# UC Berkeley's LEANN open-source vector index cuts RAG index storage sharply

published: 2026-10-28T04:05:39.127Z
topic: search
source: https://www.marktechpost.com/2026/10/27/leann-vector-index-mlsys-2026/
url: https://aiagentnews.io/stories/uc-berkeley-s-leann-open-source-vector-index-cuts-rag-index-storage-sharply

UC Berkeley has released LEANN, an open-source vector index that stores a pruned graph and recomputes embeddings at query time. According to MarkTechPost, it matches HNSW accuracy at 90% recall while using 4 GB instead of 188 GB, at the cost of slower, seconds-level search.

UC Berkeley's LEANN is an open-source vector index that keeps a pruned graph instead of full embeddings and recomputes embeddings when a query runs. MarkTechPost reports that it shrinks a 60-million-chunk RAG index from 201 GB to 6 GB.

In the comparison given in the article, LEANN matches HNSW accuracy at 90% recall using 4 GB where HNSW uses 188 GB. The trade-off is search latency, which the article describes as seconds-level.

## Why it matters if you build agents

Teams running large retrieval indexes for agents may be able to cut storage costs considerably with this approach.

Each query recomputes embeddings, so latency-sensitive agents will need to test whether seconds-level search is acceptable. Figures come from the article, so benchmark on your own corpus before switching indexes.