Updated my local AI repo to use @dhh's #Omarchy Linux (optimized for agentic work with local models running on @FrameworkPuter Desktop) github.com/johnymontana/loca…

"Memory records what happened. An ontology turns what happened into knowledge. Distillation turns that knowledge into something an agent can run." This weekend's favorite read is @lyonwj on agent memory and skill distillation. neo4j.com/blog/genai/from-ag…

Persistent memory gives agents a record of what happened. But it is not the same as knowing what to do next time. The #Neo4j Agent Memory Service (NAMS) closes that gap with skill distillation: taking a scoped slice of a workspace's memory graph and turning it into a portable SKILL. md package the next agent can load and run. Not a summar: a procedure grounded in what actually worked, with provenance attached and a governance loop that keeps it honest as the underlying memory evolves. Skill distillation produces knowledge your agents can act on. Read the details by @lyonwj and try it now: bit.ly/4i2pUBR #skill #agentmemory

The @Neo4j Agent Memory Service (NAMS) recently added skill distillation and governance. Portable actionable knowledge distilled from your org's actual observed agent memory, driven by a domain specific ontology. Read more about it here: neo4j.com/blog/genai/from-ag…

If your AI agents reset every session, they are not learning. They are just repeating. @lyonwj recorded a session on exactly this problem: why most agents are still stateless, what breaks in production as a result, and how memory and context graphs fundamentally change the architecture. The full session also covers practical design patterns, the most common pitfalls when implementing memory, and integration approaches for Salesforce Agentforce, Databricks, and major cloud providers. 30 minutes. Watch on demand in the link: bit.ly/4dBPQ3h

This post by @BarrasaDV is one of the best posts on real-world AI in the enterprise I've read this year. As the AI Field CTO at Neo4j he's worked with hundreds of organizations to do agents at enterprise scale, and there's a clear pattern emerging. Let me summarize! 🧵👇

Going Meta S03E09 – a Series on Semantics, Knowledge Graphs and All Things AI nitter.siddz.com/i/broadcasts/1dGYllLLa…

Excited to launch @neo4j Virtual Graph 🚀 Graph reasoning directly on enterprise data. no ETL, no copies, Cypher pushed into Any Lakehouse. Helping make enterprise data accessible to AI agents. lnkd.in/eeSTkaCP #GraphAI #EnterpriseAI #AIAgents #Snowflake #Databricks

Did you miss the webinar "Three Memory Types Every Production #AI Agent Needs" - here it is! @lyonwj bit.ly/41UdqTF

You are gonna like this webinar! @lyonwj invites you to join him on June 4 to tackle one of the most common frustrations in production #AI: agents that work great in demos but lose all context the moment a session ends 😒 Will will walk you through #ContextGraphs and persistent memory and will show you practical patterns for working with Salesforce Agentforce, #Databricks, and major cloud providers. Europe: bit.ly/4dy9FbS Americas: bit.ly/4fAPexz Asia Pacific: bit.ly/4nHb0Sl #Neo4j

⭐ create-context-graph, the Neo4j Labs CLI that scaffolds a complete full-stack context graph agent app in one command: FastAPI backend, Next.js front-end with live graph visualization, and an AI agent wired to three types of memory through #Neo4j. One command generates a complete, working full-stack application: uvx create-context-graph ➕ Connect to your Linear workspace or your Claude Code session history and ask questions you couldn't answer before. Get started now: bit.ly/4npcFvO with @lyonwj

[new blog post] Introducing Create Context Graph: AI Agents With Graph Memory, Scaffolded In Seconds with uvx create-context-graph medium.com/neo4j/introducing…

What's an #Agent? Short and clear by @lyonwj in an interview with @WeAreDevs

Insightful Context Graph Panel coming up next week at #NodesAI! @akoratana, CEO of PlayerZero; and @forgerock1, CEO of @Indykite, will join #Neo4j's @emileifrem, @prathle and @lyonwj on a panel discussion about how #ContextGraphs are emerging as a new foundation for #AI systems that can reason, learn, and improve over time. Join us at #NodesAI on April 15 - this live event has a super cool agenda. Check it out and register today: bit.ly/4sqjuOZ

Microsoft Agent Framework + #Neo4j + neo4j-agent-memory library is all you need to build a conversational AI Agent. A practical blog to discover how the TfL Explorer, a London transport assistant, is built ✔️ Short-term conversational context, long-term entity and preference storage, and reasoning trace retrieval, all without blocking your response stream, is possible. Check it out: find the code and resources here, bit.ly/4dEmZ02 All by @lyonwj- our memory graph expert. #ContextGraphs

🚀 Contest alert!! We launched #Neo4j #AuraAgents to help you build and deploy AI agents grounded in your knowledge graph in minutes. No frameworks. No infra. Just your data. To celebrate, for the next 24 hours, we are giving away Aura credits to help you build your first agent! Participate and be one of the winners! 🔁 Repost 💬 Tell us what you want to build 👋 Tag @Neo4j - We’ll DM you! We have 5K in credits to share among participants! Don't miss this opportunity!

Yes. And an amazing way to get started with 22 industry domains out of the box: create-context-graph.dev/