Redis Iris

Redis Iris is a suite of managed and self-managed services that give your customers accurate, consistent experiences with your AI agents by providing memories, approved answers, governed access to business data, and turn-by-turn tracing.

Redis Iris eliminates the infrastructure burden of building context-aware AI agents.

Explore Redis Iris

Concepts

What happens when an agent asks Redis Iris for context

Learn more →
Read more
SDK and CLI setup

Install redis-iris and connect it to Redis Cloud or a self-managed deployment

Learn more →
Read more
Agent Memory

Persistent short-term and long-term memory across agent interactions

Learn more →
Read more
Agent Playbooks

Publish reusable answers and procedures for agents

Learn more →
Read more
Context Gateway

One MCP endpoint for the tools of any MCP server and your Redis data

Learn more →
Read more
Intent Router

Classify requests into intents and route them to the right tool or agent

Learn more →
Read more
Lens (beta)

Debug agent answers by tracing the context behind each turn

Learn more →
Read more
Agent Mesh (beta)

Share agent-to-agent task state across Python replicas and resume event delivery

Learn more →
Read more

What is Redis Iris?

Redis Iris is a production-ready context engine for AI agents that:

  • Adds persistent memory: Agents remember past interactions and user preferences across sessions
  • Answers recurring questions without a model call: Agent Playbooks return the answers and procedures your business published, matched to the agent's task by semantic similarity
  • Connects tools and business data: Context Gateway gives agents one MCP endpoint for the tools of any MCP server and your Redis data
  • Routes each message: Intent Router matches a message to the intents you defined and returns the target that handles it
  • Shows why an agent answered the way it did: Lens (beta) traces each turn, from what each source returned to what entered the prompt
  • Keeps long responses deliverable: Agent Mesh (beta) keeps an agent's response stream resumable when the client disconnects
  • Keeps data fresh: Data Integration streams live changes from relational databases into Redis within seconds
  • Deploys your way: Check each service’s operator guide for its managed and self-managed deployment options.

Why use Redis Iris?

For AI applications

  • Agents that remember context across sessions and users
  • Consistent answers to recurring questions, from content your business approved
  • Reliable, structured access to live business data
  • No stale data: near real-time sync from your source databases

For developers

  • Managed and self-managed deployment options documented for each service
  • Python and JavaScript SDKs and REST APIs for all services
  • Define your data model once, reuse it across all agents
  • Trace each agent turn to see which context reached the prompt
  • No database setup required on Redis Cloud

Next steps

Learn how Redis Iris works, from the agent request to where each kind of context lives.

RATE THIS PAGE
Back to top ↑