Dice Question Streamline Icon: https://streamlinehq.com

Adoption of AI configuration files in open-source projects

Determine how widely open-source software projects have adopted machine-readable AI configuration files for AI coding agents, such as AGENTS.md, CLAUDE.md, GitHub Copilot’s copilot-instructions.md, and GEMINI.md, to quantify their prevalence across repositories.

Information Square Streamline Icon: https://streamlinehq.com

Background

The paper introduces AI configuration files (e.g., AGENTS.md) as version-controlled artifacts that encode project-specific context for AI coding agents. Despite anecdotal evidence of widespread usage, the actual adoption in engineered open-source software projects remains uncertain.

Establishing adoption rates is essential for understanding real-world practice in context engineering and for guiding further empirical analyses on structure, evolution, and effectiveness of these files.

References

Important unanswered questions include: RQ1 How widely have open-source software projects adopted AI configuration files?

— Context Engineering for AI Agents in Open-Source Software (2510.21413 - Mohsenimofidi et al., 24 Oct 2025) in Introduction (Section 1), list of research questions