browsa 0.1.3

Official Python SDK for Browsa — anti-detect cloud browsers for AI agents (browsa.io)

browsa (Python)

Anti-detect browsers for AI agents — official Python SDK for browsa.io.

Install

pip install browsa

Zero dependencies. Pure stdlib. Single-file wheel.

Five-line hello world

from browsa import Client

c = Client(api_key="agt_live_...")
job = c.run_task(
    task="Go to news.ycombinator.com and return the top story title.",
    llm="claude-opus-4-7",
    llm_api_key="sk-ant-...",
)
print(job.final_result)
print("watch live:", job.live_url)

That runs a real Chromium fork (Phantom — our anti-detect browser) inside an isolated burner session, driven by browser-use + Claude Opus. The agent navigates, extracts, and returns. A live noVNC stream URL is available the moment the burner spawns.

Async

import asyncio
from browsa import AsyncClient

async def main():
    async with AsyncClient(api_key="agt_live_...") as c:
        job = await c.run_task(
            task="Scrape the top 5 products on producthunt.com today.",
            llm="claude-opus-4-7",
            llm_api_key="sk-ant-...",
            country="US",
        )
        print(job.final_result)

asyncio.run(main())

Webhooks

from browsa import webhooks

# In your receiver (Flask/FastAPI/whatever):
ok = webhooks.verify_signature(
    body=raw_request_body,
    header=request.headers["X-Agents-Signature"],
    secret=os.environ["BROWSA_WEBHOOK_SECRET"],  # hex-encoded
)
if not ok:
    return 401
# Trust the payload only after this point.

What you get

Capability	Notes
Sync + async clients	Client + AsyncClient, same surface
Real Job envelope	Typed dataclass + .raw escape hatch
Long-poll waits	wait_for_job(timeout=...) uses server-side ?wait=30
Webhook signature verify	HMAC-SHA256, constant-time compare, skew check
Canonical error envelope	AuthError, InvalidIDError, RateLimitError, etc.
X-Request-Id propagation	Every error carries the server's request id
Zero deps	Single wheel, audit-friendly, no transitive surface

Advanced

Long-running tasks with progress callback

def show(job):
    print(f"  step {job.step_count}/{job.progress_total}  status={job.status}")

job = c.run_task(
    task="Open-ended research: scrape arxiv for papers on test-time compute, return top 10 by citation.",
    llm="claude-opus-4-7",
    llm_api_key="sk-ant-...",
    max_steps=80,
    on_progress=show,
)

Interactive (input_required) tasks

If your task can pause for human input (captcha, decision point), watch for status input_required and respond:

job = c.create_task(task="...", llm="...", llm_api_key="...")
while not job.is_terminal:
    job = c.get_job(job.id, wait=30)
    if job.status == "input_required":
        answer = input(f"Agent asks: {job.input_question}\n> ")
        job = c.respond_to_job(job.id, answer)

JA3-spoofed sessions

Some sites fingerprint TLS handshake shape. Set a profile to spoof macOS Chrome:

job = c.run_task(
    task="Go to a TLS-fingerprint-fingerprinted site",
    llm="claude-opus-4-7", llm_api_key="sk-...",
    ja3_profile="macos_chrome_137",  # uses utls
)

Docs

• API reference: https://browsa.io/docs
• Source: https://github.com/mohasaaid/neout/tree/main/sdks/browsa-python
• Issues: https://github.com/mohasaaid/neout/issues

License

MIT.