Eliza is an open-source operating system for creating and deploying autonomous AI agents. It targets developers and power users looking to build custom chatbots, autonomous systems, or integrate AI into business processes, offering broad model support and multi-agent capabilities.

How It Works

Eliza utilizes a modular architecture with a core functionality package, extensible client implementations, and a system for custom actions. It supports a wide array of AI models (Llama, Grok, OpenAI, Anthropic, Gemini) and integrates with platforms like Discord, X (Twitter), and Telegram. Key features include multi-agent coordination, document ingestion with retrievable memory, and a plugin system for extending functionality.

Quick Start & Requirements

• Installation: Clone the eliza-starter repository and run pnpm i && pnpm build && pnpm start.
• Prerequisites: Python 2.7+ (3.8+ recommended), Node.js 23+, pnpm. WSL 2 is required for Windows users.
• Resources: Minimum 1GB storage, 4GB RAM, broadband internet. GPU recommended for local LLM inference.
• Documentation: Technical Report, Documentation

Highlighted Details

• Supports integration with Discord, X (Twitter), and Telegram.
• Compatible with a wide range of AI models including Llama, Grok, OpenAI, Anthropic, and Gemini.
• Features multi-agent support and "room" functionality for agent interaction.
• Offers document ingestion with retrievable memory and a document store.
• Highly extensible via a plugin system and custom actions.

Maintenance & Community

• Active development with frequent iteration.
• Community support via GitHub Issues and elizaOS Discord.
• A technical paper is available for citation: arXiv:2501.06781.

Licensing & Compatibility

• The repository does not explicitly state a license in the README. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project iterates rapidly, suggesting potential for breaking changes. The lack of a clearly stated license in the README raises concerns about commercial use and derivative works. Python 2.7 is listed as a minimum requirement, which is outdated and may indicate compatibility issues with modern Python ecosystems.