Redis

Millions of engineers already ship on Redis. Now you can build your agent on Redis, easier than ever. Join Redis CEO, @Rowantrollope, and Director of Engineering & Head of AI Product, @Simba_Khadder, for a special livestream Monday, May 18 at 10am PT. twitter.com/i/broadcasts/1…

More developers choose Redis to power production-grade agent memory than any other platform. Redis acts as a real-time context engine, gathering, syncing, and serving the data your AI needs to respond fast and accurately. Semantic caching, agentic memory, high-throughput vector search—all on AWS. Download the ebook to see how it's done: redis.io/resources/redi…

Three new partners in the Redis network. One shared north star: performance. @LangChain, @tavilyai, and @Railway are teams building the infrastructure that makes real-time AI possible. Different layers of the stack. Same standard for speed. Learn more about the Redis Partner Network: redis.io/partners/

Need document parsing that stays fully local and private? 👀 Meet liteparse-server, a self-hostable, open-source HTTP server for parsing documents and generating screenshots from PDFs, Office files, and images. ✅ 100% self-hosted ✅ Private by default ✅ Open source ✅ Built for production deployments Deploy it as: 🐳 a @Docker container ⚡ or a serverless Express.js API It also integrates easily with: - @Redisinc for caching and rate limiting - @opentelemetry-compatible collectors for traces and metrics - observability tools like @JaegerTracing, @PrometheusIO and @grafana Read the full breakdown here: llamaindex.ai/blog/liteparse… GitHub repo: github.com/run-llama/lite…

Agents without memory hallucinate, forget, and burn through API costs. LangGraph + Redis fixes these issues with stateful workflows, persistent memory, and real-world performance. Whether you're building RAG systems, customer support agents, or multi-agent orchestration, this guide covers the architectures and practical advice to get you there. Get the guide and go build: redis.io/guides/masteri…

That's what mission-critical looks like. Check out the full case study: redis.io/customers/blip/

@Blipbr processes 1.5 billion messages every month. Session state, message routing, and multi-step conversations across WhatsApp, Instagram, and Messenger all depend on fast, consistent coordination under the hood. After standardizing on Azure Managed Redis, Blip saw: → <0.2 ms average latency across core apps → 73% improvement in P99 latency → ~1M ops/sec per app across 11 clusters → 350k+ requests/sec handled without manual intervention

.@Redisinc is returning to Interrupt! Say hello to their team at the expo hall to learn about their fast memory layer for chatbots and AI agents as well as their ready-to-use tools for building AI apps.

Great AI apps aren't built alone. Whether that's deploying solutions for clients, co-selling, or plugging Redis directly into their own platforms, our goal is the same: get to market faster and perform better when it counts. Meet some of the members from the Redis Partner Network: Eden, @Infosys, @PersistentSys, and @Tech_Mahindra. Learn more about the network: redis.io/partners/

Cool to see how OpenAI uses Redis to scale voice AI to 900M users: openai.com/index/deliveri… We're huge Codex fans here at Redis - I use Codex 5.5 extensively - amazing work by the team there. GPT 5.5 is the best model for most tasks IMO. It even fixed my wifi tonight (no joke)

Never close the lid

Define once. Serve in milliseconds. Redis Feature Form, our managed feature store for production ML, is ready to build on: redis.io/feature-form/

🚨 your AI agents can now break out of prison last friday, 150+ builders took over the @AWS Builder Loft in SF. we put Mac Minis, AirPods Pros, and $20K+ on the table. judges @hanghuang_ @DevSeth44 @gregosuri and prizes from @Vapi_AI @Redisinc @wundergraphcom @akashnet @NexlaInc @TigerDatabase @GuildAI @chainguard_dev @InsForge_dev

Here’s the truth: Your AI is only as good as the context it runs on. With Redis, your chatbots and agents always have the right context—searched, gathered, and served in real time, on the platform teams already trust at scale. Build AI that actually knows things: redis.io/redis-for-ai/

Our CEO @TheMostlyGreat is joining @Redisinc, FastMCP, @AgenticAIFdn and @wandb by @CoreWeave on May 5th for a panel on MCP vs. A2A. We’ll cover how these approaches show up in production and what teams should understand before committing to one. redis.io/resources/vide…

MCP vs. A2A? The protocol you pick today shapes everything that follows. Join us alongside @wandb, @TryArcade, @fastmcp, and @techgirl1908 of the @AgenticAIFdn on May 5 for a deep dive on the protocols powering the next wave of AI agents. Register here: redis.io/resources/vide…

Your rate limiter works fine. Until you add a second API instance. Then every server tracks limits in its own memory, and your “global” limit is no longer global. I just published a video on building a production-ready rate limiter using Redis: youtu.be/5ix52STEPp0

Read more about our recommended fix and what this means for enterprise teams building RAG pipelines.

The risk gets higher in agentic pipelines, where one retrieval miss can affect the steps that come next—not just the answer a user sees. Common fixes like hybrid search, MaxSim reranking, and larger models don’t fully solve it either.

We just published research on retrieval tradeoff that should get the attention of anyone building RAG or agentic systems. Read more here from @TechJournalist in @VentureBeat: venturebeat.com/data/rag-preci…