Skyvern

Browser automation agent powered by the Skyvern SDK

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

Configure Skyvern in the root config.yaml under agents.skyvern:

agents:
  skyvern:
    active_model: gemini        # active model profile
    models:
      gemini:
        enable_openai_compatible: true
        model_id: gemini-3-flash-preview
        max_tokens: 16000
        temperature: 0.0
        supports_vision: true
        api_key: $OPENAI_COMPATIBLE_API_KEY
    browser:
      browser_id: local
      headless: false
    defaults:
      engine: skyvern_v2
      max_steps: 25
      timeout: 600
      max_screenshot_scrolls: 5
      include_action_history_in_verification: true
      max_consecutive_repeats: 3
      max_action_occurrences: 5

Store sensitive keys (e.g. OPENAI_COMPATIBLE_API_KEY, SKYVERN_API_KEY) in the repo root .env.

Engine Options

ENGINE	Description
skyvern_v1	Skyvern v1 engine
skyvern_v2	Skyvern v2 engine
openai-cua	OpenAI CUA engine
anthropic-cua	Anthropic CUA engine
ui-tars	UI-TARS engine

Browser Backends

browser_id	Description
local	Local browser
cdp	Connect to an external CDP browser (set CDP_ADDRESS)
lexmount	Lexmount cloud browser (set LEXMOUNT_BROWSER_MODE)
skyvern-cloud	Skyvern cloud browser

Common Parameters

Parameter	Description	Example
enable_openai_compatible	Enable OpenAI-compatible mode	true
model_id	LLM model name	gemini-3-flash-preview
api_key	LLM API key (use $ENV_VAR form)	$OPENAI_COMPATIBLE_API_KEY
base_url	LLM API base URL	$OPENAI_BASE_URL
max_tokens	Max output tokens	16000
temperature	Temperature	0.0
supports_vision	Model supports vision	true
request_timeout	LiteLLM per-request timeout (seconds)	600
execution_engine	Skyvern execution engine	skyvern_v2 (default)
headless	Headless mode for local browser	true / false
timeout	Task timeout (seconds)	600
max_steps	Max steps per task	25
max_screenshot_scrolls	Max scroll screenshots	5
include_action_history_in_verification	Include action history in verification	true
max_consecutive_repeats	Max consecutive repeats	3
max_action_occurrences	Max occurrences of one action	5

Renamed keys (legacy still honored)

The openai_compatible_* prefix on per-model config keys was dropped so Skyvern matches every other agent (model_id, api_key, base_url, max_tokens, temperature, supports_vision, request_timeout). The old names still work — you’ll see a one-shot DeprecationWarning per key, then the value is aliased onto the new key. The underlying env vars passed to the Skyvern subprocess (OPENAI_COMPATIBLE_*) are unchanged.

Why no browser_control?

Skyvern is a fully managed service: the decision of when to use DOM inspection versus visual grounding is made internally by the Skyvern execution engine (configurable via execution_engine). The benchmark only submits tasks via API and does not control the internal interaction strategy.

Usage Examples

Basic Run

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

Run All Tasks

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

Evaluation

# --model-id matches the model_id used at run time
bubench eval --agent skyvern --data LexBench-Browser --model-id gemini-3.1-pro-preview

Supported Benchmarks

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

Links

• Skyvern GitHub Repository