Urgent.News

What's breaking now, across thousands of outlets.

AI

Redis is going all in on AI.

Redis, the in-memory data structure store, is expanding its AI capabilities with the release of Redis Iris. This new offering includes six capabilities centered around retrieval, memory, routing, and messaging.

The core idea behind Redis Iris is to provide a unified, real-time engine that delivers relevant context to AI agents, ensuring they remain accurate, accountable, and efficient at scale. One of the main challenges in AI, particularly in agent-based systems, is the lack of context. Agents often fail due to missing or stale information, leading to inaccurate responses, sluggish performance, and frustrated users.

Redis Iris addresses this by allowing agents to follow connections between available data and tools, transforming them from mere query systems into connected exploration platforms. Agents can retain preferences, decisions, and past outcomes, while discarding stale, superseded, or irrelevant data. By retrieving only the relevant information and reusing previously generated answers, agents can significantly reduce costs and latency.

Memory and learning are essential for agents to improve over time. Redis Iris offers built-in memory, learning, and statefulness for AI agents. By turning agent behavior into a queryable record of decisions and providing complete trails for diagnosis and cost control, Redis Iris aims to eliminate the black box nature of AI agents.

Agent Mesh, a feature of Redis Iris, provides persistence and routing for agent streams, ensuring that agents can pick up exactly where they left off, even in the event of a dropped network connection. Intent Router further optimizes agent responses by sending requests to the appropriate place, whether that's a remembered FAQ, an agent skill, a human, or an LLM, thereby skipping redundant computations and improving response times.

Agent Playbooks, another feature, recognizes prompts that mean the same thing and reuses responses, reducing waste while allowing agents to grow more accurate over time. Ultimately, Redis Iris aims to deliver working memory and long-term recall in a single place, keeping conversations tight with active context while persisting vital long-term pieces like user preferences and past decisions across sessions and channels.

Written by urgent.news from Daily Dose of DS's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at redis.io →

More in AI

More from Thursday 19 November →