Inline code completions provide you with code completion suggestions as you code, in the same line. Watch the below video to see how it works.
The default code suggestion mode is inline, which has the following benefits:
[cta_btn url=”https://www.tabnine.com/enterprise?contact-enterprise” label=”Request a demo”]
Are developers getting lazy? Is there a conspiracy to replace us all with AI-based code generators? Probably not, but it’s easy to suspect so with the apparent onslaught of AI/ML coding assistants from the world’s tech giants.
The latest addition to the growing list of AI coding assistants is Amazon CodeWhisperer. Amazon defines CodeWhisperer as an “ML-powered coding companion.” Sounds familiar? It might be because Github calls Copilot an “AI pair programmer” – essentially the same thing.
It’s clear why Amazon chose to release its alternative to Copilot. Github’s code completion tool made waves across the developer community with impressive adoption rates. Then, only days after Microsoft put a price tag on Copilot, Amazon announced it would be releasing a preview version of CodeWhisperer for IDEs that support the AWS Toolkit.
Speaking to TechCrunch, Vasi Philomin, Amazon’s VP in charge of AI services, emphasized that the company didn’t create CodeWhisperer to compete with Github’s Copilot. According to Amazon, CodeGuru (Amazon’s AI code reviewer and performance profiler) and DevOps Guru (a tool for finding operation issues), the company laid the groundwork for CodeWhisperer’s launch years ago.
For heavy AWS users, CodeWhisperer may seem like a logical AI/ML coding assistant choice. After all, it comes installed with the AWS Toolkit, and the waiting list can’t be long. But is CodeWhisperer worth trying out if you’re not looking for AWS-specific suggestions in your code? And how does it compare to more established code completion and suggestion tools?
Amazon CodeWhisperer is, according to the official description, a “machine learning (ML)–powered service that aims to improve developer productivity by generating code recommendations based on their comments in natural language and code in the integrated development environment (IDE).” Announced in June 2022, CodeWhisperer is available only upon request to users who apply for the preview period.
At the time of writing, CodeWhisperer supports code suggestions for Java, Python, and JavaScript projects only. It is installed as part of the AWS Toolkit and will work on popular IDEs, including JetBrains IDEs, Visual Studio Code, and, of course, AWS Cloud9.
According to Amazon, they train CodeWhisperer on “billions of lines of code drawn from open source repositories, internal Amazon repositories, API documentation, and forums.” Then, you can use CodeWhisperer in your IDE to get recommendations based on previous code lines or comments.
Intelligent code completion is not new. Neither Github nor Amazon discovered the proverbial wheel of software development AI assistants. Quite a few solutions existed before CodeWhisperer and Copilot were announced. One of these veteran AI assistants is Tabnine – yup, that’s us.
Tabnine is a code completion tool that supports all the most popular languages, libraries, and frameworks in your favorite IDEs. Our AI models are only trained on permissive open source licensed code, so you can rest assured that your code is not going anywhere.
Tabnine Pro subscription lets you train your own private AI model based on your code and get personalized code completions that match your style and patterns. Getting to keep all your code on your local corporate is not the only benefit of training your own junior AI pair programmer. Hosting and training your own AI models for organizations and teams enables collaborative autocompletion across IDEs.
Pricing:
Free account (enabling short code completion)
Pro account: starting at $12/month per user (free trial available)
Enterprise account: pricing is available on quote.
[cta_btn url=”https://www.tabnine.com/pricing/landing” label=”Start a free trial”]
GitHub Copilot uses the OpenAI Codex to suggest code and whole functions for popular code editors like Visual Studio Code, Visual Studio, Neovim, and JetBrains IDEs. In terms of languages, Copilot offers support for languages like Python, JavaScript, TypeScript, Ruby, and Go.
Copilot’s somewhat bumpy launch into the world brought positive competition like CodeWhisperer and a lot more attention to the abilities of proven software development AI solutions.
Pricing:
$10/month or $100/year (free trial available).
Amazon CodeWhisperer draws more from Captain Stack than Copilot, even though Github’s service inspired Captain Stack.
Captain Stack is a code suggestion tool that uses Google instead of AI. It sends your search query to Google, retrieves StackOverflow and Github Gist answers, and auto-completes them. Available for VSCode alone, Captain Stack is more of a shortcut to Google in your IDE than an intelligent code completion tool.
