The Replit Team

Last week, we launched Replit Agent, our AI system that can create and deploy applications. Now, with only a few sentences and a few minutes, you can take an application from idea to deployment.

You can think about the Agent like a pair programmer. It configures your development environment, installs dependencies, and executes code. From your laptop or the Replit mobile app, the Agent is changing how our users build software.

If you'd like to learn more, we've compiled some of our favorite examples, tutorials, and articles on the agent so far. 

Introducing Replit Agent

Amjad Masad

Ever since the LOGO programming language educators have been using Turtle Graphics to demonstrate the power of programming to their students while making it fun and interesting.[](preview end)

In fact, my first real programming experience was when I was 6 years old learning LOGO at school. I learned how to program the turtle to draw a square and a triangle which I then put together to create a house. However, I was frustrated that I had to keep repeating the code to create a village made from multiple houses -- and that's how discovered loops! It's a natural way for children to learn programming. Here is an example turtle graphic house in repl.it :)



So far, we've been focused on what we think was largely missing from the web: running programs that typically require installing a compiler or an interpreter on your computer. However, now that we've built tools for teachers to bring programming to their classroom, many want to use turtle graphics as part of their cirriculum. And that's why we're excited to introduce Turtle Graphics support for Python.

To get started just select Python (with Turtle) from the list of languages, import the turtle module and start drawing!

Introducing Turtle Graphics For Python

It's no secret we're big fans of REPLs. We believe that immediate access to the programming environment accelerates learning and is generally more productive. REPLs cut out the middleman -- no need to build UIs or scripts for every possible action you might want to take -- just talk to the interpreter directly.[](preview end)

In every medium-to-large project we embark on we include a repl.sh script that starts out a REPL in the context of the project. This includes preloaded libraries, custom commands, and a database connection when it makes sense. You can interact with the database, use utility functions, and inspect the environment in whatever way you find useful.



This is especially easy in NodeJS; the module that makes up the REPL that ships with it is made into a stand-alone module repl. Once you require('repl') you'll be able to supply it with a custom eval function which you can then use to process the and parse the code in whatever way you find useful before calling a callback with a return value.

We love using async/await so we process top-level awaits with babel in the REPL to make it very easy to add, update, or delete from the development database. In the above gif you can see how we can test and iterate on our notifications page by creating notifications from the REPL and see it update instantly!

Every Project Should Have Its Own REPL

Faris Masad

Autocomplete plays a big role in how we use software, imagine a world where you have to type full search terms without predictions into google search, ugh, the savagery! Many developers employ this technology when writing code in order to increase their productivity. So we decided to implement this feature to help you become the power user you want to be.[](preview end)

BEHOLD! Note: if you're not a fan of autocomplete you can always turn it off from the preferences menu (⋮) at the top left of your editor.

We've also been getting many requests to enable renaming the repl from the workspace. Now, after you hit save, you can click at the top to change the name of your repl. Soon, we'll add a way to add tags without having to go to the repls page so you can organize and easily search for your repls.



Autocomplete Your Code with Replit

In this age of containers it's much easier to run arbitrary code in the cloud. The harder parts are scaling the service, making it reliable, and —as in this case— creating cool and useful experiences. When we looked at existing Swift REPL implementations on the web we found that none delivered a stateful and interactive environment. Just an editor with a run button.[](preview end)

As for us, as much as possible, we try to create an environment similar to the original inspiration for our website: DrScheme (now DrRacket).





Introducing Replit Agent

Introducing Turtle Graphics For Python

Every Project Should Have Its Own REPL

Autocomplete Your Code with Replit

A Swift REPL