localdecide

ChenneyZhuang/laya-browser-agent on GitHub

Stars: 7
Forks: 2
Language: Python
License: Apache-2.0
Last push: 23 Sep 2026

Read from GitHub on 24 Sep 2026. Counts change daily.

How it uses Jev

sys.path.insert(0, str(ROOT))

FIXTURES = ROOT / "tests" / "fixtures"
API = "https://api.typesafe.ai/v1/systemone"
KEY = os.environ.get("TYPESAFE_API_KEY", "")
MODEL = "jev-latest"

from localdecide import build_element_table, table_to_questions  # noqa: E402


def observe(fixture: str) -> dict:
    request = json.dumps({"url": (FIXTURES / fixture).as_uri()})

View in examples/diagnostics/jev_edge_h2h.py

Open on GitHub

PrimitivesChoice Score Noul

Use casesReal-time control

Jev Ultrafast (Browser Use)

Browser Use's fast browser agent where Jev picks the operation and the DOM element in a single request; a small LLM is only invoked to write text when typing is required. Demoed on a Google Flights search.

browser-useOpen

19k starsFlight search 7.1 s

ProjectTyped tool dispatch+2

Laya-MLX

An independent MLX port of Laya for Apple Silicon, 13.4ms median for a short English decision and 7.4ms on the multilingual checkpoint, with a Snake demo that plays at up to 75 moves per second under 1GB of memory.

mizorewwwOpen

6.1k starsShort decision 13.4 ms P50Snake demo 75.4 moves/s

ToolReal-time control

Agent Desktop

Rust desktop automation that reads apps through the OS accessibility tree instead of pixels. Its jev-desktop skill takes a plain-language goal and has Jev pick one operation and one target element per turn, so the 150-element tree never enters the agent's context.

lahfirOpen

1.6k starsToken reduction 78-96%

ProjectTyped tool dispatch+1

Laya-CoreML

Core ML ports of all three Laya checkpoints for Apple Silicon, reaching 4.98ms P50 on the Neural Engine for a short multilingual decision, with a Snake demo sustaining about 50 decisions per second.