[05] Retrieval/ What it knows

Retrieval for AI agents

Your own corpus, made searchable.

6 options tracked · 4 open source · 4 self-hostable · optional

· All 6 options/ Compare
OptionWhat it doesLicenceSelf-host
pgvectorVector search inside the Postgres you already run.Open sourceYes
QdrantRust vector database with strong payload filtering, self-host or cloud.Open sourceYes
PineconeFully managed vector database. No index to operate.ProprietaryNo
ChromaEmbedded vector store that runs in-process. Ideal first index.Open sourceYes
turbopufferVector and full-text search on object storage — very cheap at rest.ProprietaryNo
LanceDBEmbedded multimodal store backed by the Lance columnar format.Open sourceYes
· Head to head/ 15 comparisons
· Common questions/ FAQ

What is the retrieval layer of an AI agent?

Your own corpus, made searchable. It is optional; plenty of working agents skip it.

How many retrieval options are there?

This registry tracks 6. 4 are open source and 4 can run on your own infrastructure.

Which retrieval option should I choose?

It depends on constraints rather than preference: whether you must self-host, whether the budget allows a hosted service, and which language your team writes. Describe what you are building and the advisor fills this layer along with the other 9.

· The other 9 layers/ Keep going
· For agents/ This page, machine-readable

Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.

curl -s -H "Accept: text/markdown" https://newagent.build/layers/retrieval