Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

Early Adoption of Agentic Coding Tools by GitHub Projects

Source

arXiv

arxiv.org/abs/2607.14037v1

Read the source

Source

Plain-Language Brief

The paper investigates the early adoption of automated coding tools by GitHub projects. It found that while intensive adoption is concentrated in a few projects, smaller projects tend to have higher participation ratios and agent-related activity. The study also finds that human oversight is mainly single-human, and multi-human collaboration patterns are rare.

What the Document Says

  • The paper discusses the use of agentic coding tools in software development on GitHub.
  • The authors analyze 25,264 agentic pull requests (PRs) from 2,361 popular GitHub repositories.
  • They investigate three aspects: adoption of agentic coding tools, project-level agentic PR productivity, and human-agent collaboration patterns.

Key Concepts Mentioned

  • Agentic coding tools
  • Pull requests (PRs)
  • Software development
  • GitHub repositories
  • Adoption
  • Project-level productivity
  • Human-agent collaboration

Claims Made by the Document

  • Intensive adoption of agentic coding tools is concentrated in a small subset of projects.
  • Small projects have higher participation ratios and average levels of agentic PR activity than medium-sized and large projects.
  • There is substantial variation in project-level agentic PR productivity.

Evidence Used

  • Data analysis of 25,264 agentic PRs from 2,361 popular GitHub repositories.

Methods / Approach

  • Data analysis of pull request activity on GitHub

Limitations Stated by the Authors

  • The study only captures an early snapshot of agent adoption and does not track how adoption patterns evolve over time.

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The data might not represent all GitHub projects or all usage patterns of agentic coding tools.

Open Questions

  • How will the adoption patterns of agentic coding tools evolve over time?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • This study focuses on a specific period and may not capture long-term trends or changes in adoption patterns.

Raw Abstract / Excerpt

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.