⬢github Python · 44 ★ +40 since we first saw it · pushed 1 d ago · MIT
strot-ai/Project-STROT
STROT (arXiv:2505.01636): compile-time LLM code synthesis with deterministic, self-routing NLU runtimes. PyPI: strot-ai
STROT is a Python library that uses an LLM once at 'compile time' to turn your intent plus sample data into a frozen, self-contained decision model. At runtime it classifies, scores, routes, or answers typed questions about records on your own CPU hardware with confidence scores and zero per-record LLM cost, abstaining on low-confidence cases.
Why now: It was just showcased on Hacker News ('Show HN') with benchmarks claiming big accuracy gains and zero marginal cost, which has drawn attention.
Who it is for: Developers who need bulk text classification, routing, or scoring without paying per-record LLM API calls.
Stars over our 327 snapshots: 4 to 44, since 3 d ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/strot-ai/Project-STROT