86.5% accuracy. ~$0.07 per session. See how Redis stacks up in the Agent Memory Benchmark.

Read the report

Platform

Platform

Redis IrisReal-time context for agents Redis LangCacheSave on tokens for common questions Redis Context RetrieverLeverage context from anywhere Redis Agent MemoryAgentic memory for consistent experiences Redis Data IntegrationCDC across your structured data Redis FlexMore data, more speed, less cost CachingSub-ms read/write at scale StreamingEvent-driven messaging & data pipelines Session managementFast, persistent storage for sessions SearchSearch & query for structured data Feature storeReal-time ML feature pipeline for apps & agents

Get RedisDownloads

Deploy

Deploy

Redis CloudFully managed, fully flexible Redis SoftwareOn-prem Redis open source frameworkRedis 8.8 PricingLet’s talk numbers Redis on AWSBuy with cloud commits Azure Managed RedisMicrosoft-supported Redis Redis on Google CloudRedis from the marketplace

Tools

Redis InsightUI to visualize, query, & debug RIOTGet data into Redis from anywhere Client librariesPython, Node, Java, Go, .Net, & more SDKsConnect Redis to your apps

Get RedisDownloads

Solutions

AI & ML Apps

Scale agent & agentic systems Everything you need to be successful RAGUnderstand how Redis powers RAG Semantic searchRight answers, right now MLLeverage your features, fast Token optimizationAll the AI without all the cost AI cost optimizationControl AI costs without compromise

Core Workloads

Fraud detectionStop fraud, protect customers Real-time decisionsAct on data in real time Caching & performanceOur bread & butter Real-time messagingStreams at the speed of thought Session managementConsistent experiences everywhere LeaderboardsKnow who’s winning

Industries

Financial services E-commerce & retail Gaming Healthcare Telco

Get RedisDownloads

Devs

Docs

Redis CloudThe nitty gritty Welcome to the communityJoin the largest open source community in cache Dev HubAll the tools to build

Training

UniversityBecome a Redis expert TutorialsHow-to for whatever you’re trying to do Quick startsGo 0 to 1: Redis fast Knowledge baseGet support

Learning

BlogAll the words Resource centerEverything you need, in one place Demo centerAnything & everything, in action Reference architecturesNo guessing, just deploy

Resources

Customers

Resource Center

Events

Virtual & live eventsCome say hello

Partners

Find a partner AWS Google Microsoft

Learn how to BuildVisit our dev hub

Try Redis Book a meeting

Resource Center

Events & webinars Blog Videos Glossary Resources Architecture Diagrams Demo Center

Resource Center

Events & webinars Blog Videos Glossary Resources Architecture Diagrams Demo Center

You don’t need to pay for RAM you’re not using.

Flex gives you Redis performance where it matters.

By pushing the rest of your data to lower-cost flash, Redis Flex enables TB-scale datasets, single-digit millisecond latency, and up to ~80% lower cost per GB. If you’re running large-scale AI, fraud, or caching workloads, Flex is where things get practical.

44 minutes

In this session, we’ll break down how Flex works, where it fits, and how to dial in the right balance between speed and spend.

See how Flex tiers data across RAM and flash, for better memory efficiency and performance
Learn how to choose the right 10–50% RAM ratio based on real sizing patterns and workload needs
Walk through real-world use cases like feature stores, fraud detection, and large-scale caches/session stores
Know when Flex is the right move and when sticking with all-RAM Redis will save you time and complexity

Speakers

Matthew Schaeffer

Matthew Schaeffer

Solution Architect

Parshwa Shah

Parshwa Shah

Sr. Manager, Solution Architect

Latest content

What we’ve learned building production agents: Context engineering in practice

18 minutes

Inside the state of context engineering

18 minutes

Design, build, and scale agent memory

Get started with Redis today

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

Try for free Talk to sales