Early Adoption of Agentic Coding Tools by GitHub Projects
2026-07-15 • Software Engineering
Software EngineeringArtificial IntelligenceComputers and SocietyMachine Learning
AI summaryⓘ
The authors studied how software projects on GitHub use tools that can write and submit code changes on their own. They found that most projects only use these tools a little, with small teams using them a bit more than larger ones. Usually, one person reviews the tool’s work before it gets added to the project. The authors suggest that making these tools work well depends on both the technology and how people organize teamwork around them.
agentic coding toolspull requestsGitHub repositorieshuman-agent collaborationsoftware developmentopen-source projectscode reviewproject-level productivitydeveloper oversight
Authors
Maliha Noushin Raida, Daqing Hou
Abstract
Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development. While prior studies have examined PR-level outcomes of agent-generated contributions, less is known about how agentic coding tools are adopted and managed at the project level. In this paper, we analyze 25,264 agentic PRs from 2,361 popular GitHub repositories to investigate (1) the adoption of agentic coding tools, (2) project-level agentic PR productivity, and (3) human-agent collaboration patterns. Our results show that the median repository generates only one to two agentic PRs during a three-month period, indicating that intensive adoption remains concentrated in a small subset of projects. At the same time, small projects (1-5 contributors) exhibit higher participation ratios and average levels of agentic PR activity than medium-sized and large projects. We also observe substantial variation in project-level agentic PR productivity. While a small number of projects exceed an industry-reported estimate of 36 PRs per participant during the three-month observation period, most projects remain below this threshold. Finally, human-agent collaboration is dominated by a single-human oversight model, in which one developer reviews and/or modifies the agent's contributions, while multi-human collaboration patterns remain uncommon. These findings provide early empirical evidence on how open-source projects organize human oversight around agentic coding tools and suggest that successful integration of agent-generated contributions depends not only on advances in agent capabilities but also on the human and organizational processes that govern their use. Because this study captures an early snapshot of agent adoption, future work should continue to track how adoption patterns evolve over time.