Document & semantic search
Keyword precision and semantic recall in one engine — with embeddings computed on-device.
Install GreyCat free For AI agents
The problem
Good search needs both keyword precision and semantic recall — yet most stacks bolt a vector DB and an external embedding API onto a keyword engine, multiplying cost, latency and data sent outside.
How GreyCat solves it
Hybrid in one engine
BM25 keyword and vector search combine in a single query.
On-device embeddings
Embeddings are computed in the engine — no external API call.
Stays in your deployment
Documents and the search index never leave your infrastructure.
66k
documents indexed
1.27M
searchable paragraphs
9
search modes
34
MCP tools
A European legal-research platform on GreyCat — all from a single binary.