skyvern
Browser automator
Automates browser-based workflows using LLMs and computer vision to replace brittle automation solutions.
Automate browser-based workflows with LLMs and Computer Vision
11k stars
70 watching
768 forks
Language: Python
last commit: almost 2 years agoapiautomationbrowserbrowser-automationcomputergptllmplaywrightpythonrpavisionworkflow
Related projects:
| Repository | Description | Stars |
|---|---|---|
 parisneo/lollms-webui | An all-encompassing tool providing a web interface to access and utilize various AI models for tasks such as text generation, image analysis, music generation, and more. | 4,394 |
 skypilot-org/skypilot | A framework for running AI and batch workloads on any infrastructure, offering unified execution, cost savings, and high GPU availability. | 6,905 |
 llmware-ai/llmware | A framework for building enterprise LLM-based applications using small, specialized models | 8,303 |
 seleniumhq/selenium | A platform for automating web browser interactions | 30,979 |
 scisharp/llamasharp | An efficient C#/.NET library for running Large Language Models (LLMs) on local devices | 2,750 |
 superagent-ai/superagent | An open-source AI framework and API for building intelligent applications | 5,391 |
 jopemachine/alfred-chromium-workflow | A Chromium-based browser workflow for Alfred 5 that provides features such as search, bookmark management, and autofill data retrieval. | 127 |
 langroid/langroid | A Python framework to build LLM-powered applications by setting up agents with optional components and having them collaboratively solve problems through message exchange | 2,795 |
 microsoft/playwright | A framework for automating web browsers with a single API to enable cross-browser testing and automation. | 67,755 |
 cvat-ai/cvat | An interactive video and image annotation tool for computer vision | 12,821 |
 automaapp/automa | An extension for automating browser tasks by creating a workflow of connected blocks. | 12,581 |
 cloudwu/skynet | A framework for building multi-user online games using the actor model. | 13,387 |
 teamcapybara/capybara | A tool for testing web applications by simulating user interactions. | 10,029 |
 oegedijk/explainerdashboard | A Python library for building interactive dashboards to explain machine learning models | 2,321 |
 salesforce/lavis | A library that provides pre-trained models and frameworks for multimodal vision-language intelligence tasks such as image captioning and visual question answering. | 10,058 |