Run agents on your own machine

With local mode, the agent itself runs on your own machine. Client.local() returns a client with the same sessions API as the cloud.

Why local mode

Private. The agent and its tools run on your machine; only model calls go to H. With your own model server, nothing leaves it.
No startup wait. No cloud agent to start: a session begins working right away.
Faster tool calls. Each click, keystroke, and screenshot runs next to the agent, with no round trip through H’s cloud.

With local browser or desktop control, only the browser or desktop is yours and the agent runs on H’s platform. In local mode, the agent runs on your machine too.

Install the SDK

Install the SDK with the driver for the environment your agent uses: browser for a local browser, desktop for a local desktop.

Install

pip install "hai-agents[cli,browser]"

Run a session

Pass the agent spec inline. This one drives Chrome on your machine:

Python

from hai_agents import Client

agent = {
    "name": "local-web",
    "description": "Drives Chrome on this machine.",
    "environments": [{"id": "browser", "kind": "web", "host": "user_device"}],
}

with Client.local() as client:
    result = client.run_session(agent=agent, messages="Open example.com and tell me the page heading.")
    print(result.status, result.answer)

The first run downloads the local runtime, about 60 MB. Later runs reuse it.

Limits

	`Client()`	`Client.local()`
Environments	Cloud and local	Local browser (`{"kind": "web", "host": "user_device"}`) and local desktop (`{"kind": "desktop", "host": "user_device"}`)
Web search	Yes	No
Agents	Registered or inline	Inline, without `subagents`
API	The full Agents API	Sessions

Bring your own model

Point local mode at any OpenAI-compatible server, such as Holo4 served with vLLM or llama.cpp. Your H API key is never sent to it.

Python

from hai_agents import Client
from hai_agents_local.runtime import Inference

inference = Inference.self_hosted("http://localhost:8000/v1", model="holo4-35b-a3b")

with Client.local(inference=inference) as client:
    result = client.run_session(agent=agent, messages="Open example.com and tell me the page heading.")

Next steps

Drive your own browser

The Chrome a local browser drives, and how to bring your own.

Local inference

Serve Holo4 on your own hardware.

Custom tools

Give the agent functions from your own code.

Observe & steer

Watch a run, redirect it mid-task, and read the answer.

Get started

Concepts

Browser

Desktop

Integrations

Guides

Operate

Run agents on your own machine

Why local mode

Install the SDK

Run a session

Limits

Bring your own model

Next steps

Drive your own browser

Local inference

Custom tools

Observe & steer

​Why local mode

Install the SDK

Sign in

Run a session

​Limits

​Bring your own model

​Next steps

Drive your own browser

Local inference

Custom tools

Observe & steer

Why local mode

Limits

Bring your own model

Next steps