tzafon 2.17.0

The official Python library for the computer API

Tzafon Python SDK

The Tzafon Python SDK enables programmatic control of Chromium browsers and Linux desktop environments. Build automation workflows with full stealth capabilities, multi-tab management, and an OpenAI-compatible Chat Completions API.

Features

• Browser Automation: Control Chromium browsers with navigation, clicking, typing, scrolling, and screenshots
• Desktop Automation: Automate Linux desktop environments with GUI interactions
• Multi-Tab Support: Control multiple browser tabs within a single session
• Page Context API: Get detailed page state including viewport, scroll position, URL, and title
• Full Stealth: Built-in stealth mode for web automation
• Sync & Async: Both synchronous and asynchronous clients powered by httpx

Documentation

Full documentation available at docs.tzafon.ai. API reference in api.md.

Installation

pip install tzafon

Quick Start

Get your API key from tzafon.ai and set it as an environment variable:

export TZAFON_API_KEY=sk_your_api_key_here

Browser Automation

from tzafon import Computer

client = Computer()

with client.create(kind="browser") as computer:
    # Navigate to a webpage
    computer.navigate("https://wikipedia.org")
    computer.wait(2)

    # Take a screenshot
    result = computer.screenshot()
    url = computer.get_screenshot_url(result)
    print(f"Screenshot: {url}")

    # Interact with the page
    computer.click(400, 300)
    computer.type("Ada Lovelace")
    computer.hotkey("Return")

Desktop Automation

from tzafon import Computer

client = Computer()

with client.create(kind="desktop") as computer:
    computer.click(500, 300)
    computer.type("Hello Desktop")
    computer.hotkey("ctrl", "s")
    computer.screenshot()

Session Configuration

computer = client.create(
    kind="browser",                      # "browser" or "desktop"
    timeout_seconds=3600,                # Maximum session lifetime
    inactivity_timeout_seconds=120,      # Auto-terminate after idle
    display={"width": 1280, "height": 720, "scale": 1.0},
    context_id="my-session",             # Optional identifier
    auto_kill=True,                      # End session on inactivity
)

Available Actions

Navigation

• navigate(url) - Navigate to a URL (browser only)

Mouse

• click(x, y) - Click at coordinates
• double_click(x, y) - Double-click at coordinates
• right_click(x, y) - Right-click for context menus
• drag(from_x, from_y, to_x, to_y) - Drag between positions
• mouse_down(x, y) / mouse_up(x, y) - Press/release mouse button

Keyboard

• type(text) - Type text at cursor
• hotkey(*keys) - Send keyboard shortcuts (e.g., hotkey("ctrl", "c"))
• key_down(key) / key_up(key) - Press/release keys

Other

• scroll(dx, dy) - Scroll viewport
• screenshot() - Capture screen
• html() - Get page HTML content
• wait(seconds) - Pause execution
• set_viewport(width, height) - Change viewport size
• batch(actions) - Execute multiple actions in one API call

Page Context API

Get detailed page state with your actions:

result = computer.execute_action("screenshot", include_context=True)
context = result.page_context

print(f"URL: {context.url}")
print(f"Title: {context.title}")
print(f"Viewport: {context.viewport_width}x{context.viewport_height}")
print(f"Scroll position: ({context.scroll_x}, {context.scroll_y})")

Chat Completions API

OpenAI-compatible API for AI-powered workflows:

from openai import OpenAI

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

response = client.chat.completions.create(
    model="tzafon.northstar.cua.sft",  # Optimized for computer-use automation
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What should I click to search?"}
    ]
)

Available models:

• tzafon.sm-1 - Fast, lightweight model for general tasks
• tzafon.northstar.cua.sft - Optimized for browser/desktop automation

MCP Server

Enable AI assistants to interact with the API:

Basic Usage

import os
from tzafon import Computer

client = Computer(
    api_key=os.environ.get("TZAFON_API_KEY"),  # This is the default and can be omitted
)

# List existing sessions
computer_responses = client.computers.list()

We recommend using python-dotenv to add TZAFON_API_KEY="My API Key" to your .env file so that your API key is not stored in source control.

Async usage

Simply import AsyncComputer instead of Computer and use await with each API call:

import os
import asyncio
from tzafon import AsyncComputer

client = AsyncComputer(
    api_key=os.environ.get("TZAFON_API_KEY"),  # This is the default and can be omitted
)


async def main() -> None:
    computer_responses = await client.computers.list()


asyncio.run(main())

Functionality between the synchronous and asynchronous clients is otherwise identical.

With aiohttp

By default, the async client uses httpx for HTTP requests. However, for improved concurrency performance you may also use aiohttp as the HTTP backend.

You can enable this by installing aiohttp:

# install from PyPI
pip install tzafon[aiohttp]

Then you can enable it by instantiating the client with http_client=DefaultAioHttpClient():

import os
import asyncio
from tzafon import DefaultAioHttpClient
from tzafon import AsyncComputer


async def main() -> None:
    async with AsyncComputer(
        api_key=os.environ.get("TZAFON_API_KEY"),  # This is the default and can be omitted
        http_client=DefaultAioHttpClient(),
    ) as client:
        computer_responses = await client.computers.list()


asyncio.run(main())

Using types

Nested request parameters are TypedDicts. Responses are Pydantic models which also provide helper methods for things like:

• Serializing back into JSON, model.to_json()
• Converting to a dictionary, model.to_dict()

Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set python.analysis.typeCheckingMode to basic.

