Holo is H Company’s Action Vision-Language Model (VLM) and Surfer-H is the agent that enacts it in the real world. Together, they provide a powerful, automated, yet optimized solution to interacting with web interfaces the way we do—setting a goal, taking decisions, re-thinking and re-assessing where needed, and, ultimately, fulfilling everyday tasks. Holo and Surfer-H have been designed and built to do everything from booking flights, to searching for recipes online, and more. The Surfer-H-CLI is the command-line interface for running and controlling the Surfer-H agent, allowing you to define tasks, connect to Holo models, and execute web interactions directly from your terminal.

​
Benefits

When combined, Holo with Surfer-H offer a number of key benefits:
  • Human-like interaction: Works with standard web UIs without needing special integrations.
  • Optimized for efficiency: Range of models and model sizes that balance performance and cost.
  • Goal-driven autonomy: Plans, executes, and re-evaluates actions to complete tasks reliably.
  • Open-source and extensible: Transparent, customizable, and community-driven.
  • Cross-platform flexibility: Deployable locally, with Docker, or in the cloud (AWS SageMaker).
  • Benchmark leadership: State-of-the-art performance on WebVoyager and multiple UI localization benchmarks.

​
Example use cases

The table below includes common Surfer-H use cases:
ExampleDescription
Travel bookingSearch, compare, and book flights or hotels.
Cooking inspirationFind and filter recipes by rating, reviews, or ingredients.
Online shoppingAdd items to cart, compare deals, and complete checkouts.
Research assistanceNavigate documentation, collect references, or extract structured info.
Automation testingSimulate user flows for QA without brittle scripts.