2️⃣ Graphiti MCP server Agents forget everything after each task. Graphiti MCP server lets Agents build and query temporally-aware knowledge graphs, which act as an Agent's memory! Check this👇

🤓 RAG are powerful. They allow you to search your own knowledge base and extend your AI system with your own data. A RAG injects relevant context into the context window tailored to your domain. But most RAG setups are static. They require manual update, it is slow and

Temporal memory from Zep AI is super interesting, seems like the missing piece for agent knowledge storage

Today, we'll add a common memory layer to Claude Desktop and Cursor so users can cross-operate without losing context. Our tech stack: - Zep AI Graphiti MCP as a memory layer for AI Agents. - Cursor and Claude as the MCP hosts. Let's begin!

Super honored to be voted one of their best speakers at AI Engineer 2025! 🎉 Thanks to swyx and team for organizing such a fantastic event. 💙 If you missed this year, def make a plan to attend next year’s event!

Build an MCP-powered shared memory for all your AI apps! Using real-time knowledge graphs! 🧠 (switch apps, not the context)

The Daily Dose of Data Science guys are awesome! You should subscribe! (and I love that they build stuff with Zep AI and Graphiti ❤️)

Another awesome product round-up from the Zep AI team!

the only primitives that should be shared across most AI agents: durable execution, memory, and observability. the argument is simple: the best AI apps aren't using frameworks. don't let artificial constraints or abstractions built by someone else impact your product direction.

1️⃣ Graphiti MCP server Agents forget everything after each task. Graphiti MCP server lets Agents build and query temporally-aware knowledge graphs, which act as an Agent's memory! Check this👇

Context engineering is replacing "prompt engineering" — and it's about time 🚀 ➡️ The industry is shifting from prompt hacking to building production systems that actually work. 🎯 Context engineering = dynamic systems that feed LLMs exactly what they need, when they need it 📈

Excited to be working with with the Cisco Outshift by Cisco team on building standards for AI Agent interoperability! 🚀

Graphiti now supports falkordb ! Build temporally-aware #GraphRAG using FalkorDB's super-fast database! Thanks to the FalkorDB team for their awesome work here!

CrewAI Zep AI Comet Here's an overview of the system we're building! - User sends a query - Assistant runs web search via MCP - Query + results go to Memory Manager - Memory Manager stores context in Graphiti - Response agent crafts the final answer

Build agents with human-like memory 🧠! Another awesome tutorial from the awesome Akshay 🚀 ! Check it out! 🔥