Redis today announced the next chapter of Redis Iris, its real-time context engine for AI agents. Redis Iris now offers six customizable capabilities designed to be used together or independently, that give agents the memory, context, and messaging they need to work reliably in the real world: Redis Intent Router, Redis Agent Playbooks, Redis Agent Memory, Redis Context Gateway, Redis Lens, and Redis Agent Mesh.
AI models and infrastructure are now good enough for enterprise, yet few teams are seeing repeatable, production-level success with agents. Agents often lack the right context, at the right time, remembered the right way. Those that do deliver value often do so inefficiently, with over-stuffed prompts, redundant LLM calls, and brittle custom integrations that cost more in tokens and time than value they return.
"Agents need the same foundations as apps and microservices: live app data, runtime state and service communication," said Rowan Trollope, CEO of Redis. "They also need new capabilities like memory, context management and routing. Redis already sits in the hot path as the leading runtime database for apps. Developers shouldn't need five infrastructure products to make agents work. Iris brings those primitives together in one place so developers can build agents that work in production."
Iris delivers production-ready context, memory, and messaging from day one, while letting teams customize each capability. Intent Router (GA) matches meaning of request rather than wording and sends it to right destination, whether remembered FAQ, agent skill, human, or LLM, with agent and model routing, guardrails, and fuzzy if-statements. Agent Playbooks (GA) lets teams define which answers are stable and should be reused, and which require current data and fresh run of known procedure, becoming more thorough and accurate the more they run.
Agent Memory (GA) builds memories from user actions as well as documents and semi-structured data through MemoryETL, organizes them in hierarchies, and provides inspection, audit, and provenance. It can also forget what it should not keep, such as personally identifiable information. Context Gateway (GA) gives agents a single, governed point of entry to connected context sources. Teams can bring their own MCP servers, cache which tools solve a given problem, and build reusable results.
Lens (beta) makes agent behavior traceable. Every outcome can be traced back to skill, route, or FAQ that served it, the memory it learned from, and source session, providing auditable evidence alongside visibility into task success, tokens per task, and latency. Agent Mesh (beta) lets agents communicate over ephemeral streams and automatically buffers and reconnects when connection drops. Durable SSE Streams keep responses flowing through interruptions, and A2A Comms give agents reliable channel for delegation and handoffs.
Production agents must handle unpredictable human inputs, multiple channels, and handoffs between agents. Iris is built around four principles: context should be navigable rather than siloed, memory should be adaptive and selective, context should be efficient to keep costs in check, and context should compound as agents learn from past interactions.
Since Redis Iris first launched in May 2026, customers have been putting it to work in production. "Everything you see in Paradigm is stored in Redis. It is the memory and orchestration layer that lets our agents work in real time, at a scale that wasn't possible before," said June Lee, CTO, Paradigm.
Redis Iris is available today. Intent Router, Agent Playbooks, Agent Memory, and Context Gateway are generally available; Lens and Agent Mesh are in beta.
About Redis
Redis is the world's fastest data platform. From its open source origins in 2011 to becoming the #1 cited brand for caching solutions, Redis has helped more than 10,000 customers build, scale, and deploy the apps our world runs on. With cloud and on-prem databases for caching, GenAI, and more, Redis helps digital businesses set a new standard for app speed.
