🌾 winnow — live demo

Budget-aware context compression for RAG & agents. Paste a context, set a token budget, and watch winnow keep the highest-signal chunks. This runs the real Python library in your browser via Pyodide — no server, no API keys.

booting Python runtime…
orig tokens
kept tokens
reduction
chunks kept

winnow scores each chunk with BM25 relevance to the query, then selects with Maximal Marginal Relevance under the token budget — keeping relevant chunks while pruning near-duplicates. Kept chunks are highlighted; dropped chunks are dimmed. The Python running here is fetched verbatim from src/winnow.