cd /news/ai-infrastructure/run-redisearch-vector-sets-redisjson… · home › topics › ai-infrastructure › article
[ARTICLE · art-170926] src=redis.io ↗ pub= topic=ai-infrastructure verified=true sentiment=↑ positive

Run RediSearch, vector sets, & RedisJSON natively on Windows with Memurai

Memurai for Redis 8 is now generally available, bringing Redis 8.2 capabilities to Windows developers without Docker, WSL, or a separate Linux environment, according to Redis and its official Windows partner Memurai. The release adds RediSearch for full-text, structured, and vector similarity search, RedisJSON for native JSON field-level reads and updates, and vector sets, a Redis 8 data type built for vector similarity search. Memurai for Redis 8 supports Windows Server 2016 and later and Windows 10 and later, runs as a Windows service writing to the event log, is free for development and testing, and Memurai Enterprise is available for a 90-day no-cost trial.

key takeaway

Windows teams can now run RediSearch vector similarity search, RedisJSON, and the vector sets data type natively via Memurai for Redis 8 without Docker or WSL, which the post says supplies the search that RedisVL and LangChain's Redis integration need.

read2 min views18 publishedNov 16, 2026
Run RediSearch, vector sets, & RedisJSON natively on Windows with Memurai
Image: Redis (auto-discovered)

Blog

Memurai for Redis 8 is now generally available, bringing Redis 8.2 capabilities to Windows developers without requiring Docker, WSL, or a separate Linux environment. For organizations running Windows-based apps, this means access to modern Redis capabilities without changing their existing infrastructure.

Memurai is a Windows-native, Redis-compatible data store and our official partner for Redis on Windows. It works with the Redis clients you already use, including StackExchange.Redis for .NET and Jedis for Java, thanks to full RESP compatibility.

What's new in Memurai for Redis 8 #

  1. RediSearch adds secondary indexing and advanced querying, including full-text, structured, and vector similarity search.
  2. RedisJSON adds native JSON support, so you can read and update individual fields without treating whole documents as opaque strings.
  3. Vector sets add a Redis 8 data type built for vector similarity search.

Core workloads #

User profiles, session state, and conversation history are all documents. Store them as JSON, index the fields you query, and read them back in real time. From memurai-cli:

With RedisJSON, you fetch or update only the fields you need. That means simpler app code, less network traffic, and fewer update conflicts, since changes are applied inside Memurai. With RediSearch, Memurai does the searching, filtering, and aggregating, so you run no separate search system.

AI workloads #

AI apps rely on rapid access to relevant data, memory, and context. Common patterns include:

  1. RAG: store documents in RedisJSON and use RediSearch to retrieve the right context for each prompt.
  2. Agent memory: keep short-term and long-term memory in one data store.
  3. Semantic caching: reuse earlier LLM responses for similar prompts to reduce response times.

Memurai is the only enterprise-ready Windows-native port of Redis, and it now provides the search that RedisVL and LangChain's Redis integration need, so Windows teams can build these AI workloads natively.

Similarity search with vector sets:

Healthcare, insurance, and government organizations often have on-premises requirements. They can run these capabilities in existing Windows environments and keep data and AI workloads on infrastructure they control.

Availability #

Memurai for Redis 8 supports Windows Server 2016 and later, and Windows 10 and later. Memurai integrates with Windows infrastructure, running as a Windows service and writing to the event log. Other Redis 8 modules are planned.

Try it today #

Developers can download Memurai for Redis 8 from the Memurai website and use it free for development and testing. Teams planning production use can try Memurai Enterprise for 90 days at no cost. Release notes are on the Memurai portal. If you build something with it, we would love to hear about it.

Get started with Redis today #

Speak to a Redis expert and learn more about enterprise-grade Redis today.

── more in #ai-infrastructure 4 stories · sorted by recency
── more on @memurai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/run-redisearch-vecto…] indexed:0 read:2min 2026-11-16 · —