AI-powered code reviewer DeepCode has announced it's checked the code of over four million developers. DeepCode's machine learning-based bot is fluent in JavaScript, TypeScript, Java, C/C, and Python. "Our data shows that over 50% of repositories have critical issues and every second pull-request has warnings about issues that need to be fixed," said Boris Paskalev, CEO and co-founder of DeepCode. "By using DeepCode, these issues are automatically identified and logically explained as suggestions are made about how to fix them before code is deployed." Over the past few months, DeepCode has focused on improving the JavaScript skills of the bot.

Zurich-based DeepCode claims that their system -- essentially a tool for analyzing and improving code -- is like Grammarly for programmers. The system, which uses a corpus of 250,000 rules, reads your public and private GitHub repositories and tells you how to fix problems, remain compatible and generally improve your programs. Founded by Veselin Raychev, advisor Martin Vechev and Boris Paskalev, the team has extensive experience in machine learning and AI research. This project is a spin-off from ETH in Switzerland and is a standalone research project turned programming utility. I ran one of my public repositories through the system and received 49 suggestions in 449 files.