Redis Iris Context Engine

7/13/2026

This post provides a foundational explanation of vector embeddings, covering their theory, creation process, and similarity search mechanisms. It details their practical applications in various AI-driven systems and positions Redis Iris as a solution for storing and querying these embeddings at scale, emphasizing its performance benefits for AI workloads like semantic caching and agent memory.

7/10/2026

This post introduces Redis Agent Memory as a managed service for AI agent memory, featuring two tiers: session memory for working context and long-term memory for vector embeddings. It details automatic promotion between tiers, native TTL support for data aging, and structured key patterns for data deletion. It also positions Redis Iris as a context engine combining memory, retrieval, live data, and semantic caching, mentioning LangCache for LLM cost reduction and Redis Flex for tiered storage.

7/6/2026

Announces the general availability of Redis Data Integration (RDI) in Redis Cloud on AWS, detailing its benefits for keeping application data fresh, especially for AI agents. Highlights new features in the GA release like faster provisioning, improved visibility, error reporting, sync performance, source configuration, and REST API management. Introduces new integrations with MongoDB and Snowflake. Also announces an update to Flex, allowing tunable RAM-to-Flash ratios (10-50% RAM) and extending Flex pricing to BYOC deployments.

7/1/2026

This post provides a comparative analysis of open-source vector databases, positioning Redis as a unified platform solution. It details Redis's vector search architecture, performance benchmarks for billion-scale datasets, hybrid search capabilities with advanced ranking algorithms, and semantic caching features. The post contrasts Redis's integrated approach with standalone vector databases, emphasizing the benefits of consolidating infrastructure for vector search, caching, and operational data.

6/22/2026

This post introduces the concept of sub-agents as specialized components within a larger AI system, designed to handle narrowly scoped tasks. It discusses various coordination patterns (orchestrator-worker, supervisor, swarm, router) and highlights the 'context window problem' as a primary driver for splitting agents. The post explains how specialized sub-agents keep context windows focused by sifting through information and returning condensed summaries. It also addresses the challenges of inter-agent misalignment and the need for shared memory to maintain a common ground truth, preventing issues like context poisoning, confusion, clash, and rot. Redis Iris is presented as a solution for providing both memory and retrieval capabilities to these sub-agents, utilizing layered memory (short-term, long-term, episodic, semantic) and hybrid search with vector embeddings and metadata.

6/17/2026

This post is an FAQ that elaborates on the practical application of Redis Iris for AI agents. It details strategies for managing context through chunk-based RAG, agentic RAG, and MCP-style tools. It emphasizes the importance of real-time context engines for providing fresh, relevant data to agents, addressing limitations of basic RAG, and the role of agent memory and semantic caching in improving personalization, speed, and cost-efficiency. Redis Iris is positioned as a solution to wire these components together, offering Context Retriever for business data, Redis Search for multi-modal retrieval, and Agent Memory/LangCache for persistent and cost-effective context.

6/17/2026

This post elaborates on the necessity of combining retrieval (for stateless fact lookup) with memory (for stateful interaction history) in AI agents. It highlights the limitations of using only one of these components and the challenges of integrating separate systems for retrieval and memory, such as latency, freshness drift, and consistency issues. Redis Iris is presented as a solution that unifies these capabilities.

6/12/2026

This post details AI agent access control, focusing on the gap between authentication and authorization, the challenges of per-action scope, and how to enforce permissions in RAG pipelines through metadata filtering, permission-aware retrieval, and layered policy enforcement at document, row, and field levels. It highlights the importance of a governed data model and attribute/relationship-based access control for fine-grained security.

6/12/2026

This post details the limitations of the Model Context Protocol (MCP) in handling agent memory, data freshness, and chain reliability, and explains how Redis Iris addresses these gaps. It highlights that MCP standardizes tool connectivity but leaves state management, memory persistence, and data currency to the application layer. The post explains how Redis Iris, as a real-time data platform, provides solutions for these challenges by offering features like in-memory data structures for working memory, vector search for long-term memory, data integration for keeping retrieved context current, and LangCache for semantic caching to reduce staleness and improve retrieval reliability. It emphasizes that Redis Iris enables agents to have both fresh context and long-term memory, thereby improving the end-to-end reliability of agent chains.

6/11/2026

This post elaborates on the challenges of context quality in AI agents, introducing failure modes such as context poisoning, distraction, confusion, clash, and rot. It details technical solutions for improving context quality, including precision-focused re-ranking (using cross-encoders), hybrid search (combining vector search and BM25 with RRF), metadata filtering, and freshness constraints. The post argues that retrieval quality is paramount for context quality and that these techniques collectively shape the information provided to LLMs, directly impacting agent performance.

6/4/2026

This post announces the General Availability (GA) of Redis Data Integration (RDI) in Redis Cloud on AWS. It details RDI's capabilities in moving operational and analytical data into Redis in near real-time, transforming source records into Redis data structures for optimized reads. The post highlights key improvements in the GA release, including enhanced CDC latency and throughput, faster full hydration, improved pipeline management with early validation, advanced configuration, snapshot SQL support, and new source connectors for Snowflake (preview) and MongoDB. It also emphasizes RDI's role as a foundational component for Redis Iris, enabling real-time context for AI agents by ensuring data freshness.

6/3/2026

This post elaborates on the challenges of providing accurate business context to AI models, emphasizing the critical role of the surrounding infrastructure (the context layer) over the AI model itself. It details common failure modes such as stale data, noise, contradictory sources, and context window decay. The post defines the key functions of a context layer: separating systems of record from query layers, retrieving relevant material (not just more), and serving it quickly. It then explains how Redis, and specifically Redis Iris (comprising Redis Context Retriever, Agent Memory, Data Integration, LangCache, and Search), addresses these challenges by providing a real-time context engine that enables fast, low-latency access to continuously updated business state, supporting hybrid retrieval and semantic caching for AI workloads.

6/3/2026

This post introduces context graphs as a complementary retrieval mechanism to vector search for RAG pipelines. It explains the limitations of vector-only RAG, such as missing connected information and issues with multi-hop questions, chunk boundaries, and exact matches. It details the architecture of context graphs (entity/relationship extraction, knowledge graph construction, graph-aware retrieval) and highlights their strengths in multi-hop question answering, technical specification Q&A, and global/thematic queries. It also contrasts these with scenarios where vector search excels (single-hop lookups, self-contained content) and discusses the costs of graph construction and retrieval latency. The post advocates for dual-channel retrieval, combining vector and graph search, and positions Redis Query Engine's hybrid search and Redis Iris's unified context/memory layer as foundational components for such architectures.

6/3/2026

This post clarifies the distinction between BI semantic layers and AI context layers. It details the limitations of semantic layers for AI agents, including lack of native vector search support, batch refresh, no memory, inability to prevent hallucination, and no support for unstructured data. It then defines a context layer as a runtime system that manages AI agent access to information at each reasoning step, encompassing retrieval pipelines (RAG), short-term and long-term memory, tool definitions, and permission filtering. The post highlights the architectural differences and failure modes of each layer, emphasizing the need for a dedicated context infrastructure to avoid issues like context rot, fragmentation across data stores, and retrieval gaps. Redis Iris is presented as a solution that provides fresh context and long-term memory for AI agents.

5/29/2026

Introduces Redis Iris, a new context engine for AI agents. Highlights two preview capabilities: Context Retriever for making external data sources navigable by agents, and Agent Memory for preserving short- and long-term memory across workflows and sessions.