Redis Iris

Overview

Redis Iris is a real-time context engine for AI agents first launched in May 2026. On November 4, 2026 Redis expanded it with six components that can be used together or independently: Intent Router, Agent Playbooks, Agent Memory and Context Gateway (all generally available), and Lens and Agent Mesh (both in beta). Intent Router matches a request by meaning and routes it to a stored FAQ, an agent skill, a human or an LLM. Agent Memory builds hierarchical memories from user actions and documents via MemoryETL, supports audit and provenance, and can forget data such as PII. Redis published no Iris-specific performance figures or pricing in the release.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

• Intent Router (GA): semantic routing to FAQ, skill, human or LLM; also model/agent routing and guardrails
• Agent Playbooks (GA): separates reusable answers from steps that need fresh data and a rerun
• Agent Memory (GA): MemoryETL, hierarchical memory, inspection/audit/provenance, PII forgetting
• Context Gateway (GA): single governed entry point to context sources, bring-your-own MCP servers
• Lens (beta): traces outcomes to the skill, route, FAQ, memory and session; tracks task success, tokens and latency
• Agent Mesh (beta): agent-to-agent messaging over ephemeral streams with buffering, reconnection and A2A handoffs

Use cases

• Customer-support agents that reuse stable answers and rerun procedures only when data changes
• Long-lived agents that need auditable, deletable memory
• Multi-agent systems needing delegation and handoff messaging

Pricing

unknown; not stated in the November 4, 2026 release.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released

1 May 2026

Record updated

8 Nov 2026

Record last checked

8 Nov 2026

• redis.io/press/redis-expands-redis-iris-to-give-ai-agents-the-memory-context-and-messaging-they-need-to-get-to-production/
• redis.io/blog/the-next-chapter-of-redis-iris-what-agents-need-to-work-in-the-real-world/