fantasy  by charmbracelet

Go framework for building AI agents

Created 3 months ago
334 stars

Top 82.0% on SourcePulse

GitHubView on GitHub
Project Summary

Builds AI agents using Go, offering a unified API across multiple AI model providers and models. It targets Go developers seeking to integrate diverse AI capabilities into their applications with a single, consistent interface, enabling rapid prototyping and deployment of sophisticated AI agents.

How It Works

Fantasy provides a Go SDK that abstracts away the complexities of interacting with various AI service providers. It employs a multi-provider, multi-model architecture, allowing developers to switch between backends like OpenRouter or OpenAI-compatible services seamlessly. The core advantage lies in compiling directly to native machine code, potentially offering performance benefits over interpreted languages, while maintaining a consistent API for model selection and tool integration.

Quick Start & Requirements

Integration involves importing the charm.land/fantasy package and provider-specific modules (e.g., openrouter). Requires API keys for chosen providers. Examples are available in the project's examples directory.

Highlighted Details

  • Unified API for diverse AI providers and models.
  • Go-native implementation compiling to machine code.
  • Extensible design encourages community contributions for new provider integrations.

Maintenance & Community

Fantasy is part of the "Charm" project. Community support and discussion channels are available via Slack, Discord, Twitter, The Fediverse, and Bluesky.

Licensing & Compatibility

The provided README does not specify a software license. This absence requires clarification regarding usage rights, distribution, and potential compatibility issues for commercial or closed-source applications.

Limitations & Caveats

The project is currently in preview, with potential for API changes. It does not yet support image models, audio models, PDF uploads, or provider-specific tools like web search. Contributions for these features are welcome.

Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
25
Issues (30d)
7
Star History
218 stars in the last 30 days

Explore Similar Projects

Starred by Wes McKinney Wes McKinney(Author of Pandas), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
22 more.

autogen by microsoft

0.3%
52k
Agentic framework for multi-agent AI applications
Created 2 years ago
Updated 1 month ago
Feedback? Help us improve.