🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉
Skyvern automates browser-based workflows using LLMs and computer vision. It provides a simple API endpoint to fully automate manual workflows, replacing brittle or unreliable automation solutions.
Want to see more examples of Skyvern in action? Click here!
This quickstart guide will walk you through getting Skyvern up and running on your local machine.
Before you begin, make sure you have the following installed:
- Brew (if you're on a Mac)
- Poetry
brew install poetry
- Python 3.11
poetry env use 3.11
- PostgreSQL 14 (if you're on a Mac, setup script will install it for you if you have homebrew installed)
brew install postgresql
- Clone the repository and navigate to the root directory
- Run the setup script to install the necessary dependencies and setup your environment
./setup.sh
- Create the
.envfile by copying the.env.examplefile and fill in the necessary environment variables (such as your OpenAI API key, etc.)cp .env.example .env
- Start the server
./run.sh
- You can start sending requests to the server, but we built a simple UI to help you get started. To start the UI, run the following command:
./run_ui.sh
- Navigate to
http://localhost:8501in your browser to start using the UI
If you're looking to contribute to Skyvern, you'll need to install the pre-commit hooks to ensure code quality and consistency. You can do this by running the following command:
pre-commit installSkyvern was inspired by the Task-Driven autonomous agent design popularized by BabyAGI and AutoGPT -- with one major difference: we give Skyvern the ability to interact with websites using browser automation libraries like Playwright.
We love to see how Skyvern is being used in the wild. Here are some examples of how Skyvern is being used to automate workflows in the real world. Please open PRs to add your own examples!
Our focus is bringing stability to browser-based workflows. We leverage LLMs to create an AI Agent capable of interacting with websites like you or I would — all via a simple API call.
Traditional approaches required writing custom scripts for websites, often relying on DOM parsing and XPath-based interactions which would break whenever the website layouts changed.
Skyvern operates like a human — increasing reliability by not relying on fragile scripts, instead relying on computer vision to parse items in the viewport and interact with them the way a human would.
This approach gives us a few advantages:
- Skyvern can 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
- 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
- Skyvern is able to circumvent or navigate through many bot detection methods as many of them rely on allowing people to access the websites
- Skyvern leverages LLMs to reason through interactions to ensure 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!)
This is our planned roadmap for the next few months. If you have any suggestions or would like to see a feature added, please don't hesitate to reach out to us via email or discord.
- Open Source - Open Source Skyvern's core codebase
- [BETA] Workflow support - Allow support to chain multiple Skyvern calls together
- Improved context - Improve Skyvern's ability to understand content around interactable elements by introducing feeding relevant label context through the text prompt
- Cost Savings - Improve Skyvern's stability and reduce the cost of running Skyvern by optimizing the context tree passed into Skyvern
- Self-serve UI - Deprecate the Streamlit UI in favour of a React-based UI component that allows users to kick off new jobs in Skyvern
- Prompt Caching - Introduce a caching layer to the LLM calls to dramatically reduce the cost of running Skyvern (memorize past actions and repeat them!)
- Chrome Viewport streaming - Introduce a way to live-stream the Chrome viewport to the user's browser (as a part of the self-serve UI)
- Past Runs UI - Deprecate the Streamlit UI in favour of a React-based UI that allows you to visualize past runs and their results
- Integrate LLM Observability tools - Integrate LLM Observability tools to allow back-testing prompt changes with specific data sets + visualize the performance of Skyvern over time
- Integrate public datasets - Integrate Skyvern with public benchmark tests to track the quality our models over time
- Workflow UI Builder - Introduce a UI to allow users to build and analyze workflows visually
We welcome PRs and suggestions! Don't hesitate to open a PR/issue or to reach out to us via email or discord. Please have a look at our contribution guide and "Help Wanted" issues to get started!
By Default, Skyvern collects basic usage statistics to help us understand how Skyvern is being used. If you would like to opt-out of telemetry, please set the SKYVERN_TELEMETRY environment variable to false.
Skyvern's open source repository is supported via a managed cloud. All of the core logic powering Skyvern is available in this open source repository licensed under the AGPL-3.0 License, with the exception of anti-bot measures available in our managed cloud offering.
If you have any questions or concerns around licensing, please contact us and we would be happy to help.