Redis is the world's fastest data platform. We provide cloud and on-prem solutions for caching, vector search, and more that seamlessly fit into any tech stack. With fast setup and fast support, we make it simple for digital customers to build, scale, and deploy the fast apps our world runs on.
Happy Friday everyone - you know what time it is, end of the month means a just a few minutes to catch up everything happening at Redis. And yes... I know its longer than two minutes, okay. I could've spent six minutes at least because all of the releases that happened this month.
You probably saw Redis Iris (which I covered if you haven't heard about it) got announced but there are some serious sleeper updates that flew under the radar... check it out!
https://lnkd.in/gJTcBDRE
Huge amount of gratitude to the folks helping us get these videos and blogs out: #RedisAvery PetersonLana KotovaSylvia OgwengFionce SiowJonathan SalomonMirko OrtensiBosmat TuvelAharon BlitzerNoam Stern
Happy Friday everyone - you know what time it is, end of the month means a just a few minutes to catch up everything happening at Redis. And yes... I know its longer than two minutes, okay. I could've spent six minutes at least because all of the releases that happened this month.
You probably saw Redis Iris (which I covered if you haven't heard about it) got announced but there are some serious sleeper updates that flew under the radar... check it out!
https://lnkd.in/gJTcBDRE
Huge amount of gratitude to the folks helping us get these videos and blogs out: #RedisAvery PetersonLana KotovaSylvia OgwengFionce SiowJonathan SalomonMirko OrtensiBosmat TuvelAharon BlitzerNoam Stern
#MicrosoftBuild 2026 is next week. We’ll be there, showing how teams can use Azure Managed Redis to build faster, smarter agents.
Here’s where to find us:
▶️ Our lightning talk “Faster and smarter agents with Redis and Foundry” at noon PT on Tuesday, June 2. A focused live session demoing how Azure Managed Redis and Microsoft Foundry help developers build agents with real-time memory, context, vector search, semantic caching, and RAG patterns.
▶️ An on-demand session “Faster AI Responses with Semantic Caching in Azure Managed Redis.” A deeper walkthrough for developers building copilots, autonomous agents, and large-scale LLM chatbots on how to use Azure Managed Redis with Microsoft Foundry for agent memory, real-time context, vector search, and semantic caching.
▶️ Come see us at our booth. Azure Managed Redis will be part of the shared Azure Data / NoSQL booth experience. We’ll have demos across real-time AI applications, vector search, semantic caching, and integrations with Azure AI Foundry and agent frameworks. It’s also a chance to talk directly with product experts about where Azure Managed Redis fits in production architectures.
Read Microsoft’s full “know before you go” post here: https://lnkd.in/gJRCZUCZ
We'll see you there: https://lnkd.in/eKgQTn4q
Redis shipped Iris last week — a context engine for AI agents that packages memory, caching, and data retrieval as managed infrastructure.
That caught my attention, so I spent the weekend building a travel agent on it to see how it holds up in practice.
My takeaway: the hard part of production agents usually isn’t the model. It’s the plumbing around it — session memory, long-term memory, current data, retrieval, and avoiding repeated LLM calls for the same work.
Iris is essentially a bet that more of this should live in infrastructure, not scattered across app code.
I wrote up what worked, what felt promising, and what I had to work around.
Not an endorsement — just a hands-on read.
https://lnkd.in/gsfebMRA#AIAgents#Redis#LangGraph
We made the Redpoint InfraRed 100, a list that recognizes the companies that are building the AI infrastructure of today and tomorrow through reliability, scalability, security, and innovation.
Context orchestration at scale is the most important problem to be solved in the agentic era. We’ve built Redis to deliver the right context, with the right meaning, fast enough for agents to act on.
Proud to be building alongside the other teams and companies who raised the bar. Check out the full report: https://lnkd.in/gVRDNS6Q
Redis has just announced Iris, their architecture for AI agent retrieval that takes an interesting approach to the context layer problem.
Rather than pre-compiling answers into static artifacts, Iris focuses on keeping a fast, navigable copy of your operational data that agents can query in real time.
In this video, I walk through the Redis Iris stack, what each component does, and how its runtime approach compares to build-time alternatives like Pinecone's recently announced Nexus offering.
What's covered:
🔹 Redis' four core requirements for agent retrieval at scale: navigability, speed, freshness, and self-improvement
🔹 Redis Data Integration (RDI) and how change data capture keeps an operational copy of data in sync
🔹 Redis Context Retriever: defining entities, fields, relationships, and tools (find, get, search, filter) exposed via MCP or CLI with row-level access control
🔹 Redis Agent Memory: short-term session memory with custom TTL, plus long-term memory for preferences, learned patterns, and promoted session data
🔹 LangCache for semantic response caching, including similarity thresholds, search strategies, and the risks of stale or out-of-context cache hits
🔹 Redis Search across vector, structured, and unstructured data in a single index
🔹 Redis Flex, SSD-based storage tier for more cost-effective scaling beyond pure in-memory
🔹 A direct comparison of Redis Iris (runtime, fresh-on-demand) vs Pinecone Nexus (build-time, pre-compiled knowledge artifacts) and when each architecture fits best.
Full video in the comments.
ICYMI: Redis Docs now ships with downloadable Markdown on every content page. Feed them directly into coding agents.
No reformatting. No friction. Just grab the file and build.
Looking for more resources for AI agent development with Redis? We got you: https://lnkd.in/gT4T58jP
Harness engineering is the discipline of designing the infrastructure, rules, and execution environments around AI agents so they can operate as reliable, observable, and scalable work systems.
It covers the runtime pieces that manage sessions, permissions, tool execution, state, caching, rate limits, retries, logging, monitoring, and failure handling.
System engineering by another name.
This is one of the slides from the session where I'll cover three specific components of reliable and scalable systems:
- Caching
- Session Management
- Rate Limiting
Whether you're a machine learning engineer trying to harness your agents or a traditional software engineer trying to scale your systems reliably you will definitely learn something new in this webinar.
And as an extra, we will also talk about context engineering! All around Redis!
The session will take place next Thursday, the 26th of May. Don't forget to RSVP!
Webinar:
https://lnkd.in/e8GWVHs2
Most AI agents forget everything the moment a session ends. Redis Agent Memory changes that by giving agents both short-term session context and durable long-term memory that persists across conversations.
Lead Developer Advocate Ricardo Ferreira builds a LangGraph travel agent that uses Redis Agent Memory with:
→ Short-term memory to keep the current conversation coherent
→ Long-term memory to store preferences and facts across sessions
→ Background extraction to decide what's worth keeping and what isn't
If you're building customer support agents, AI copilots, or personalized assistants, this is the memory layer worth understanding. Full tutorial here: https://lnkd.in/gE2ut-w8
This week, we launched Redis Iris, our new agent context and memory platform.
Here's what people are saying:
Redis CEO Rowan Trollope joined TBPN to break down why context architecture is replacing RAG, and why the agent era demands a fundamentally different data layer. → https://x.com/RedisincVentureBeat's Sean M. Kerner covered the launch with analysis from HyperFRAME Research's Stephanie Walter and mangoes.ai founder Amit Lamba, who runs real-time voice AI for healthcare use cases natively on Redis. → https://lnkd.in/eTmjXWY5Blocks and Files editor Chris Mellor went deep on Redis Iris and Redis Flex, petabyte-scale retrieval, sub-5ms latency, at a tenth of the cost of RAM. → https://lnkd.in/gtzJaiA3
Agents don't get smarter just by better models. They work when the data underneath them is fast, fresh, and structured for machines, not humans. That’s why we built Redis Iris.
Learn more: redis.io/iris
