There’s a simpler way to ground your agents.

Or request access to Antfly Cloud

The retrieval pipeline with zero pipes.

Chunking, embedding, indexing, reranking: it all happens inside the engine as data arrives. There’s nothing to wire together and nothing to keep tuned.

Read the quickstart →

terminal
# Install and start a local single-node engine, free
curl -fsSL https://releases.antfly.io/antfly/latest/install.sh | sh
antfly standalone

Bring whatever data you have.

See how it fits your stack →

On top

Antfly sits on your Postgres, your buckets, your file systems, your docs. Nothing to migrate, nothing to replace.

Any shape

PDFs, screenshots, tables, audio: every context layer becomes food for the retrieval engine.

Unified API

Vector, keyword, and graph search are indexes inside one database, fused in a single query plan. The inference that chunks, embeds, and reranks runs in there too. That’s where the pipes went.

Private

None of that inference leaves your infrastructure. No third-party API ever sees your data.

Built-in models

Retrieval needs a model at every step: embeddings when documents arrive, a reranker when queries run, an extractor to build the graph. Antfly ships them inside the engine, so there’s nothing to deploy and nothing to call out to.

Explore models →

Built on Antfly

Meet the builders →

Run it yourself, or let us.

Or request access to Antfly Cloud

re·triev·al

getting back something that was lost, saved or stored.