Code4MeV2: a Research-oriented Code-completion Platform
Roham Koohestani, Parham Bateni, Aydin Ebrahimi, Behdad Etezadi, Kiarash Karimi, Maliheh Izadi
2025-10-07
Summary
This paper introduces Code4MeV2, a new, openly available tool designed to help researchers study how programmers interact with AI code completion systems.
What's the problem?
Currently, data about how people use AI code completion tools is kept secret by the companies that make them. This makes it really hard for academic researchers to study these interactions and improve the tools, because they have to build their own systems from scratch just to collect data, which is time-consuming and limits the scale of their research.
What's the solution?
The researchers created Code4MeV2, which is a plugin for popular programming software like IntelliJ IDEA. It works like other code completion tools, suggesting code as you type and even offering a chat assistant. But, importantly, it's built to easily and transparently collect data about how people use it, giving researchers a lot of control over what information they gather. It's also fast, with suggestions appearing in about 200 milliseconds, which is comparable to industry standards.
Why it matters?
This tool is important because it provides the research community with a shared, open platform for studying human-AI collaboration in coding. By making data collection easier and more accessible, it will allow researchers to better understand how AI can best assist programmers, leading to more effective and user-friendly coding tools in the future.
Abstract
The adoption of AI-powered code completion tools in software development has increased substantially, yet the user interaction data produced by these systems remain proprietary within large corporations. This creates a barrier for the academic community, as researchers must often develop dedicated platforms to conduct studies on human--AI interaction, making reproducible research and large-scale data analysis impractical. In this work, we introduce Code4MeV2, a research-oriented, open-source code completion plugin for JetBrains IDEs, as a solution to this limitation. Code4MeV2 is designed using a client--server architecture and features inline code completion and a context-aware chat assistant. Its core contribution is a modular and transparent data collection framework that gives researchers fine-grained control over telemetry and context gathering. Code4MeV2 achieves industry-comparable performance in terms of code completion, with an average latency of 200~ms. We assess our tool through a combination of an expert evaluation and a user study with eight participants. Feedback from both researchers and daily users highlights its informativeness and usefulness. We invite the community to adopt and contribute to this tool. More information about the tool can be found at https://app.code4me.me.