📖 New MCP (Model Context Protocol) guidebook from the Daily Dose of Data Science team covers practical implementation patterns across 11 hands-on projects. Really solid coverage of building local MCP clients, agentic RAG systems, voice agents, and shared memory implementations.

🧠 Build autonomous AI agents that think, remember, and act. Akshay 🚀’s new crash course walks through: ✅ Tool integration via MCP servers ✅ Memory with Zep’s Graphiti ✅ Tracing and observability with Comet’s Opik All orchestrated with CrewAI — and fully

real-time knowledge graphs for AI agents

A great guest has joined our 29 July How to build a knowledge graph workshop: Daniel Chalef Zep AI (Graphiti) founder! What you can expect: ▪️ Q&A with Roi Lipman (CTO), Gal Shubeli (GraphRAG-SDK Dev.) and Daniel Chalef (ZEP ▪️ Graphiti introduction eu1.hubs.ly/H0lMl3F0

looks like graphiti by Zep AI is getting some love in the AI memory space, with their temporary aware knowledge graphs (14k stars) now faster with falkordb integration!

🆕 Publishing our entire GraphRAG track! ft. • Mitesh Patel, @NVIDIA • Chin Keong Lam, Patho • Sam Julien, Writer • Daniel Chalef, Zep • Ola Mabadeje, Cisco • Tom Smoker, WhyHow • Michael Hunger 🇪🇺 🇺🇦 @[email protected] Stephen Chin Jesús Barrasa, Neo4j bonus sessions released: • @jonflarson,

Read the Zep paper yesterday. One of the most complex papers I've read around memory, made me feel very stupid. Really liked their implementation of a bitemporal model and also the hierarchical graphs are just top tier thinking.

🚀 MILESTONE ALERT: Graphiti just hit 15K GitHub stars! 🥳 In under 6 months, Zep AI (YC W24) knowledge graph framework for AI agents has grown from 2K to 15K+ stars — that's a 650% increase! 📈 🤯 This incredible momentum is all thanks to our amazing community who've been

Reminder: How to build a knowledge graph workshop w/ Daniel Chalef from Zep AI Tomorrow (29 July) over Zoom! ▪️ Q&A ▪️ Practical knowledge graph construction from diverse data sources ▪️ Graphiti introduction Sign up: eu1.hubs.ly/H0m1lk40 (we'll send the recording link)

Another great demo of Zep AI Graphiti in action! 🧠 Very cool video! Thanks for sharing, Avi Chawla ! 💙

Daniel Chalef Zep AI Avi Chawla I connected @Zep_ai to my Claude Desktop and it really changes the way of interacting. I finally have a conversational memory. Graphiti is really super and very cheap because connected to Openai. The speed and the quality of the research is really impressive. 🚀

okay this Zep memory approach solves the exact problems that broke mario for months when we built erika, ava, mario - context management was the nightmare traditional approaches: load everything → hit token limits → lose critical info zep's temporal knowledge graph? this is the

Lee Robinson I use MCP servers literally every day for the things surrounding writing code. Not necessarily to write code. Love MCPs for making a Jira ticket, getting latest docs in Context7, Graphiti memory can be a great way to hand off work from one dev to the next, etc.

This tutorial(on YouTube) will teach you how to choose and set up the right memory node for your n8n AI agents - covering simple memory, Zep, Redis, Postgres, and MongoDB with full setup guides and when to use each one

Graphiti (Zep AI) simplifies building knowledge graphs with real-time, temporal data support. Perfect for LLM agents and advanced RAG pipelines, it integrates seamlessly with FalkorDB. Missed our workshop? Check the recording and Google Colab demo in the comments!