browser-use with an uncensored model

To run browser-use with an uncensored model, give its ChatOpenAI class a base URL and an abliterated model id, then hand it a local Chrome.

Updated November 18, 2026By unrestrictedaiagent
run.pyPython
import os
from browser_use import Agent, Browser, ChatOpenAI

agent = Agent(
    "Open http://localhost:3000, my own app, and list every page that shows an error.",
    llm=ChatOpenAI(
        "kimi-k3.1-pro-uncensored",
        base_url="https://api.silkcompute.com",
        api_key=os.environ["SILK_API_KEY"],
    ),
    browser=Browser("chromium"),
)
print(agent.run_sync().final_result())
OpenAI format
ChatOpenAI(base_url=)
Anthropic format
Not documented
Tool calling
Custom tools
Streaming
Not documented
Browser use
Local or cloud Chrome
Memory
Not documented

Labels link to browser-use's own docs, read November 18, 2026. Compare all 11

Point the agent only at systems, files and accounts you own or are allowed to test.

Deploy it

3 steps, with Kimi K3.1 Pro.

  1. 01

    Install an exact version. The README asks for an exact pin, because releases can break APIs.

    Terminal
    pip install "browser-use==1.0.6"
    export SILK_API_KEY=...
  2. 02

    Use ChatOpenAI with a base URL. Browser("chromium") opens a fresh local Chrome with a temporary profile.

    See run.py above
  3. 03

    Keep it on your own sites. Pass passwords as sensitive_data. The README warns it is not a sandbox.

    Terminal
    python run.py

Which model

The config uses the Silk Compute base URL, which serves both models with a 1,048,576-token context.

Sources

More frameworks