Skip to main content
Skyvern is a Python-based browser automation agent built on the Skyvern SDK. It supports multiple execution engines (skyvern_v1, skyvern_v2, openai-cua, anthropic-cua, ui-tars) and browser backends (local, cdp, lexmount, skyvern-cloud).

​
Installation

# Install core dependencies and register the bubench CLI
uv sync
The skyvern and browser-use extras conflict. Use a separate venv (default .venvs/skyvern for skyvern, and .venvs/browser_use for browser-use in config.yaml). bubench run will auto-create that venv and install the skyvern extra on first use.
Activate .venv (or use uv run bubench ...) before running bubench commands.

​
Configuration

Copy the example config, then edit it: 
cp configs/agents/skyvern/config.yaml.example configs/agents/skyvern/config.yaml
Edit configs/agents/skyvern/config.yaml: 
# LLM settings
ENABLE_OPENAI_COMPATIBLE: true
OPENAI_COMPATIBLE_MODEL_NAME: gemini-3-flash-preview
OPENAI_COMPATIBLE_MAX_TOKENS: 16000
OPENAI_COMPATIBLE_TEMPERATURE: 0.0
OPENAI_COMPATIBLE_SUPPORTS_VISION: true

# Engine
ENGINE: skyvern_v2

# Browser
BROWSER_ID: local
HEADLESS: false
LEXMOUNT_BROWSER_MODE: normal

# Runtime
MAX_STEPS: 25
TIMEOUT: 600
Store sensitive keys in the repo root .env, such as OPENAI_COMPATIBLE_API_KEY or SKYVERN_API_KEY.

​
Engine Options

ENGINEDescription
skyvern_v1Skyvern v1 engine
skyvern_v2Skyvern v2 engine
openai-cuaOpenAI CUA engine
anthropic-cuaAnthropic CUA engine
ui-tarsUI-TARS engine

​
Browser Backends

BROWSER_IDDescription
localLocal browser
cdpConnect to an external CDP browser (set CDP_ADDRESS)
lexmountLexmount cloud browser (set LEXMOUNT_BROWSER_MODE)
skyvern-cloudSkyvern cloud browser

​
Common Parameters

ParameterDescriptionExample
ENABLE_OPENAI_COMPATIBLEEnable OpenAI-compatible modetrue
OPENAI_COMPATIBLE_MODEL_NAMEModel namegemini-3-flash-preview
OPENAI_COMPATIBLE_MAX_TOKENSMax output tokens16000
OPENAI_COMPATIBLE_TEMPERATURETemperature0.0
OPENAI_COMPATIBLE_SUPPORTS_VISIONModel supports visiontrue
HEADLESSHeadless mode for local browsertrue / false
TIMEOUTTask timeout (seconds)600
MAX_STEPSMax steps per task25
MAX_SCREENSHOT_SCROLLSMax scroll screenshots5
INCLUDE_ACTION_HISTORY_IN_VERIFICATIONInclude action history in verificationtrue
MAX_CONSECUTIVE_REPEATSMax consecutive repeats3
MAX_ACTION_OCCURRENCESMax occurrences of one action5

​
Usage Examples

​
Basic Run

bubench run \
  --agent skyvern \
  --benchmark LexBench-Browser \
  --mode first_n \
  --count 3

​
Run All Tasks

bubench run \
  --agent skyvern \
  --benchmark LexBench-Browser \
  --mode all \
  --skip-completed

​
Evaluation

bubench eval --agent skyvern --benchmark LexBench-Browser

​
Supported Benchmarks

  • ✅ LexBench-Browser
  • ✅ Online-Mind2Web
  • ✅ BrowseComp