GoKawiilWorld Model Optimizer
wmo optimize turns collected agent traces into smaller open-source models using the Tinker API, with optional closed-loop simulation training. wmo serve exposes an endpoint that routes requests between frontier and smaller models; on RouterBench, it maintains frontier quality at 27% lower cost. Rerun the pipeline as new traces arrive to continually improve a model you own.
🌐 Platform | 📚 Docs | Discord
Getting started
1. Register your providers.
pip install world-model-optimizer wmo providers set
That verifies the provider and then offers to register its models as routing candidates in .wmo/pool.toml , the roster everything below chooses from. It searches the provider's own catalog (OpenRouter's 338 published models included) and asks only for what that backend needs. Re-run it to add another provider's models beside the ones already registered.
2. Tune a router on your OTel traces.
wmo build --file traces.jsonl --name my-model # Score every registered model on held-out tasks from your traces wmo optimize route sweep my-model --traces traces.otel.jsonl # Deterministically reserve 30% for reporting and fit on the other 70% wmo optimize route fit matrix.json --kind knn \ --out .wmo/models/my-model/policy.json
3. Serve it.
... continue reading