GABM: Generative Agent-Based Model

Overview

GABM is a flexible, extensible Python framework for developing agent-based models that use large language models (LLMs) as agent reasoning engines. It supports use of multiple LLM providers and implements persistent response caching.

License

See LICENSE.

Code of Conduct and Reporting

Please see our Code of Conduct for guidelines on expected behavior and reporting issues.

For security or conduct concerns, you can also use the Contact maintainers link on the GitHub repository, or see the SECURITY.md file in the documentation for details on confidential reporting.

User Guide

Please use the User Guide.

Developer Guide

Please use the Developer Guide.

Roadmap

See ROADMAP.md for planned next steps and future goals.

Change Log

See CHANGE_LOG.md for details of each release.

Development History

The collaborative development of GABM is captured in the DEVELOPMENT_HISTORY.md.

Acknowledgements

This project was developed with significant assistance from GitHub Copilot for code generation, refactoring, and documentation improvements.

We gratefully acknowledge support from the University of Leeds. Funding for this project comes from a UKRI Future Leaders Fellowship awarded to Professor Viktoria Spaiser (grant reference: UKRI2043).