Skip to main content
Client.local() gives you the same sessions API as the cloud. Only model calls go to H, plus any cloud browser you use. With your own model server and your own browser or desktop, nothing does. Sessions start instantly, and each action runs next to the agent, with no network round trip. From the terminal, use holo --local. Where the agent loop runs is independent of what it drives: a cloud browser, your browser, or your desktop.
1

Install the SDK

Add the driver for your environment: browser or desktop.
Install
2

Sign in

Model calls go to H with your API key. Sign in once, or set HAI_API_KEY:
CLI
3

Run a session

Pass the agent spec inline:
Python
The first run downloads the local runtime, about 60 MB. Later runs reuse it.

Cloud vs local

Use your own model server

Run Holo4 on hardware you control. Your H API key is never sent to it, so you can skip Sign in and the cli extra, but cloud environments cannot run. The model server can run on any machine you can reach.
1

Serve Holo4

Start a Holo4 server with Local inference: vLLM on an NVIDIA GPU (base URL http://localhost:8000/v1) or llama.cpp on a Mac (http://localhost:8080/v1).
2

Point the runtime at it

Use the agent from Run a session, with its model set:
Python
With llama.cpp, use http://localhost:8080/v1. Without inference, Client.local() reads HAI_AGENT_RUNTIME_BASE_URL and HAI_AGENT_RUNTIME_MODEL instead.

Two model names

GPUs on another machine

No API key is sent to your server, so keep it private. Use an SSH tunnel and keep http://localhost:8000/v1:
SSH tunnel

Troubleshooting