Redis constructed its identify because the caching layer that stored internet purposes from collapsing underneath load. The issue it’s focusing on now has the identical construction however is tougher to unravel: manufacturing AI brokers failing not as a result of the fashions are flawed, however as a result of the information beneath them is scattered, stale and structured for people fairly than machines. Retrieval pipelines constructed for single queries can not soak up the amount brokers generate.
The hole Redis is focusing on is structural: brokers make orders of magnitude extra knowledge requests than human customers, however most retrieval layers have been constructed for the human-scale drawback. Redis Iris, launched Monday, is the corporate's reply: a context and reminiscence platform that sits between an agent and the information it must act. The platform combines real-time knowledge ingestion, a semantic interface that auto-generates MCP instruments from enterprise knowledge fashions, and an agent reminiscence server constructed on Redis Flex, a rewritten storage engine that runs 99% of knowledge on flash at a tenth of the price of in-memory storage alone.
The announcement lands as enterprise RAG infrastructure is in lively transition. VentureBeat's Q1 2026 VB Pulse RAG Infrastructure Market Tracker discovered purchaser intent to undertake hybrid retrieval tripling from 10.3% to 33.3% between January and March. Retrieval optimization surpassed analysis as the highest enterprise funding precedence for the primary time. Customized in-house retrieval stacks rose from 24.1% to 35.6% as enterprises outgrew off-the-shelf choices. Redis shouldn’t be the one infrastructure vendor studying these indicators — a number of knowledge platform suppliers have repositioned round agent context layers in current weeks.
The dimensions mismatch is the structural argument behind the launch.
"Firms could have orders of magnitude extra brokers than human beings," Rowan Trollope, CEO of Redis, advised VentureBeat. "Orders of magnitude extra brokers than human beings means orders of magnitude extra load on again finish methods."
From cache to context
Trollope traces the parallel again to the cell period: When legacy backends constructed for department tellers immediately needed to serve one million smartphone customers, Redis grew to become the caching layer that absorbed the load with no full rebuild.
What’s totally different this time is that brokers can not write their very own middleware. Within the cell period, a developer would sit with a database administrator, establish the queries an utility wanted and hard-code the caching logic right into a middleware layer. Brokers can not try this. They should discover the suitable knowledge at runtime, by way of interfaces constructed for them prematurely, or they stall.
"That is just like the analogy of the grocery retailer within the fridge," he mentioned. "If each time it’s important to go make your sandwich, it’s important to run to the grocery retailer to get the meals, that's not very environment friendly. You place a fridge in each home, you retailer just a little little bit of meals there. And that's form of the place we nonetheless are inclined to exist within the infrastructure stack."
What Redis Iris consists of
Iris ships 5 parts that collectively cowl knowledge ingestion, semantic entry, reminiscence and caching.
Redis Knowledge Integration. Now usually availability. RDI makes use of change knowledge seize pipelines to sync knowledge from relational databases, warehouses and doc shops into Redis constantly, with connectors for Oracle, Snowflake, Databricks and Postgres.
Context Retriever. Now in preview. Builders outline a semantic mannequin of enterprise knowledge utilizing pydantic fashions and Redis auto-generates MCP instruments brokers use to question it instantly, with row-level entry controls enforced server-side. Trollope describes the shift from traditional RAG as a directional inversion. "It's only a flip to let the agent pull the information as an alternative of presupposing and stuffing it into the pipeline," he mentioned.
Agent Reminiscence. Now in preview. Shops quick and long-term state throughout periods so brokers carry context with out re-deriving it on every flip.
Redis Flex. A rewritten storage engine that runs 99% of knowledge on SSDs and 1% in RAM, delivering petabyte-scale retrieval at sub-millisecond latencies.
Redis Search and LangCache. The retrieval and semantic caching spine beneath the platform. LangCache reduces redundant mannequin calls by caching immediate responses.
What analysts say
The info trade is mostly heading in the identical route now. Each main database vendor is making a context layer argument.
