AIDev: Studying AI Coding Agents on GitHub

2026-02-09

AI Summary

This study addresses the scarcity of large-scale, real-world data on AI-powered coding agents and their impact on software engineering practices. To bridge this gap, we present AIDev, the first large-scale dataset capturing the adoption and collaboration patterns of five prominent AI coding agents—Codex, Devin, Copilot, Cursor, and Claude Code—in authentic development environments. Constructed via GitHub API and multi-source tracing techniques, AIDev comprises 932,791 pull requests generated by these agents across 110,000 repositories and 72,000 developers, along with complete interaction contexts—including comments, reviews, commits, and linked issues—for 33,596 high-star projects. This dataset establishes a foundational empirical resource for investigating AI adoption behaviors, human–AI collaboration dynamics, and productivity effects in software development.

Technology Category

• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

AI coding agents are rapidly transforming software engineering by performing tasks such as feature development, debugging, and testing. Despite their growing impact, the research community lacks a comprehensive dataset capturing how these agents are used in real-world projects. To address this gap, we introduce AIDev, a large-scale dataset focused on agent-authored pull requests (Agentic-PRs) in real-world GitHub repositories. AIDev aggregates 932,791 Agentic-PRs produced by five agents: OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code. These PRs span 116,211 repositories and involve 72,189 developers. In addition, AIDev includes a curated subset of 33,596 Agentic-PRs from 2,807 repositories with over 100 stars, providing further information such as comments, reviews, commits, and related issues. This dataset offers a foundation for future research on AI adoption, developer productivity, and human-AI collaboration in the new era of software engineering.>AI Agent, Agentic AI, Coding Agent, Agentic Coding, Agentic Software Engineering, Agentic Engineering

Problem

• AI coding agents
• real-world usage
• software engineering
• dataset gap
• Agentic-PRs

Innovation

• AI coding agent
• Agentic-PR
• AIDev dataset
• human-AI collaboration
• software engineering