Redis

Redis

@redis.io

See how fast feels https://redis.io/

83 followers37 following31 posts

Redis reposted

Cassidy
@cassidoo.co

Replying to @cassidoo.co

This week's sponsor is @redis.io! Ever notice your agents just...forget everything the second a session ends? Redis Agent Memory fixes that. It gives your agents short-term memory plus context that actually sticks around across conversations, managed for you. redis.io/agent-memory...

redis.ioRedis Agent Memory | RedisDevelopers love Redis. Unlock the full potential of the Redis database with Redis Enterprise and start building blazing fast apps.
View full thread
Redis
@redis.io

➡️ Working memory vs. long-term memory, and when an agent should write to each ➡️ How Redis Context Retriever (the tool at the heart of Redis Iris) auto-generates business entities and exposes them as MCP tools ➡️ Why semantic caching with LangCache turns paraphrased repeat queries into cache hits

Redis
@redis.io

➡️ How Redis Data Integration keeps agent context fresh from your source databases without manual stitching ➡️ The cold-cache vs. warm-cache latency difference, measured live. If you're building agents, or agent infrastructure, watch this today.

Redis
@redis.io

It goes deep on how to fix that using Redis Iris, our real-time context engine, and walks through building a wealth advisor agent live, from end to end. Here's what you'll learn:

View full thread
Redis
@redis.io

More upgrades: ➡️ Hash subkey notifications — subscribe to field-level events ➡️ Multiple time series aggregators in one command (hello, candlestick charts) ➡️ Explicit JSON float storage: BF16/FP16/FP32/FP64 ➡️ New COUNT aggregator for sorted set unions/intersections

View full thread
Redis
@redis.io

Rate limiting is one of the most common Redis patterns, and it used to need Lua. Not anymore. The new INCREX command gives you a window counter rate limiter natively, with bounds and expiration control built in.

Redis
@redis.io

Streams get NACKing. The new XNACK command lets consumers explicitly release pending messages, so they're immediately re-delivered to other consumers instead of sitting idle in the PEL. SILENT, FAIL, and FATAL modes map to real-world failure scenarios.

Redis
@redis.io

Redis Array: a new general-purpose data structure created by @antirez.bsky.social. Index-addressable, dynamic, sparse-friendly, and compute-aware. Fast access by index, sliding windows, and server-side SUM/MIN/MAX. Its ARRING command does ring buffers at 2x the throughput of RPUSH+LTRIM

Redis
@redis.io

Agents 🤝 Ham radio 🤝 Guy Royse—it's a match made in AI heaven. Be sure to watch Guy build Earshot, his transcription agents that captures ham radio chatter as it happens, live this Thursday, June 4 at 9am PT as part of Microsoft's VS Code Live.

Guy Royse@guy.dev

I built Earshot. Agents listen to audio (a mic and my ham radio), transcribe it, and write it to shared memory. A chatbot reads it and chats about it. The interesting bit, the agents never talk directly. They just share memory. Agent coordination is just decoupling. github.com/redis-develo...

github.comGitHub - redis-developer/redis-agent-memory-audio-capture-ts-demo: Earshot is a multi-agent demo of Redis Agent Memory: agents ingest, transcribe, curate, and recall audio from various ambient sources...Earshot is a multi-agent demo of Redis Agent Memory: agents ingest, transcribe, curate, and recall audio from various ambient sources, stored as long-term memories. - redis-developer/redis-agent-me...
Redis
@redis.io

Uber’s CacheFront serves 150M+ reads per second with 99.9%+ cache hit rates, and does it while maintaining strong consistency guarantees.

Redis
@redis.io

Their secret? Treating cache as a first-class part of the data system, not an afterthought. By integrating Redis directly into the write path, Uber tackled one of the hardest problems in distributed systems: cache invalidation at massive scale.

Redis
@redis.io

Meet "Podbot," an AI chatbot @guy.dev built using Azure OpenAI to recommend podcasts based on your preferences. It uses Redis Memory Server to manage memory, so it remembers what you like across conversations. Build your own Podbot here (and feel free to open a PR): github.com/redis-develo...

github.comGitHub - redis-developer/podcast-chatbot-with-agent-memory-azure-demo: Demo showing how to use Redis Agent Memory Server to build context-aware AI chatbots with persistent conversation memory on Azure...Demo showing how to use Redis Agent Memory Server to build context-aware AI chatbots with persistent conversation memory on Azure. - redis-developer/podcast-chatbot-with-agent-memory-azure-demo
Redis
@redis.io

Redis Open Source 8.4 is now GA. It’s faster, more scalable, and now has hybrid search. It’s the most advanced version of Redis yet, continuing our mission to make Redis faster, simpler, and more powerful.

View full thread
Redis
@redis.io

Redis Open Source 8.4 is now GA. It’s faster, more scalable, and now has hybrid search. It’s the most advanced version of Redis yet, continuing our mission to make Redis faster, simpler, and more powerful.