Conventional database distributors together with Oracle are integrating context and reminiscence layers to carry relational databases into the agentic AI period. Function-built vector database distributors together with Pinecone are doing the identical, constructing out a brand new data layer for agentic AI context. Standalone context layers like Hindsight are additionally a part of the rising panorama.
Trollope frames Redis's place as structurally totally different from that competitors.
"For us to win, nobody else has to lose," he mentioned. Many Redis deployments already run MongoDB or Oracle because the backend system of report. Iris displays and caches from these methods fairly than displacing them. Redis is launching Iris within the Snowflake market with native connectors.
Stephanie Walter, Follow Chief for AI Stack at HyperFRAME Analysis, places the market context plainly. "The market is converging on the identical conclusion: brokers don't simply want extra tokens or higher fashions. They want ruled, present, low-latency context," Walter mentioned.
Her learn on Redis's differentiation focuses on the place Redis already sits within the stack, which is near runtime, latency-sensitive operational state, and real-time knowledge.,
"The pitch shouldn’t be 'higher RAG' as a lot as 'brokers want dwell context, reminiscence, and quick retrieval whereas they’re truly working," she mentioned.
Whether or not it's Redis or one other vendor, each context layer know-how will face a governance problem to achieve success.
"Agentic AI won’t scale within the enterprise if each agent turns into a brand new value middle, a brand new knowledge entry danger, and a brand new governance exception," she mentioned. "The successful context layers would be the ones that make brokers quicker, cheaper, and safer to run."
For real-time scientific AI, getting context flawed shouldn’t be an choice
Mangoes.ai is one firm that has already needed to reply these questions in manufacturing, underneath circumstances the place the price of getting context flawed is measured in affected person outcomes.
Amit Lamba, founder and CEO of Mangoes.ai, runs a real-time voice AI platform deployed throughout giant healthcare services the place sufferers and clinicians ask dwell questions on remedy, scheduling and case historical past. Mangoes.ai constructed its stack natively on Redis from the beginning.
"Retrieval, reminiscence, and session state all run by way of Redis, so we're not stitching collectively separate instruments and hoping they speak to one another," Lamba mentioned.
The issue Iris's dynamic reminiscence functionality addresses is what occurs throughout a posh session.
"Take into consideration a one-hour group remedy session," Lamba mentioned. "You might want to know who mentioned what, when, and be capable to floor the suitable data to the therapist within the second. That's not a easy retrieval drawback."
The platform runs a number of specialised brokers in parallel, one for entity identification, one for relationship reasoning and one for integrating case historical past.
"The dynamic reminiscence functionality maps virtually completely to the issue we're fixing," Lamba mentioned.
What this implies for enterprises
For enterprises that constructed their AI stack round RAG, the retrieval layer that received them to manufacturing is now not sufficient to maintain them there
The RAG period is giving approach to context structure. The traditional RAG mannequin pushed knowledge into the agent earlier than the mannequin was known as. Manufacturing deployments are flipping that: brokers pull what they want at runtime by way of software calls, treating the information layer as a dwell useful resource fairly than a pre-loaded payload. Groups nonetheless optimizing RAG pipelines are fixing final 12 months's drawback.
The semantic layer is now manufacturing infrastructure. The mannequin that defines enterprise entities, their relationships and the entry guidelines between them must be constructed, versioned and maintained with the identical self-discipline as a knowledge pipeline. Most organizations haven’t staffed or structured for that work. The enterprises that outline their context structure now are those that won’t should rebuild it when agent workloads scale.
Funds is already transferring. VB Pulse Q1 2026 knowledge exhibits retrieval optimization funding rising from 19% to twenty-eight.9% throughout the quarter, overtaking analysis spending for the primary time. Organizations that spent the earlier 12 months measuring their retrieval high quality are actually spending to repair it. The context layer is an lively procurement choice, not a roadmap merchandise.
"The primary purchaser query shouldn’t be 'Do I would like a vector database, lengthy context, reminiscence, or a context engine?' It must be 'What does this agent have to know, how recent should that data be, who’s allowed to entry it, and what does each retrieval value?'" Walter mentioned.