Pricing: Free
Another open-source plugin for VSCode that Copilot inspired is GTP-Code-Clippy.
GPT-Code-Clippy (GPT-CC) aims to be an open source version of GitHub Copilot, a language model (based on GPT-3, called GPT-Codex) fine-tuned on publicly available code from GitHub.
Pricing: Free
Just a second, mate! Let me wait for the code suggestions to load. Second Mate is another open-source AI code completion plugin. It uses EleutherAI GPT-Neo-2.7B (via Huggingface Model Hub) for Emacs. It is a much smaller model, so it will likely not be as effective as CodeWhisperer, Tabnine, or other alternatives.
Pricing: Free
Even though it is no longer maintained or available, we remember Kite fondly. This security-aware coding assistant was one of the more user-friendly and flexible players in the arena. Unfortunately, at the time of writing, there was no indication that Kite would ever return to the ring.
The six solutions listed above are not the only ones out there. YouCompleteMe, Google’s mysterious AI pair programmer, and other niche code completion and AI pair programming tools will continue to pop up as the battle for the role of your virtual coding assistant rages on. CodeWhisperer is still very new on the block, and it may take some time before it is adopted beyond the AWS fanbase.
Suppose you’re a software developer who hasn’t heard of Microsoft’s GitHub Copilot. In that case, I’m curious about the amenities in the distant cave you must have been vacationing in for over a year. You’ve probably used or at least heard of Microsoft’s GitHub Copilot as a software developer. The crowdsourced code completion plugin has made waves throughout the global dev community since its launch in July 2021.
Then the free beta period ended, and developers had to pay a subscription fee. Unsurprisingly, many of these users turned to Copilot alternatives.
Our list of the best GitHub Copilot alternatives includes free and language-specific tools and paid services that charge a subscription fee. Before we compare and contrast them with GitHub Copilot, it’s worth going over the main features of the product Microsoft dubs “a first-of-its-kind AI pair programmer.”
GitHub Copilot is a code completion tool from GitHub and OpenAI. It employs OpenAI’s Codex, a transformer trained on billions of code lines on GitHub, to autogenerate code based on the current file’s contents and your cursor location. Copilot is compatible with popular code editors like Visual Studio Code, Visual Studio, Neovim, and JetBrains IDEs and supports languages like Python, JavaScript, TypeScript, Ruby, and Go.
According to GitHub and user reviews, Copilot can generate whole code lines, functions, tests, and documentation. All it needs is context and the behind-the-scenes work of developers who committed their code to GitHub, regardless of their software license.
When the Copilot beta ended, GitHub released the pricing for individual users. The subscription included a 60-day free trial, which would turn to $10/month or $100/year per user.
No free subscription
Free licenses are still available, but they’re now limited to OSS maintainers and students only.
No midline code completion
As noted previously, Copilot requires a great deal of context to produce any code. The more context you provide, the more accurate the results will be. However, Copilot will only offer you the following line, function, or whole block of code based on context and cursor location. You still have to type entire lines and correct the code generated instead of saving the keystrokes by letting the tool autocomplete as you type.
AI models can’t run locally
Do you like to code offline or need to keep your code local for compliance reasons? Then Copilot is not for you. The AI models cannot run locally.
[cta_btn url=”https://www.tabnine.com/pricing/landing” label=”Start a free trial”]
One of the first code completion tools on the market is Tabnine (previously known as Codota). The Tabnine code completion plugin supports all the most popular languages, libraries, and frameworks in your favorite IDEs. Tabnine’s AI models are only trained on permissive open source licensed code, so your code will always remain yours.
A unique feature of the Tabnine Pro subscription is training your own private AI model based on your code and getting personalized code completions that match your style and patterns. This way, you don’t need to rely on code written by anyone else but yourself in your repositories.
For teams and organizations, the ability to host and train your own AI models enables collaborative autocompletion across IDEs. It also adds to code security as you get to keep the codebase and AI model on your secure corporate servers.
It’s also worth noting that Tabnine requires a lot less context than Copilot to generate code for you. In fact, with Tabnine you get midline suggestions as you type rather than suggestions for the next line of code upon completing the previous one.
