Artificial intelligence news.
Straight from the original announcements.

Redis expands Iris with memory, context and messaging tools for AI agents

November 6, 2026, 08:00By the AI News Bites Editorial TeamSource: PR Newswire

Redis has expanded Redis Iris with six configurable functions designed to give AI agents the memory, context and messaging capabilities needed for production use. Four features are generally available, while two are in beta.

Key points
  • Redis Iris now includes six configurable functions for AI agents.
  • Intent Router, Agent Playbooks, Agent Memory and Context Gateway are generally available.
  • Lens and Agent Mesh are in beta.
  • The features cover routing, memory, context governance, tracing and agent communication.
  • Redis Iris has been used by customers in production since May 2026.

Six functions in one runtime

The updated Redis Iris includes Redis Intent Router, Redis Agent Playbooks, Redis Agent Memory, Redis Context Gateway, Redis Lens and Redis Agent Mesh. Redis says teams can use the functions together or independently and adapt each one to their agents.

Intent Router is generally available and identifies the meaning of a request rather than relying only on its wording. It can route requests to stored FAQ answers, agent skills, people or large language models. The function also supports routing to agents or models, guardrails and flexible conditional decisions.

Agent Playbooks, also generally available, lets teams distinguish between answers that can be reused and tasks that require current data or another execution of an established process. Redis says playbooks become more comprehensive and precise with each execution, helping shorten problem-solving time and reduce token use.

Agent Memory uses MemoryETL to create memories from user actions, documents and other semistructured data. These memories are organized hierarchically, with inspection, auditing and provenance features. The system can also selectively forget information, including personal data that should not be retained.

Context access, tracing and agent communication

Context Gateway, which is generally available, provides a central, governed access point for connected context sources. Teams can connect their own MCP servers, cache which tools solve particular problems and create reusable results that remain consistent across sessions.

Lens is in beta and is designed to make agent behavior traceable. Redis says results can be linked to the skill used, the selected route or FAQ, the memory used by the agent and the original session. It also provides insight into task success, token use per task and latency.

Agent Mesh, also in beta, supports communication between agents through short-lived streams. It automatically buffers data and restores connections after interruptions. Durable SSE Streams maintain the transfer of responses during disruptions, while A2A Comms provide a channel for delegating and handing off tasks.

Redis targets production challenges

Redis says AI models and their supporting infrastructure are now capable of enterprise use, but relatively few teams have achieved repeatable success with agents in production. The company points to missing context and memory, overloaded prompts, redundant LLM calls and fragile custom integrations as common obstacles.

According to Redis, Iris is built around four principles: context should be navigable rather than isolated in silos, memory should be adaptable and selective, context should be used efficiently to control costs, and context should gain value as agents learn from past interactions.

Customers have used Redis Iris in production since its introduction in May 2026. June Lee, CTO of Paradigm, said the company uses Redis as the memory and orchestration layer for its agents, enabling them to work in real time at a scale that was previously not possible.

Availability

Redis Iris is available from November 6, 2026. Intent Router, Agent Playbooks, Agent Memory and Context Gateway are generally available. Lens and Agent Mesh are available in beta.

Redis and the development team will hold live demonstrations of the updated version on November 12 for North and South America and on November 17 for EMEA. Registration is available through Redis's Iris resources page.

RedisRedis IrisRedis Intent RouterRedis Agent PlaybooksRedis Agent MemoryRedis Context GatewayAI agentsenterprise AI

Related news

Redis adds managed memory to agents built with Vercel AI SDK
Products and toolsNovember 9, 2026

Redis adds managed memory to agents built with Vercel AI SDK

Redis has released an open-source package that adds Redis Agent Memory to agents built with Vercel's AI SDK. The integration is designed to help agents retain session…

Products and tools
Products and toolsNovember 6, 2026, 08:00

Redis Iris reaches GA with six tools for production AI agents

Redis has released Redis Iris in general availability, bringing six configurable memory, context and messaging capabilities to AI agents intended for production use. The…

Products and tools
Products and toolsNovember 6, 2026, 08:00

Redis expands Iris with six capabilities for production AI agents

Redis has expanded Redis Iris with six customizable capabilities designed to give AI agents memory, context, routing and communication tools for production use. The…