Redis adds agent routing, observability and messaging to Iris
Redis released six new capabilities for its Iris real-time context engine on November 4, 2026. Four are generally available: Intent Router directs requests to FAQs, agents, humans or LLMs based on meaning rather than exact wording, supporting guardrails and fuzzy decisions. Agent Playbooks stores reusable answers and procedures, improving accuracy and reducing token costs over repeated use.…
Key points
- Four Iris capabilities (Intent Router, Playbooks, Memory, Context Gateway) are generally available; two (Lens, Mesh) remain in beta
- Intent Router routes requests by meaning, not wording, supporting guardrails and fuzzy decisions for agent/model routing
- Agent Memory organizes user actions and documents hierarchically, with audit and PII-discarding features
Two features remain in beta: Lens traces agent outcomes to their sources (skills, routes, memories) and measures tokens, latency, and success rates for auditing. Agent Mesh ensures resilient messaging with automatic buffering and reconnection for interrupted streams. The release aims to address production pain points like lost context, redundant work, and communication failures. A free tier offers 5,000 messages to start. Redis positions Iris as a unified runtime for agents, replacing fragmented infrastructure for memory, context, routing, and communication.
Redis Broadens Iris With Agent Routing, Observability and Messaging
Unite.AI · 4 November 2026
Loading the full article…
This text was published by Unite.AI and written by Aiden Cross, AI Product Strategy & Execution, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Anthropic’s Claude Duet adds always-on agent to Pro, Max, Ultra plans · 1 src
- Amazon Bedrock adds decision models for agent evaluation · 1 src
- AWS details four context engineering layers for production AI agents · 1 src
- How Do You Evaluate an AI Agent? Tasks, Trajectories, Reliability, and Cost · 1 src
- Apple opens Siri AI to developers via iOS 27.3 betas · 3 src
Comments
via GitHub Discussions