How Lightcone Works

Northstar is a vision-language model that operates computers. It takes a screenshot as input, decides the next action (click, type, scroll, navigate), and outputs structured coordinates. Lightcone provides the API to use Northstar and the cloud environments it operates in.

Architecture

┌──────────────────────────────────────────────────────────┐
│                      Your Code                           │
│                                                          │
│  ┌──────────────┐  ┌──────────────┐  ┌───────────────┐  │
│  │    Tasks     │  │ Responses API│  │  Computers    │  │
│  │  (managed)   │  │    (CUA)     │  │  (low-level)  │  │
│  └──────┬───────┘  └──────┬───────┘  └───────┬───────┘  │
└─────────┼─────────────────┼──────────────────┼───────────┘
          │                 │                  │
          ▼                 ▼                  ▼
┌──────────────────────────────────────────────────────────┐
│                   Lightcone API                          │
│                  api.tzafon.ai                           │
├──────────────────────────────────────────────────────────┤
│                                                          │
│  ┌─────────────────────────────────────────────────┐     │
│  │               Northstar CUA Fast                │     │
│  │   screenshot in → structured action out          │     │
│  └─────────────────────────────────────────────────┘     │
│                                                          │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐      │
│  │   Desktop   │  │   Desktop   │  │   Browser   │ ...  │
│  │ environment │  │ environment │  │ environment │      │
│  └─────────────┘  └─────────────┘  └─────────────┘      │
│                                                          │
│         Isolated containers · Lightcone OS               │
└──────────────────────────────────────────────────────────┘

Three ways to use Northstar

1. Tasks — fully managed

You describe what needs to be done. Northstar operates a computer from start to finish — opening apps, navigating, typing, reading the screen, making decisions.

for event in client.agent.tasks.start_stream(
    instruction="Open LibreOffice Calc, create a budget spreadsheet with categories for rent, food, and transport",
    kind="desktop",
):
    print(event)

Best for: work that’s easy to describe but tedious to script — filling forms, navigating multi-app workflows, research, data collection.

Learn more →

2. Responses API — build your own loop

You build a computer-use loop: Northstar looks at a screenshot, tells you what action to perform, you execute it, and feed back the new screenshot. You control the loop and can inject custom logic between steps.

response = client.responses.create(
    model="tzafon.northstar-cua-fast",
    input="Open the terminal and check disk usage",
    tools=[{"type": "computer_use", "environment": "desktop"}],
)
# Execute the action, screenshot, send back, repeat

Best for: custom workflows where you need to validate results, branch on conditions, or integrate with other systems between steps.

Learn more →

3. Computers API — direct control (no model)

You send individual actions to a cloud computer: click, type, navigate, screenshot, shell commands. No model involved — you decide what to do at every step.

with client.computer.create(kind="desktop") as computer:
    client.computers.exec.sync(computer.id, command="firefox https://example.com &")
    computer.wait(3)
    computer.click(400, 300)
    computer.type("hello")
    result = computer.screenshot()

Best for: programmatic automation, testing, and any workflow where you know exactly what steps to take.

Learn more →

Models

Model	Purpose	Training
tzafon.northstar-cua-fast	Computer use — sees screenshots, outputs GUI actions	GUI reinforcement learning
tzafon.northstar-cua-fast-1.2	Computer use — sees screenshots, outputs GUI actions	GUI reinforcement learning
tzafon.sm-1	Low-level Rust programming	—

Northstar CUA Fast is optimized for speed and cost ($1/M input, $5/M output). It recovers from mistakes, generalizes across desktop environments, and is competitive with open-source models at twice its size.

Both models are available through the Responses API and Chat Completions API. Tasks use northstar-cua-fast by default.

Coordinate system

Northstar outputs GUI actions in a normalized 0–999 coordinate grid — (0,0) is the top-left of the screen, (999,999) is the bottom-right. Coordinates always come back in this 0–999 space; your code converts them to pixels using int(coord / 1000 * display_dim) before passing to click() or other methods.

See Coordinates for the full guide, including scaling formulas, visual examples, and which API to use.

OpenAI-compatible API

Already using the OpenAI SDK? Northstar works as a drop-in — just change the base URL and model name:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tzafon.ai/v1",
    api_key="sk_your_api_key_here",
)

response = client.chat.completions.create(
    model="tzafon.northstar-cua-fast",
    messages=[{"role": "user", "content": "What is reinforcement learning?"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.tzafon.ai/v1",
  apiKey: "sk_your_api_key_here",
});

const response = await client.chat.completions.create({
  model: "tzafon.northstar-cua-fast",
  messages: [{ role: "user", content: "What is reinforcement learning?" }],
});

Streaming, tool calling, and structured outputs are all supported. See Chat Completions for the full reference.

Environments

When Northstar operates a computer, it runs inside an isolated cloud environment powered by Lightcone OS — a minimal desktop runtime optimized for AI operation. You can choose:

• Desktop (kind: "desktop") — full Linux desktop. Northstar can use any native application.
• Browser (kind: "browser") — Chromium in the foreground, with stealth mode and proxy support for web-focused tasks.

Environments are fully isolated from each other — separate filesystem, network stack, and display. They spin up in seconds and are destroyed when you’re done.

Next steps

• Quickstart — get Northstar running a task in 5 minutes
• Tasks — the simplest way to use Northstar
• Responses API — build your own computer-use loop
• Integrations — connect to LangChain, Playwright, and more