Pricing: A free account enables short code completion and Pro accounts start at $12/month per user. (There’s also a 90-day free trial available). Enterprise account pricing is available on quote. Tabnine Enterprise offers a secure coding environment for your development team. You can benefit from powerful AI code assistance for more productive and bug-free coding while keeping your company’s data safe and secure.
Developers and StackOverflow are like human resources managers and LinkedIn. We need our platforms and tools. Captain Stack is an open source VS Code plugin that’s a bit of both. Inspired by Copilot, Captain Stack is a code suggestion tool that uses Google instead of AI. It sends your search query to Google, retrieves StackOverflow and GitHub Gist answers, and autocompletes them.
Pricing: Free.
Another open source alternative to Copilot is GPT-Code-Clippy. According to the description, GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model (based on GPT-3, called GPT-Codex) that is fine-tuned on publicly available code from GitHub.
Similar to Captain Stack, GPT-CC is only available as a plugin for VS Code.
Pricing: Free.
Second Mate is another open source imitation of GitHub Copilot. It uses EleutherAI GPT-Neo-2.7B (via Huggingface Model Hub) for Emacs. It’s a much smaller model, so it will likely not be as effective as Copilot or other alternatives. On the other hand, you can run it on Emacs, and it’s free.
Pricing: Free.
IntelliCode is an experimental AI coding assistant trained on a subset of GitHub projects, a Microsoft product available for Visual Studio only. One of the more attractive features of IntelliCode is team completion. Team completion may prove beneficial for organizations with a Microsoft-based architecture and developers accustomed to Visual Studio in an age of remote working. However, if you’re looking for a cross-IDE solution that enables team autocompletion training, Tabnine supports this feature for all popular IDEs out there.
With Microsoft tempting developers through GitHub and Copilot, it was clear other tech giants would step in. In June 2022, Amazon launched its own AI pair programming tool named CodeWhisperer. CodeWhisperer was trained, according to Amazon, “on billions of lines of code drawn from open source repositories, internal Amazon repositories, API documentation, and forums.”
At the time of writing, CodeWhisperer is available in its preview version only upon signup and can be installed on any IDE that supports AWS IDE tools.
Pricing: Free (in preview)
Google Transformer-based hybrid semantic ML code completion — you can’t expect Google to stay silent with Amazon and Microsoft on the scene. So, as expected, Google released its code completion engine in July 2022. However, at the time of writing, it’s available only to developers working at Google itself.
If you’re a Vim user, you might want to look at YouCompleteMe, a free autocompletion library for your favorite code editor. YouCompleteMe has several completion engines built in and supports any protocol-compliant Language Server to work with practically any language.
Though free and flexible, expect the setup to be lengthy and complicated if you plan to code in more than one language.
Pricing: Free.
The last solution in our list is worthy of mention because it’s one of the more flexible and user-friendly solutions offered for free. Unfortunately, at the time of writing, Kite is unavailable for download and is not maintained.
Source: https://xkcd.com/2169/
Pricing: Free.
Machines aren’t coming for your job. They’re coming for the boring parts that make your wrists ache. AI code prediction and completion tools and services are here to stay. It’s only a matter of choosing the most suitable platform for your needs that will enable you to code faster and better.
Tabnine is the AI coding assistant that accelerates and simplifies software development while keeping your code private, secure, and compliant. Boost engineering velocity, code quality, and developer happiness by automating the coding workflow through AI tools customized to your team.
[cta_btn url=”https://www.tabnine.com/pricing/landing” label=”Start a free trial”]
It’s been an intense few months here at Tabnine, and we’ve rolled out a lot of new features and changes for our users, including new generation AI models and new serving modes.
The latest update is that we’re introducing a 14-day free trial for our Tabnine Pro plan .
Tabnine users who upgrade to Tabnine Pro can get access to all the new, advanced code completion features we’re offering for a period of 14 days, including access to our next-generation, context-sensitive AI models, which enable a whole new experience in terms of code completions:
Once you upgrade, you’ll be able to use Tabnine Pro at no charge for a period of 14 days. We’ll only start charging you once that 14-day period ends.
We’ve gotten incredible feedback so far from our dev community regarding the coding experience offered by Tabnine Pro, so we’re pretty confident you’ll want to continue using it once the trial is over.
That said, if you decide, for any reason, not to continue using Tabnine Pro, you can cancel it at any time during the 14-day period.
[cta_btn url=”https://www.tabnine.com/pricing” label=”Start a free trial”]