San Francisco, November 4, 2026 / PRNewswire / -- Redis announced today that its real-time context engine Redis Iris for the AI agent has entered the next phase. Redis Iris now offers six customizable capabilities that can be used in combination or independently, providing the agent with the memory, context, and messaging capabilities necessary for reliable operation in the real world: Redis Intent Router, Redis Agent Playbooks, Redis Agent Memory, Redis Context Gateway, Redis Lens, and Redis Agent Mesh.

Redis indicates that today, the AI models and infrastructure are already sufficient to meet corporate needs, but there are still not many teams that have successfully implemented repeatable, production-level agents. Agents often fail to obtain the correct context at the right time, nor can they remember this information in the proper manner. Even when some agents are able to create value, they are frequently inefficient, suffering from issues such as excessive use of prompts, repeated calls to large language models, and fragile customized integrations, which results in costs in terms of token and time that exceed the value they provide.

Redis CEO Rowan Trollope stated: "Agents require the same foundation as applications and microservices: real-time application data, runtime state, and service communication. They also need new capabilities such as memory, context management, and routing. As a leader in the field of application runtime databases, Redis is already on the critical path. Developers should not have to use five different infrastructure products just to get agents up and running. Iris integrates these fundamental capabilities into one place, enabling developers to build agents that can run in a production environment."

Six capabilities, one runtime

Redis indicates that Iris provides context, memory, and messaging capabilities suitable for a production environment from day one, while also allowing teams to customize each of these capabilities for their respective agents. This release includes:

• Intent Router (officially available, GA)Match based on the meaning of the request rather than its wording, and send it to the correct destination, whether it's a remembered FAQ, a certain agent skill, manual processing, or a large language model. This feature also supports agent and model routing, guardrail mechanisms, as well as "fuzzy" if statements, allowing decisions to be no longer limited to true or false.
• Agent Playbooks (officially available, GA)Let the team define which answers are stable and can be reused, and which ones require current data as well as a new round of execution of the known processes. Redis indicates that as the number of runs increases, Playbooks will become more comprehensive and accurate, thereby reducing problem-solving time and lowering the token overhead.
• Agent Memory (officially available, GA)Through MemoryETL, memories are constructed from user behavior as well as documents and other semi-structured data, and these memories are organized in a hierarchical manner to achieve finer-grained control. At the same time, it provides capabilities for inspection, auditing, and traceability. This feature can also erase information that should not be retained, such as personal identification information.
• Context Gateway (officially available, GA)Provide a unified and governed entry point for agents to access connected context sources. Teams can connect to their own MCP servers, cache which tools can solve specific problems to reduce the use of token, and build reusable results to maintain consistency across different sessions.
• Lens (Test version, beta)Makes agent behavior traceable. Every result can be traced back to the skill, route, or FAQ that provided that result, back to the memory upon which its learning is based, as well as the source session; it also provides auditable evidence and demonstrates visibility into task success rates, single-task token consumption, and latency, among other aspects.
• Agent Mesh (Test version, beta)Allow agents to communicate through temporary streams, and automatically buffer and reconnect when the connection is interrupted. SSE Streams ensures that transmissions can continue during interruptions, while A2A Comms provides a reliable channel for agent delegation and handover.

Redis indicates that by combining these capabilities, it helps ensure that the agent remembers the correct information, answers in the right way, remains transparent in each operation, and at the same time produces more results with less token. Since Iris runs on the Redis technology that the team is already familiar with, organizations can reduce the custom integration work typically required for connecting retrieval, memory, routing, and messaging.

Built for the complex real world

Redis indicates that agents in a production environment must handle unpredictable human input, multiple channels, as well as handovers between agents, and any of these links can become a point of failure. Iris is built around four principles: the context should be navigable rather than isolated and scattered; memory should be adaptive and selective; the context should be efficient to control costs; and the context should be able to continuously accumulate as agents learn from past interactions.

Since its first release by Redis Iris in May 2026, Redis indicates that customers have put it into production use.

Paradigm Chief Technology Officer June Lee said: "Everything you see in Paradigm is stored in Redis. It is the memory and orchestration layer that enables our agents to run in real-time and achieve a scale that was previously unattainable."

Availability and Related Resources

Redis Iris is now available. Intent Router, Agent Playbooks, Agent Memory, and Context Gateway are officially available; Lens and Agent Mesh are in the beta version. For more information, please visit redis.io / iris.

Redis will hold the first online launch event with their engineering team on November 12 (for the American region) and November 17 (for Europe, Middle East, and Africa). Registration information can be found at redis.io / resources / videos / redis-iris-full-spectrum.

About Redis

Redis indicates that the company is the fastest data platform in the world. Since its inception as open-source software in 2011, it has become the most frequently cited brand in caching solutions. Redis has helped over 10,000 customers build, scale, and deploy applications that power the modern world. By providing cloud and local databases for caching, generative AI, and other use cases, Redis helps digital enterprises set new standards for application speed.

Redis has offices in San Francisco, Austin, London, Tel Aviv, and Singapore. The company claims to be internationally recognized as a leader in rapidly building high-performance applications. For more information, see redis.io.