Nested params

Nested parameters are dictionaries, typed using TypedDict, for example:

from tzafon import Computer

client = Computer()

computer_response = client.computers.create(
    display={},
)
print(computer_response.display)

Handling errors

When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of tzafon.APIConnectionError is raised.

When the API returns a non-success status code (that is, 4xx or 5xx response), a subclass of tzafon.APIStatusError is raised, containing status_code and response properties.

All errors inherit from tzafon.APIError.

import tzafon
from tzafon import Computer

client = Computer()

try:
    client.computers.list()
except tzafon.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except tzafon.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except tzafon.APIStatusError as e:
    print("Another non-200-range status code was received")
    print(e.status_code)
    print(e.response)

Error codes are as follows:

Status Code	Error Type
400	BadRequestError
401	AuthenticationError
403	PermissionDeniedError
404	NotFoundError
422	UnprocessableEntityError
429	RateLimitError
>=500	InternalServerError
N/A	APIConnectionError

Retries

Certain errors are automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors are all retried by default.

You can use the max_retries option to configure or disable retry settings:

from tzafon import Computer

# Configure the default for all requests:
client = Computer(
    # default is 2
    max_retries=0,
)

# Or, configure per-request:
client.with_options(max_retries=5).computers.list()

Timeouts

By default requests time out after 1 minute. You can configure this with a timeout option, which accepts a float or an httpx.Timeout object:

from tzafon import Computer

# Configure the default for all requests:
client = Computer(
    # 20 seconds (default is 1 minute)
    timeout=20.0,
)

# More granular control:
client = Computer(
    timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
)

# Override per-request:
client.with_options(timeout=5.0).computers.list()

On timeout, an APITimeoutError is thrown.

Note that requests that time out are retried twice by default.

Advanced

Logging

We use the standard library logging module.

You can enable logging by setting the environment variable COMPUTER_LOG to info.

$ export COMPUTER_LOG=info

Or to debug for more verbose logging.

How to tell whether None means null or missing

In an API response, a field may be explicitly null, or missing entirely; in either case, its value is None in this library. You can differentiate the two cases with .model_fields_set:

if response.my_field is None:
  if 'my_field' not in response.model_fields_set:
    print('Got json like {}, without a "my_field" key present at all.')
  else:
    print('Got json like {"my_field": null}.')

Accessing raw response data (e.g. headers)

The "raw" Response object can be accessed by prefixing .with_raw_response. to any HTTP method call, e.g.,

from tzafon import Computer

client = Computer()
response = client.computers.with_raw_response.list()
print(response.headers.get('X-My-Header'))

computer = response.parse()  # get the object that `computers.list()` would have returned
print(computer)

These methods return an APIResponse object.

The async client returns an AsyncAPIResponse with the same structure, the only difference being awaitable methods for reading the response content.

.with_streaming_response

The above interface eagerly reads the full response body when you make the request, which may not always be what you want.

To stream the response body, use .with_streaming_response instead, which requires a context manager and only reads the response body once you call .read(), .text(), .json(), .iter_bytes(), .iter_text(), .iter_lines() or .parse(). In the async client, these are async methods.

with client.computers.with_streaming_response.list() as response:
    print(response.headers.get("X-My-Header"))

    for line in response.iter_lines():
        print(line)

The context manager is required so that the response will reliably be closed.

Making custom/undocumented requests

This library is typed for convenient access to the documented API.

If you need to access undocumented endpoints, params, or response properties, the library can still be used.

Undocumented endpoints

To make requests to undocumented endpoints, you can make requests using client.get, client.post, and other http verbs. Options on the client will be respected (such as retries) when making this request.

import httpx

response = client.post(
    "/foo",
    cast_to=httpx.Response,
    body={"my_param": True},
)

print(response.headers.get("x-foo"))

Undocumented request params

If you want to explicitly send an extra param, you can do so with the extra_query, extra_body, and extra_headers request options.

Undocumented response properties

To access undocumented response properties, you can access the extra fields like response.unknown_prop. You can also get all the extra fields on the Pydantic model as a dict with response.model_extra.

Configuring the HTTP client

You can directly override the httpx client to customize it for your use case, including:

• Support for proxies
• Custom transports
• Additional advanced functionality

import httpx
from tzafon import Computer, DefaultHttpxClient

client = Computer(
    # Or use the `COMPUTER_BASE_URL` env var
    base_url="http://my.test.server.example.com:8083",
    http_client=DefaultHttpxClient(
        proxy="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

You can also customize the client on a per-request basis by using with_options():

client.with_options(http_client=DefaultHttpxClient(...))

Managing HTTP resources

By default the library closes underlying HTTP connections whenever the client is garbage collected. You can manually close the client using the .close() method if desired, or with a context manager that closes when exiting.

from tzafon import Computer

with Computer() as client:
  # make requests here
  ...

# HTTP client is now closed

Versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

1. Changes that only affect static types, without breaking runtime behavior.
2. Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
3. Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

Determining the installed version

If you've upgraded to the latest version but aren't seeing any new features you were expecting then your python environment is likely still using an older version.

You can determine the version that is being used at runtime with:

import tzafon
print(tzafon.__version__)

Requirements

Python 3.9 or higher.

Contributing

See the contributing documentation.