Show HN: Distill and serve small models with frontier quality for half the cost

The lead

Hi HN, we built world-model-optimizer, an open-source tool for continually improve models specialized to agents. Today we are launching `wmo serve`, a tool to route repetitive tasks to distilled smaller models.

The significance

Agent traces you already capture are opportunities to get signal on how to make your model cheaper, faster, better. We continuously improve - your specialized model through distillation from open source models - model routing to frontier + custom models - token compaction to remove noise and save tokens Demo: https://www.

The context

v=2_m4Ze6mdko Pass in traces and an OpenRouter key, and wmo starts a local OpenAI-compatible endpoint to run with your model at a lower cost with equivalent quality

Where this fits in Signal Ledger

Related coverage from the Technology desk.

• Japan legend Miura, 59, scores first goal since 2022
• Cursor Bridge – Run Unlimited Claude Code on Your Cursor Subscription
• Teaching Kids Forth

The read

We continuously improve - your specialized model through distillation from open source models - model routing to frontier + custom models - token compaction to remove noise and save tokens Demo: https://www. Tinker continually trains as new traces arrive.