Our latest developer-oriented DORA research shows that more than 75% of developers are relying on AI in their daily responsibilities. As one example, more than 25% of all new code at Google is generated by AI, then reviewed and accepted by engineers.

While well-resourced organizations are empowering their engineering teams with the latest AI capabilities, that level of tooling hasn’t always been accessible to students, hobbyists, freelancers and startups. And with a worldwide population of developers forecasted to grow to 57.8 million by 2028, we think AI should be available to them whether they can pay for it or not, so they can start building with what are quickly becoming the standard digital tools of the future.

To bridge that gap, today we’re announcing the public preview of Gemini Code Assist for individuals, a free version of our AI-coding assistant.

Development assistance powered by Gemini 2.0

Gemini Code Assist for individuals is globally available and powered by Gemini 2.0. It supports all programming languages in the public domain, and importantly, it’s optimized for coding. We fine-tuned the Gemini 2.0 model for developers by analyzing and validating a large number of real-world coding use cases. As a result, the quality of AI-generated recommendations in Gemini Code Assist is better than ever before and ready to address the myriad of daily challenges developers face, whether they’re hobbyists or startup developers.

While other popular free coding assistants have restrictive usage limits, with usually only 2,000 code completions per month, we wanted to offer something more generous. We're offering practically unlimited capacity with up to 180,000 code completions per month using Gemini Code Assist – a ceiling so high that even today’s most dedicated professional developers would be hard-pressed to exceed it.

But AI isn’t just an accelerant for writing code; it can also help us write better code. A quality and efficient code review process is critical; yet code reviews are often time consuming and stand in the way of getting things done. So we’re also helping reduce the time it takes developers to perform code reviews with the public preview of Gemini Code Assist for GitHub, which provides free, AI-powered code reviews for both public and private repositories.

AI coding assistance, where developers want it, at no cost

Developers spend most of their time coding in integrated development environments (IDEs).

With the new, free version of Gemini Code Assist in Visual Studio Code and JetBrains IDEs, individual developers now have the same code completion, generation and chat capabilities that we’ve offered businesses for over a year, and that are already available for free in Firebase and Android Studio. Now anyone can more conveniently learn, create code snippets, debug and modify their existing applications — all without needing to toggle between different windows for help or to copy and paste information from disconnected sources.

And with the most generous usage limit of 90 times¹ more code completions per month than other popular free coding assistants, coders of all types can reap the rewards. If you’re a student working on a time-sensitive project, you won’t find your coding project suddenly stalled because you’ve hit a cap, or have to worry about chat limits stopping your pair-programming sessions.

Gemini Code Assist for individuals comes with a generous token context window, with up to 128,000 input token support in chat. This large context window lets developers use large files and ground Gemini Code Assist with a broader understanding of their local codebases.

The chat feature also makes it easy for developers to focus on the creative part of development, while leaving the necessary, but repetitive steps — like writing comments or automated tests from requirements — to Gemini.

Developers can use natural language in a variety of languages in Gemini Code Assist to generate, explain and improve code. For example, a freelance website developer could quickly get code with a prompt like, “Build me a simple HTML form with fields for name, email, and message, and then add a ‘submit’ button.” Or someone just looking to automate more routine tasks can ask Gemini to “Write a script that sends a daily email with the latest weather forecast,” or “Explain what this Python code snippet does and find any errors.”

Customizable, actionable feedback on your pull requests with Gemini Code Assist for GitHub

Code review is one of the most critical, albeit time consuming, parts of software development.

With Gemini Code Assist for GitHub, developers get a powerful helping hand that can detect stylistic issues and bugs and automatically suggest code changes and fixes. Offloading basic reviews to an AI agent can help make code repositories more maintainable and improve quality, allowing developers to focus on more complex tasks. It’s available directly in GitHub, where most open-source developers post and review code, via a GitHub app.

Different developer teams may also have different best practices, coding conventions and preferred frameworks and libraries. To address this need, Gemini Code Assist for GitHub supports custom style guides for code reviews. Each team can describe which instructions Gemini should follow when reviewing code in a .gemini/styleguide.md file in their repository. That way, Gemini tailors its code reviews to the needs of the repository.

Get started today, quickly and easily

Whether you’re a student building an interactive data visualization using JavaScript, or a freelance developer testing ideas for an application or game, you can use Gemini Code Assist to help you get your project done faster, with more expertise, at no cost.

Signup is quick and easy, and only requires a personal Gmail account, no credit card needed. Get started by installing Gemini Code Assist in Visual Studio Code, GitHub or JetBrains IDEs.

With user feedback on this public preview, we’ll continue to fine-tune Gemini Code Assist. You can share feedback right from the “Send feedback” form in the IDE or in GitHub.

People interested in advanced functionality such as productivity metrics, customized AI responses based on private source code repositories, or integrations with Google Cloud services like BigQuery can also consider Gemini Code Assist Standard or Enterprise.