STROT compiles LLM instructions into locally run decision workflows

Amit Rath's open-source project puts a large model in the setup step and a small local model on the job, while its Pac-Man demo shows the limits of that split.

By · Published

Primary source: GitHub

Why it matters

STROT puts a large model in workflow setup and keeps repeated decisions local, which could reduce cost and latency for bounded tasks. Its own demo also shows why compilation and golden tests cannot replace evaluation on real, changing data.

STROT compiles LLM instructions into locally run decision workflows — Amit Rath's open-source project puts a large model in the setup step and a small local model on the job, while its Pac-Man demo shows the limits of that split.

Amit Rath's STROT uses a large language model to turn a developer's instructions into a Python artifact, then runs routine classification and routing decisions with a smaller model on local hardware. Rath, listed as the project's author and maintainer on PyPI, has now carried the idea from a 2025 research framework into an open-source tool developers can install and test.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.