Product Thumbnail

Skyvern

Open source AI agent to automate browser-based workflows

Open Source
SaaS
Artificial Intelligence
GitHub

Skyvern is an open source AI Agent that helps companies automate browser-based workflows. We help them replace brittle scripts with a simple API endpoint to automate tasks on hundreds of different websites.

Top comment

TL;DR: Skyvern helps companies automate browser based workflows using AI. We provide a simple API endpoint to fully automate manual workflows, replacing brittle or unreliable scripts. We’re open source — check out our repository (https://github.com/Skyvern-AI/Sk...). 🎉 We just launched Skyvern Cloud — check it at app.skyvern.com Here's what Skyvern helps companies with today: 📝 Filling out a job application form based on a resume / CV 🧾Downloading invoices on many different websites behind a logged-in portal 🏢 Filling out forms on government websites 🛍️ Automate purchasing products on e-commerce websites ☀️ Completing dynamic multi-step workflows ❓How does Skyvern work? Skyvern operates by being given a URL + goal-based prompt. Skyvern then takes actions on a website until it accomplishes the goal given to it. We use multi-modal LLMs under the hood to parse the viewport and interact with it the way a human would. This approach gives us a few advantages: 1. Skyvern can take a single prompt (ie “Download an invoice from the order history page”) and repeat it across a large number of similar websites. This would traditionally require one script per website — making tackling the long-tail of website interactions very challenging 2. Skyvern is able to operate on websites it’s never seen before, as it’s able to map visual elements to actions necessary to complete a workflow, without any customized code 3. Skyvern is resistant to website layout changes, as there are no pre-determined XPaths or other selectors our system is looking for while trying to navigate 4. We’re able to circumvent or navigate through many bot detection methods as many of them rely on looking for outlier behaviour 5. We rely on LLMs to reason through interactions to make sure we can cover complex situations. Examples include: - If you wanted to get an auto insurance quote from Geico, the answer to a common question “Were you eligible to drive at 18?” could be inferred from the driver receiving their license at age 16 - If you were doing competitor analysis, it’s understanding that an Arnold palmer 22 oz can at 7/11 is almost definitely the same product as a 23 oz can at Gopuff (even though the sizes are slightly different, which could be a rounding error!) 🤩 Curious to see how it works under the hood? We're open source! We’re open source for two big reasons: 1. It allows developers to be able to look at, understand, and dive deep into the Skyvern’s implementation details to (1) expand their capabilities by adding support for new functionality and (2) decode why they’re doing what they’re doing. 2. It allows security-minded enterprises to escape “security theater” and keep data on prem by self-hosting Skyvern. You can check out our repository here (https://github.com/Skyvern-AI/Sk...). We have over ⭐️5.3K Stars on Github ⭐️ 📞 Do you have any complex workflows that you’d love to automate? We’d love to chat! Shoot me an email at [email protected] and I'd be happy to help! 🎁 Launch offer We're giving everyone $5 of free credits to go and play around with Skyvern. Happy automating!!

Comment highlights

I was lucky to get the opportunity to chat with @suchintan_singh recently about Skyvern for the APIs You Won't Hate podcast. I love Skyvern's story, and I am wild about the idea of automating long, tedious, and ambiguous tasks using the tech that powers LLMs. Congrats on the launch, team - I'm a huge fan!

Excellent idea, great people and great execution. We are looking to eventually bake in Skyvern to execute done-for-you tasks within Tallyfy

Hey! Just stumbled upon this little gem called Skyvern. As a fellow AI enthusiast and startup co-founder, I've developed an eye for spotting promising tech and I must say - Skyvern certainly caught my attention. Automating tasks on the web? Count me in for loving what you're cooking up here! Their whole concept of replacing brittle scripts with an API endpoint is music to my ears. Any CPO dealing with hundreds of websites would certainly appreciate the efficiency boost that this could bring to the table. Not to mention the to-do list that just shuddered in relief somewhere out there in the universe! Keep up the epic work, team!

Congrats on the launch! 🚀 I can see this being really useful for interaction testing as a dev 😄

Can't wait to use this! A surprising amount of my work is repetitive browser tasks, I'd love to be able to automate most of them

We used Skyvern for critical retail browser automation workflows and the product has been great to work with!! Highly recommend the product, and fantastic customer support.

Congrats on the launch! They're the absolute best, got us up and running in a matter of hours 🚀

It is a great for automating browser workflows! The AI adapts seamlessly to new websites without pre-determined selectors. Excited to see Skyvern Cloud in action—this will streamline so many tasks. Great job!

Huuuge, congrats on your launch guys!🔥 Struggles of automating browser tasks, so this AI agent is a game-changer!

That sounds impressive, Skyvern! Automating browser-based workflows with AI is a game-changer. I'm particularly intrigued by your approach to handling dynamic multi-step workflows and your resistance to website layout changes. This could really streamline operations for many businesses. Could you share more about the typical setup time and integration process for companies adopting Skyvern Cloud?

This is a game changer for many industries and teams. Efficiency in mundane tasks will surely reduce costs and also improve productivity of the teams.

Congrats on the launch of Skyvern! The ability to automate browser tasks with AI is incredible. This is going to save so much time to for businesses. Great work!

Congratulations on the launch of Skyvern on Product Hunt! As a real user, I am excited to see an open-source AI agent that can automate browser-based workflows. This will definitely be a game-changer for companies looking to streamline their processes and improve efficiency. Looking forward to trying out Skyvern and seeing the impact it can make in the industry.

Skyvern’s automation capabilities sound impressive. How do you ensure the AI adapts to changes in website layouts or navigation structures? It would be interesting to know how this has impacted productivity for your users. Congrats on the launch, Suchintan!