LaVague
Large Action Models framework to build AI Web Agents
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for LaVague, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
LaVague is an open-source framework designed to develop AI Web Agents using Large Action Models. These agents can automate complex web interactions by interpreting natural language commands and executing tasks such as web navigation, data extraction, and form filling. By leveraging components like the World Model and Action Engine, LaVague simplifies the process of building and deploying AI agents that can perform a wide range of web-based tasks efficiently.
Key features and capabilities
- Open-source framework, Natural Language Processing (NLP) capabilities, Integration with Selenium and Playwright, Customizable and extensible, Supports local and cloud-based models
Use cases
- Web quality assurance (WebQA), Process automation (e.g., data entry, navigation), Information retrieval from SaaS applications, Automated form filling, Job application automation