> ## Documentation Index
> Fetch the complete documentation index at: https://hub.hcompany.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> H Platform has four products: the Agents API (managed computer-use agents, base URL https://agp.eu.hcompany.ai/api/v2 or https://agp.hcompany.ai/api/v2 for the US), the Models API (OpenAI-compatible Holo vision-language models at https://api.hcompany.ai/v1), HoloDesktop CLI (Holo on the user's own desktop), and HoloTab (a free no-code Chrome extension that runs Holo in the user's browser, with recordable routines and schedules).
> Authenticate with a bearer API key from the HAI_API_KEY environment variable. SDKs: `pip install hai-agents` (Python, `from hai_agents import Client`) and `npm install hai-agents` (TypeScript, `import { HaiAgentsClient } from "hai-agents"`). CLI: `hai`.
> Agents do work in a browser or on a desktop; describe the task as an imperative instruction. To run a task quickly, prefer the pre-built agent `h/web-surfer-flash`. Read results from the session's `latest_answer` after it reaches a terminal status.
> Sessions are the unit of work; wait for a terminal status (completed, failed, timed_out, interrupted) before reading the answer. Use webhooks or the `changes` long-poll endpoint to follow progress.

# Agents API

> Run Holo-powered computer-use agents that do work in a cloud browser or on a desktop: pre-built agents, custom agents, live sessions, skills, vaults.

export const YouTube = ({id, title}) => <iframe className="aspect-video w-full rounded-xl border-0" src={`https://www.youtube-nocookie.com/embed/${id}?rel=0&modestbranding=1`} title={title} loading="lazy" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowFullScreen />;

A **computer-use agent** sees a screen and decides what to click, type, and scroll. Use one when the work lives behind a user interface with no API. The Agents API runs these agents for you: describe the task, and H provisions a browser or desktop, runs a [Holo](https://hcompany.ai/newsroom/holo4)-powered agent on it, and streams progress and the result back through a session you can watch, steer, and stop.

Everything works from the SDKs, CLI, and REST API, and from the [platform](/agents-api/run-from-the-platform) with no code.

## Building blocks

| Concept | What it is |
| - | - |
| [Agent](/agents-api/agents/overview) | A reusable configuration: environments, model, skills, instructions. Use a [pre-built agent](/agents-api/agents/overview#pre-built-agents) or create your own. |
| [Environment](/agents-api/environments/overview) | What the agent sees and acts on: a cloud browser, or your own browser or desktop with [local control](/agents-api/local-control). |
| [Session](/agents-api/sessions/overview) | One run of an agent on a task, with a lifecycle you can steer. |
| [Skill](/agents-api/skills/overview) | An optional instruction fragment the agent loads when a task matches. |

## Run an agent

```python Python theme={"system"}
from hai_agents import Client

client = Client()
result = client.run_session(
    agent="h/web-surfer-flash",
    messages="Open Hacker News and list the top 3 stories with their URLs.",
)
print(result.answer)
```

Get a key and run this in any language: [Quickstart](/agents-api/quickstart).

## See it in action

The agent finds a vinyl on Amazon and adds it to the cart.

<Frame>
  <YouTube id="JFdSHV0p0dE" title="Computer-use Agents: Add to Cart" />
</Frame>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.