Brian Sam-Bodden @bsbodden

I’ve been experimenting with #GOAP in the context of Agents, mainly with Embabel. Since I also have a lot of projects on #LangGraph, I wanted to try to GOAPify some of them, so I put together a GOAP framework extension for LangGraph, aptly named LangGOAP github.com/LangGOAP/LangG…

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)

Starting in 5 minutes: Secrets of Agentic Memory Management With Brian Sam-Bodden (@bsbodden @Redisinc) Learn how to give AI agents continuity, personalization & depth in Java. Tune in → jdconf.com #JDConf #Java

@bsbodden is live now!

The future belongs to developers who understand AI—not just use it. Don’t miss @bsbodden's keynote at #ArcOfAI: a decade of AI breakthroughs distilled into the insights that matter today. arcofai.com/speaker/355822… 🎟️ Tickets: arcofai.com #AI #LLM #Developer #GenAI

Your AI agent forgets everything between calls. That's a problem when users expect continuity. @bsbodden @Redisinc dives into short-term vs long-term agent memory, semantic retrieval, deduplication, and how MCP exposes memory. #JDConf | Free | April 8-9 jdconf.com

Join @bsbodden and me today, to discuss AI agent memory and how we do it at @cognee_ with @Redisinc

Did a thing... It wasn't easy, but it was worth it!

@devnexus My presentation slides for devnexus.com/events/design-… can be found here github.com/bsbodden/desig… (along with the code)

The future belongs to developers who understand AI—not just use it. Don’t miss @bsbodden's keynote at #ArcOfAI: a decade of AI breakthroughs distilled into the insights that matter today. arcofai.com/speaker/355822… 🎟️ Tickets: arcofai.com #AI #LLM #Developer #GenAI

🤖 Less hype. More engineering. The AI Engineering Track at Devnexus is all about building real, production-ready AI systems with Java, agents, and modern architecture. 🔗 devnexus.com/schedule/ai Here’s what’s coming in the AI Engineering Track: • Design Patterns for Multi-Agent Systems — @bsbodden • Brokk: an AI-Native Code Platform for Java, in Java — @spyced • Fundamentals of Software Engineering in the Age of AI — @ntschutta & @therealdanvega • Hands-on Embabel — @springrod • The Evolution of Memory in Humans and AI Agents — @raphaeldelio • GraphContext: Connecting the Dots with Graphs — @steveonjava • The Missing Protocol: How MCP Bridges LLMs and Data Streams — @gamussa • Agentic AI for Java Microservices: Cloud Performance Optimization at FinTech Scale — @sibaspadhi • Stop Fighting Your AI: Engineering Prompts That Actually Work — @martinrojas • AI Agents for Java Devs: From Demo to Deployment — @bbenz This is one of 11 tracks at Devnexus — designed for engineers who want to stay relevant, competitive, and ahead as AI reshapes software development. 🚀 Don’t just learn about AI — learn how to engineer it. 🎟️ Secure your ticket and build the skills that will define the next generation of software. devnexus.com Sign up to keep up to date with all the conference info atlj.ug/Xconnect #AIEngineering #Java #SpringFramework #JavaDevelopers #SoftwareArchitecture #AI #TechConference #DevCommunity #Cloud #AI

Excited for #JCON EUROPE 2026? See @bsbodden at #JCON2026 in Cologne talking about 'Design Patterns for Multi-Agent Systems' Teams building #AI beyond a single #prompt now choose among different … 🎟️ 2026.europe.jcon.one/tickets Free for #JUG members

The future is agentic. Beyond @riferrei's deep dive into AI memory, we have @bibryam on Durable Agents and a workshop on Multi-Agent Systems with @raphaeldelio & @bsbodden. Plus, Ramanpreet Singh Khinda on privacy-first SDKs!

keyboard_arrow_left Previous keyboard_arrow_right Next

Are those @DevoxxUK speakers I see? Narrowing down hundreds of incredible submissions is never easy, but the 2026 lineup is already looking like one of our strongest 𝑺𝒑𝒆𝒂𝒌𝒆𝒓𝒔: Check your emails 𝐀𝐭𝐭𝐞𝐧𝐝𝐞𝐞𝐬: See the first batch of speakers & secure your ticket

