Agentic Much? Adoption of Coding Agents on GitHub

TL;DR

This study analyzes the rapid adoption of autonomous coding agents on GitHub, revealing high adoption rates across diverse projects and significant impacts on commit characteristics.

Contribution

First large-scale empirical analysis of coding agent adoption on GitHub, highlighting its broad usage and influence on software development practices.

Findings

Adoption rate of coding agents is between 22.20% and 28.66%.

Adoption spans various project maturities, organizations, and programming languages.

Agent-assisted commits tend to be larger and include more features and bug fixes.

Abstract

In the first half of 2025, coding agents have emerged as a category of development tools that have very quickly transitioned to the practice. Unlike ''traditional'' code completion LLMs such as Copilot, agents like Cursor, Claude Code, or Codex operate with high degrees of autonomy, up to generating complete pull requests starting from a developer-provided task description. This new mode of operation is poised to change the landscape in an even larger way than code completion LLMs did, making the need to study their impact critical. Also, unlike traditional LLMs, coding agents tend to leave more explicit traces in software engineering artifacts, such as co-authoring commits or pull requests. We leverage these traces to present the first large-scale study (128,018 projects) of the adoption of coding agents on GitHub, finding an estimated adoption rate of 22.20%--28.66%, which is very high for a technology only a few months old--and increasing. We carry out an in-depth study of the adopters we identified, finding that adoption is broad: it spans the entire spectrum of project maturity; it includes established organizations; and it concerns diverse programming languages or project topics. At the commit level, we find that commits assisted by coding agents are larger than commits only authored by human developers, and have a large proportion of features and bug fixes. These findings highlight the need for further investigation into the practical use of coding agents.