skyagi  by litanlitudan

LLM-based role-playing game for human behavior simulation

created 2 years ago
781 stars

Top 45.6% on sourcepulse

GitHubView on GitHub
1 Expert Loves This Project
Project Summary

SkyAGI enables the simulation of emergent human-like behaviors in Large Language Models (LLMs), offering a novel approach to creating believable non-player characters (NPCs) for role-playing games and other interactive experiences. It targets developers and researchers interested in AI-driven character development and interactive storytelling.

How It Works

SkyAGI implements the "Generative Agents" concept, focusing on simulating human behavior through LLM-driven agents. Each agent maintains a memory of past interactions and uses this context to generate contextually relevant and human-like responses and actions, enabling emergent narrative progression without explicit human scripting.

Quick Start & Requirements

  • Install via pip: pip install --upgrade skyagi or make install.
  • Requires an OpenAI API key set as an environment variable: export OPENAI_API_KEY="...".
  • Agent configuration files (e.g., for characters from "The Big Bang Theory" or "The Avengers") are not included with pip install and must be downloaded separately from the repository's examples directory.

Highlighted Details

  • Demonstrates emergent memory capabilities, with agents recalling past interactions.
  • Shows agents making progress in a narrative autonomously, without direct human intervention.
  • Aims for human-like responses that are difficult to distinguish from human-generated content.
  • Supports custom character definitions via JSON configuration files.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels (like Discord/Slack) is provided in the README.

Licensing & Compatibility

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

Limitations & Caveats

The project relies on OpenAI's API, incurring costs per interaction. Agent configuration files are not bundled with the standard pip installation, requiring manual download. The README does not detail specific LLM versions or hardware requirements beyond the need for an OpenAI API key.

Health Check
Last commit

1 year ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
4 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.