🤖 Introducing the Devnexus AI Engineering Track AI is changing how software is built. The AI Engineering Track at Devnexus gives developers, architects, and engineering leaders practical guidance for building real, production-ready AI systems — with a strong focus on Java, architecture, agents, and performance. Here’s what’s coming in the AI Engineering Track: • Design Patterns for Multi-Agent Systems — @bsbodden • Brokk: an AI-Native Code Platform for Java, in Java — @spyced • Fundamentals of Software Engineering in the Age of AI — @ntschutta & @therealdanvega • Hands-on Embabel — @springrod • The Evolution of Memory in Humans and AI Agents — @raphaeldelio • GraphContext: Connecting the Dots with Graphs — @steveonjava • The Missing Protocol: How MCP Bridges LLMs and Data Streams — @gamussa • Agentic AI for Java Microservices: Cloud Performance Optimization at FinTech Scale — @sibaspadhi • Stop Fighting Your AI: Engineering Prompts That Actually Work — @martinrojas • AI Agents for Java Devs: From Demo to Deployment — @bbenz This is one of 11 tracks at Devnexus — designed for engineers who want to stay relevant, competitive, and ahead as AI reshapes software development. 🚀 Don’t just learn about AI — learn how to engineer it. 🎟️ Secure your ticket and build the skills that will define the next generation of software. devnexus.com Sign up to keep up to date with all the conference info atlj.ug/Xconnect #Devnexus #AIEngineering #Java #SpringFramework #JavaDevelopers #SoftwareArchitecture #AI #TechConference #DevCommunity #Cloud #AI

This new graph DB is 496x faster than Neo4j! (open-source) Let me break down why: A traditional graph DB stores two things: nodes (entities) and edges (relationships between them). When you query a traditional graph DB, it traverses by "pointer chasing": → Start at a node → Follow a pointer to the connected node → Follow another pointer → Repeat This is inherently sequential. One hop at a time. And as your graph grows, this gets painfully slow. FalkorDB asks a different question: What if we represent the entire graph as a matrix? Here's how it works: Imagine a simple grid. Rows are source nodes, columns are destination nodes. If Mary follows Bob, you set position [Mary, Bob] = 1. That's it. Your entire graph is now a matrix of 1s and 0s. Let's call this the Follows matrix (F). Here's where it gets interesting: Finding who Mary’s friends follow? In a traditional graph DB, you hop twice: Mary → friends → friends’ friends. But with matrices, you multiply the Follows matrix by itself: F × F = F². This takes just one operation, and you’re done! Similarly, a complex pattern like “A follows B, B likes C” becomes: Follows × Likes. This means you can represent traversal as math operations. Why this matters: - Matrix operations have been optimized for 50+ years - Modern hardware (CPUs/GPUs) is built to crunch matrices - Operations run in parallel (pointer-chasing simply cannot) While there are a few more optimizations involved (like using sparse matrices, written in C, etc.), this approach makes FalkorDB 496x faster than Neo4j. The graphic below shows this difference clearly. Traditional graph DBs go through Cypher QL → Pointer-Based Traversal, while FalkorDB uses a Matrix-Aware Planner that converts queries into matrix operations. FalkorDB is built entirely on this principle: - Native Redis module (in-memory, ultra-fast) - Powered by GraphBLAS for sparse matrix operations - Auto-translates Cypher queries into matrix algebra This is hugely important for AI applications because… Modern AI agents and RAG systems need to traverse complex relationships in real-time. When an agent reasons through a knowledge graph, connecting users to actions to outcomes, every millisecond of latency compounds. Vector DBs capture semantic similarity. But they miss explicit relationships. Knowledge graphs fill that gap. And when your agent needs to perform multi-hop reasoning across thousands of connected entities, matrix-based traversal makes it easier to scale your AI application without running into latency bottlenecks. FalkorDB is 100% open-source, and you can see the full implementation on GitHub and try it yourself. I've shared a link to their GitHub repo in the replies.

@wjgilmore @guyroyse Oh yeah! Must get... now...

@therealdanvega I would have gone with DanOS

📢#Java 25 is now available!📢 Your: ☕️ FREE ☕️ Multi-platform ☕️ Open source ☕️ Production ready ☕️ Binary release ...made available by @Oracle. Learn more ➡️ blogs.oracle.com/java/post/the-… #Java25 #JDK25 #OpenJDK

How did Java go from applets to #SpringData & vector #Databases? From EJBs to JPA, the tools have evolved. What’s next in a world of #AI & #VectorSearch? @RaphaelDeLio & @bsbodden explore the journey ahead. Read now: javapro.io/2025/05/21/a-l… #SpringAI #SQL @sunmicrosystems @IBM