Open-Source Tool Routes Agent Tasks to Cheaper Distilled AI Models

A team has released "world-model-optimizer" (wmo), an open-source tool that routes repetitive AI agent tasks to smaller models trained via distillation from open-source frontier models, reducing costs while maintaining comparable output quality. The tool launches a local OpenAI-compatible endpoint and uses a router to decide which tasks go to the frontier model and which to the cheaper distilled model. It requires agent traces and an OpenRouter key to operate, and a hosted solution is also available.

Full text

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. 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.youtube.com/watch?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. Behind the scenes a router decides which tasks should go to the frontier versus your model. Tinker continually trains as new traces arrive. We also offer a hosted solution for anyone that just wants a frontier quality endpoint with self-improvement over time at a 40%+ lower cost. Sign up for the waitlist at https://experientiallabs.ai and give the repo a star!

🔥 Hot right now

Open-Source Tool Routes Agent Tasks to Cheaper Distilled AI Models

Comments

Comments

You're all caught up

Scroll like on TikTok