Redis
@redis.io

New features include: 🔎 Hybrid search: Combines full-text and vector results in one query, for more accurate AI, RAG, and semantic search. 📈 Performance improvements: Multi-threaded I/O, improved memory handling + smarter JSON storage delivers 30% higher throughput, 91% lower memory use.

Redis
@redis.io

We worked with @deeplearningai.bsky.social to create a new course called "Semantic Caching for AI Agents." Redis experts will help you build a semantic cache that makes AI agents faster and more cost-effective by recognizing when different questions mean the same thing.

View full thread
Redis
@redis.io

In this course, you'll learn how to build a semantic cache that reuses responses based on meaning, not exact text matches, as well as: • Measure cache performance • Enhance accuracy with cross-encoders & LLM validation • Build caching into an AI agent that's faster + more cost-effective over time

Redis
@redis.io

We worked with @deeplearningai.bsky.social to create a new course called "Semantic Caching for AI Agents." Redis experts will help you build a semantic cache that makes AI agents faster and more cost-effective by recognizing when different questions mean the same thing.

Redis
@redis.io

AI agents often make redundant API calls for questions that mean the same thing. Semantic caching helps your agents recognize when different queries share the same meaning, reducing costs and speeding up responses.

Redis
@redis.io

Semantic routing improves predictability and efficiency in AI systems. RedisVL classifies user queries without LLM calls, reducing token usage and latency. Combined with LangGraph, it creates a deterministic flow for routing, execution, and decision logic. Read how here: medium.com/@bhavana0405...

medium.comWhy You Need Semantic Routing in Your LangGraph Toolkit: A Beginner’s GuideNot every question needs a 175-billion-parameter LLM. Semantic routing helps decide which model, tool, or path should handle each query

Redis reposted

Raphael De Lio
@raphaeldelio.dev

🧵 1/ LLMs are stateless. They don’t remember past interactions. Every prompt is treated as an isolated request. To build actual agents, we need memory. Here’s how to do it using Spring AI and Redis — short-term + long-term memory, fully integrated. (@redis.io)

Redis reposted

Raphael De Lio
@raphaeldelio.dev

1/🤔 Have you ever heard of the Count-min Sketch data structure? We just added full support for it in Redis OM Spring — and it fits right in alongside other probabilistic data structures like Bloom and Cuckoo filters. Quick rundown 👇 cc @redis.io

Redis reposted

Raphael De Lio
@raphaeldelio.dev

1/4 Every time I present the same talk, it gets better. Sometimes because I spot things to improve. Sometimes because of great feedback from the audience. Check it out 🧵 cc @redis.io #javabubble

Redis reposted

Guy Royse
@guy.dev

Good news, everyone.

Redis@redis.io

It's a big day for us – Redis 8 is GA today. It's fast, loaded with new features, comes with the tools in Redis Stack included – and it's open source. Read more here: redis.io/blog/redis-8...

View full thread
Redis
@redis.io

▶️ New libraries including Redis vector library for GenAI use cases, open source client libraries, mapping libraries and more ▶️ Full compatibility with Redis Insight and Redis for VS Code, visual tools that let you explore data, design, develop, and optimize your apps

Redis
@redis.io

There's a ton of new stuff in Redis 8, including: ➡️ The addition of the AGPLv3 open source license ➡️ Redis Stack included – no separate download ➡️ New data structures, including vector sets, JSON, time series, and probabilistic data structures like Bloom and Cuckoo filters

Redis
@redis.io

➡️ Redis Query Engine for advanced search ➡️ Significant performance improvements: an 87% reduction in command latency, 2x more ops per second throughput via multithreading, 35% less memory use for replication, 16x more query processing power with horizontal & vertical scaling

Redis reposted

Sumit
@reachsumit.com

Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data Redis demonstrates that fine-tuning smaller embedding models on domain-specific data outperforms larger models for semantic caching. 📝 arxiv.org/abs/2504.02268

arxiv.orgAdvancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic DataThis report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching,...

Redis reposted

Guy Royse
@guy.dev

I recently joined my long-time friend @jtowermi.bsky.social on the Blue Blazes podcast to talk all things @redis.io—how it works, why it's awesome, and how devs can speed up their apps with it. J. loves Redis and, frankly, I think he just wanted to pick my brain. 🧠

Redis reposted

Raphael De Lio
@raphaeldelio.dev

I'll be talking about Vector Databases, Vector Similarity Search, RAG, and Semantic Cache tonight! All of that going around the Apollo 11 space mission! www.meetup.com/utrecht-java... #devbubble #javabubble cc @redis.io

meetup.comMonads Explained & Rediscovering Apollo 11: Using Spring AI + Redis OM Spring, Wed, Mar 12, 2025, 5:30 PM | MeetupWe are happy and very proud to announce our next meetup with Ties van de Ven and Raphael De Lio. The meetup will be hosted by Open Web. Please join us and RSVP! Because

Redis reposted

Ricardo Ferreira
@riferrei.com

Say you need to develop a solution that keeps a counter for unique elements. Your task is to choose a technology and/or an implementation pattern to make this happen. You are expected to store 100M elements, each 512KB in size. 🧵