Skyvern
Automates browser-based workflows using computer vision and LLMs to understand and interact with websites, even ones it hasn't seen before.
- Actively maintained
Overview
Skyvern uses a vision-based approach rather than relying on brittle DOM selectors or site-specific scripts: it looks at a page the way a person would, and can generalize to websites it hasn't been configured for ahead of time. It's positioned as a workflow-automation platform (with a UI for defining and monitoring runs) more than a raw library.
Skyvern is a fit for teams automating browser workflows across many different, changing, or unfamiliar sites where a vision-first approach is more resilient than DOM-based automation like browser-use (also in this catalog). Note it's licensed under AGPL-3.0, a stronger copyleft license than most projects in this catalog.
- Categories
- AI Agents & Agent Tools
- Languages
- Python, TypeScript
- License
- AGPL-3.0
Related Projects
browser-use
MITA library that lets AI agents control a real web browser -- clicking, typing, navigating and reading pages -- to complete tasks that require the open web.
Actively maintained
- AI Agents & Agent Tools
LangGraph
MITBuild resilient, stateful agents as graphs -- explicit nodes and edges for control flow, rather than an implicit agent loop, for reliable long-running or multi-step workflows.
Actively maintained
- AI Agents & Agent Tools
Composio
MITPowers 1000+ toolkits, tool search, context management and authentication so AI agents can actually take action, not just plan it.
Actively maintained
- AI Agents & Agent Tools
Letta
Apache-2.0A platform for building stateful agents with advanced memory that learns and self-improves over time, rather than resetting between conversations.
Actively maintained
- AI Agents & Agent Tools
Spotted an error? Suggest an edit on GitHub.