charmbracelet/fantasy

Build AI agents with Go. Multiple providers, multiple models, one API. 🧙

What it solves

Fantasy provides a unified API for building AI agents in the Go programming language, eliminating the need to write different code for every different AI provider or model.

How it works

It acts as a wrapper that allows developers to select a provider (such as OpenRouter, Azure, or Bedrock) and a specific model, then equip the agent with custom tools (functions the agent can call) and a system prompt to define its behavior.

Who it’s for

Go developers who want to integrate LLM-powered agents into their applications without being locked into a single AI provider.

Highlights

  • Multi-provider support including dedicated packages for Azure, Bedrock, and OpenRouter.
  • OpenAI-compatible layer for generic integration with other providers.
  • Support for custom agent tools to extend agent capabilities.
  • Compiles to native machine code for performance.

Related

  • Project
    mozilla-ai/any-agent

    A unified interface and evaluation tool that allows developers to run and compare AI agents across multiple frameworks like LangChain, LlamaIndex, and OpenAI Agents SDK using a single API.

  • Project
    microsoft/agent-framework-go

    Microsoft Agent Framework for Go is a production‑grade SDK that lets Go developers build, orchestrate, and observe multi‑agent AI workflows. It supports multiple LLM providers (Azure OpenAI, OpenAI, Microsoft Foundry), middleware, graph‑based workflow patterns, OpenTelemetry tracing, and skill‑based knowledge bases. The repo includes install instructions, a quick‑start haiku example, and a rich set of sample projects. It’s in public preview and aligns with the broader MAF ecosystem (.NET/Python).

  • Project
    andrewyng/aisuite

    A lightweight Python library providing a unified Chat Completions API and an Agents API to build AI agents across multiple LLM providers with minimal code.

  • Project
    awslabs/amazon-bedrock-agent-samples

    A collection of reference implementations and best practices for building single and multi-agent AI assistants using Amazon Bedrock Agents.

  • Project
    microsoft/teams-sdk

    A comprehensive development framework for building AI-powered agents and applications integrated into Microsoft Teams.