Wyat

Decisions, made locally.

wyat.io · wyat-1-600m · Documentation

Wyat chooses between options your application defines. You provide a message and a set of candidates. A small local model returns the ID of one of them. It is built to perform well in French while staying strong in English. Nothing leaves your machine, and nothing runs until you act on the result.

Try it

No model required. The demo uses fixed scores to show the interface.

git clone https://github.com/teilomillet/wyat && cd wyat
uv run python examples/quickstart/main.py --demo
# Selected: cancel

Install

Python 3.12 or newer, with uv.

uv add wyat --extra inference   # PyTorch, CPU or CUDA

Use --extra mlx instead on Apple Silicon, and add --extra server to serve over HTTP. The core alone (uv add wyat) has no dependencies. The model, Wyat-1 600M, downloads on first use (about 1.5 GB) and every file is checked against pinned SHA-256 digests; uv run wyat download fetches it ahead of time. Inference itself never uses the network.

Use it

import wyat

model = wyat.load("teilomillet/wyat-1-600m")

decision = model.decide(wyat.Request(
    query="Choose the requested booking action.",
    context="Please cancel my booking.",
    candidates=[
        wyat.Candidate(id="create", text="Create a booking"),
        wyat.Candidate(id="cancel", text="Cancel the booking"),
    ],
))

decision.selected  # one of your IDs, such as "cancel"

Load once. Decide many times. The same request and result work in Python, JSONL, and HTTP:

uv run wyat decide teilomillet/wyat-1-600m < requests.jsonl > decisions.jsonl
uv run wyat serve  teilomillet/wyat-1-600m

Besides choosing an option, Wyat rates on an ordered scale (Request.score) and answers yes or no with a probability (Request.noul).

Documentation

Coding agents can start from llms.txt.

License

Code is licensed under Apache 2.0; see NOTICE. Model artifacts carry their own licenses. Contributions are welcome; see CONTRIBUTING.md.