RunLocalAI
server
Open source
free (Redis OSS) + Redis Cloud

Redis (vector search)

Vector search inside the same Redis you already run. HNSW + flat indices, hybrid filtering with FT.SEARCH. The pragmatic pick when you don't want to add another service to ops.

By Fredoline Eruo·Last verified May 6, 2026·65,000 GitHub stars

Overview

Vector search inside the same Redis you already run. HNSW + flat indices, hybrid filtering with FT.SEARCH. The pragmatic pick when you don't want to add another service to ops.

Stack & relationships

How Redis (vector search) relates to other entries in the catalog — recommended pairings, alternatives, dependencies, and edges to avoid. Each edge carries a one-line operator note from our editorial team.

Redis (vector search) ↔ ecosystem

Alternatives

  • Alternative to
    Qdrant

    Redis Vector is the right choice when you already run Redis for caching and want vector search without adding another service. Slower than purpose-built vector DBs at scale.

Pros

  • Already runs in your stack
  • Sub-ms latency
  • Hybrid with full-text out of the box

Cons

  • Memory-resident — RAM cost grows linearly
  • Less specialized than Qdrant/Milvus

Compatibility

Operating systems
macOS
Linux
Windows
Docker
GPU backends
n/a
LicenseOpen source · free (Redis OSS) + Redis Cloud

Get Redis (vector search)

Official site
https://redis.io/docs/latest/develop/interact/search-and-query/
GitHub
https://github.com/redis/redis

Frequently asked

Is Redis (vector search) free?

Redis (vector search) has a paid tier (free (Redis OSS) + Redis Cloud). Check the pricing page for current terms.

What operating systems does Redis (vector search) support?

Redis (vector search) supports macOS, Linux, Windows, Docker.

Which GPUs work with Redis (vector search)?

Redis (vector search) supports n/a. CPU-only inference is also possible but slow.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.