that auto-reloads on changes.

Prerequisites

• Node.js 18+ — JavaScript runtime for running agents locally
• An API key — From OpenAI, Anthropic, or any supported provider
• Git — For version control and template management

Core Concepts

AgentForge is built around four primary concepts:

• Agents — Individual AI entities with a system prompt, model, and toolset
• Tools — Functions agents can call (web search, file I/O, API calls, custom code)
• Workflows — Multi-step processes that chain agents and tools together
• Memory — Persistent context that agents can read and write across sessions

Next Steps

Now that you understand the basics, explore the other sections:

• Installation Guide — Detailed setup for different environments
• Configuration Reference — All configuration options explained
• Agent Patterns — Common agent archetypes and when to use them
• API Reference — Complete API documentation