skyvern
21,342Automate browser-based workflows with LLMs and computer vision.
PreventionPost-generationGraduated HITLStableTier 2AEnvironment
Maturity tier details
Computed tier: 2A(raw score 4.73). Effective tier: 2A.
Facets:documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_commit=2stars=1.73
Source of truth:pipeline/maturity/score.py
Description
Skyvern automates browser workflows using LLMs plus computer vision. Browser-use supervision primitives include selector-robust DOM grounding, screenshot reasoning, and structured action plans. Positioned as a business-process-automation layer on top of browser agents.
Why it's included
Browser-agent w/ CV-grounding cell. Differentiated from browser-use (DOM-only) by treating screenshots as primary.
Addresses failure modes
- Scope creep — Actions outside declared task boundary.
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
Techniques
cv-grounded-actionsstructured-plansselector-robustness