dale(@daleverett):Today we’re launching WonderSearch (YC F26) Search millions of unstructured documents without pre-embedding the corpus. With comparable/better retrieval recall than embedding-based search. WonderSearch searches at query time: > No corpus-wide embedding step. > No vector index to maintain. > More compute only when needed. > Pay per search intead of embeddings you may never use. Go from raw data to useful answers in seconds. Link + FAQ below (+ free launch credits!) ↓

dale

@daleverett

co-founder @polygres (YC F’26) ➡️ by ➡️ backed by @ycombinator @fdotinc / twin @daltonmeon

Joined January 2020

4.2K Following 4K Followers

dale@daleverett

2026.09.28 15:09

Today we’re launching WonderSearch (YC F26) Search millions of unstructured documents without pre-embedding the corpus. With comparable/better retrieval recall than embedding-based search. WonderSearch searches at query time: > No corpus-wide embedding step. > No vector index to maintain. > More compute only when needed. > Pay per search intead of embeddings you may never use. Go from raw data to useful answers in seconds. Link + FAQ below (+ free launch credits!) ↓