Esta página se muestra en inglés. Una traducción al español está en curso.
KnowledgeApr 2, 2026·2 min de lectura

LaVague — Natural Language Web Automation

Give a text objective, LaVague drives the browser to accomplish it. Large Action Model framework for web agents. 6.3K+ stars.

Introducción

LaVague is a Large Action Model (LAM) framework with 6,300+ GitHub stars for building AI web agents that automate browser interactions using natural language objectives. Instead of writing CSS selectors or XPath queries, you describe what you want to achieve and LaVague's agent navigates websites, clicks buttons, fills forms, and extracts information autonomously. It provides full observability into each step — generated actions, page observations, and decision reasoning — making it ideal for building reliable, debuggable web automation pipelines.

Works with: Selenium, OpenAI GPT-4, Anthropic Claude, any OpenAI-compatible API. Best for teams building web scraping agents, QA automation, or AI-powered web workflows. Setup time: under 3 minutes.


LaVague Architecture

Core Components

User Objective: "Book the cheapest flight from NYC to London"
    |
    +-- World Model (LLM)
    |     Understands the page and plans next action
    |
    +-- Action Engine
    |     Generates Selenium code to execute the action
    |
    +-- Selenium Driver
          Executes actions in the browser

How It Works

  1. Observe — The agent takes a screenshot and reads the page DOM
  2. Think — The World Model (LLM) decides the next action based on the objective
  3. Act — The Action Engine generates and executes Selenium code
  4. Repeat — Until the objective is achieved or max steps reached

Step-by-Step Observability

agent = WebAgent(WorldModel(), ActionEngine(driver))
agent.get("https://example.com")

# Enable detailed logging
for step in agent.run_step_by_step("Find pricing information"):
    print(f"Step {step.number}:")
    print(f"  Observation: {step.observation}")
    print(f"  Thought: {step.thought}")
    print(f"  Action: {step.action_code}")
    print(f"  Result: {step.result}")

Use Cases

Use Case Example
Web scraping "Extract all product prices from this catalog"
Form filling "Fill out this job application with my resume data"
QA testing "Test the checkout flow and verify the order total"
Research "Find the latest papers on RAG from arXiv"
Monitoring "Check if the deployment status page shows all green"

Multi-Step Workflows

# Chain multiple objectives
agent.get("https://shopping-site.com")
agent.run("Search for wireless headphones under $50")
agent.run("Sort by customer rating")
agent.run("Extract the top 5 results with names and prices")
results = agent.result

Configuration

from lavague.core import WorldModel

# Use Claude instead of GPT
world_model = WorldModel(
    model_name="anthropic/claude-sonnet-4-6",
    api_key="sk-ant-..."
)

# Headless mode for CI/CD
driver = SeleniumDriver(headless=True)

FAQ

Q: What is LaVague? A: LaVague is a Large Action Model framework with 6,300+ GitHub stars for building AI web agents that automate browser tasks using natural language objectives, with full step-by-step observability.

Q: How is LaVague different from Browser Use or Stagehand? A: LaVague focuses on objective-driven automation — you state what you want to achieve, not the individual steps. Browser Use is a Python agent framework. Stagehand provides three TypeScript primitives. LaVague emphasizes observability and debugging for production web automation.

Q: Is LaVague free? A: Yes, open-source under Apache-2.0. You bring your own LLM API keys.


🙏

Fuente y agradecimientos

Created by LaVague AI. Licensed under Apache-2.0.

LaVague — ⭐ 6,300+

Discusión

Inicia sesión para unirte a la discusión.
Aún no hay comentarios. Sé el primero en compartir tus ideas.

Activos relacionados