Zep AI
@zep_ai
Build Agents That Recall What Matters. Systematically engineer relevant context from chat history & business data. Agent Memory | Graph RAG | Context Assembly
🚀 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…
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.
🆕 Publishing our entire GraphRAG track! ft. • Mitesh Patel, @NVIDIA • Chin Keong Lam, Patho • @samjulien, Writer • @danielchalef, Zep • Ola Mabadeje, @Cisco • @tomsmoker, WhyHow • @mesirii @steveonjava @BarrasaDV, Neo4j bonus sessions released: • @jonflarson,…
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!
A great guest has joined our 29 July How to build a knowledge graph workshop: @danielchalef @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
🧠 Build autonomous AI agents that think, remember, and act. @akshay_pachaar’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…
📖 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.…
100% open-source tech stack: - @crewAIInc for building MCP ready agents - @zep_ai Graphiti to add human like memory - @Cometml Opik for observability and tracing. You can find the entire code here: github.com/patchy631/ai-e…
A Crash Course on Building AI Agents! Here's what it covers: - What is an AI agent - Connecting agents to tools - Overview of MCP - Replacing tools with MCP servers - Setting up observability and tracing All with 100% open-source tools!
Graphiti now supports @falkordb ! Build temporally-aware #GraphRAG using FalkorDB's super-fast database! Thanks to the FalkorDB team for their awesome work here!
Graphiti + FalkorDB = 💜 Graphiti builds temporally-aware knowledge graphs that represent evolving relationships between entities over time, a perfect fit for FalkorDB! Check them out! eu1.hubs.ly/H0lwXr60 @danielchalef @zep_ai
13/ @akshay_pachaar shared a quick demo of what they're building! Tech stack: - @zep_ai for the memory layer to AI agent - @Microsoft AutoGen for agent orchestration - @Ollama to locally serve Qwen3 x.com/akshay_pachaar…
Before we dive in, here's a quick demo of what we're building! Tech stack: - @zep_ai for the memory layer to AI agent - @Microsoft AutoGen for agent orchestration - @Ollama to locally serve Qwen3 Let's go! 🚀
Excited to be working with with the Cisco @outshiftbycisco team on building standards for AI Agent interoperability! 🚀
#AGNTCY is creating the specs, code and services that form foundational tech for the #InternetOfAgents, the next major platform paradigm shift. Scroll below for quotes from: 🔹@duosec (@Cisco) 🔸@zep_ai 🔹@Superbo_ai 🔸@Smyth_OS 🔹@Cometml 🔸Pattern Agentic 🔹Agent Overlay
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👇
🧠 The "𝗣𝗼𝗿𝘁𝗮𝗯𝗹𝗲 𝗠𝗲𝗺𝗼𝗿𝘆 𝗪𝗮𝗹𝗹𝗲𝘁" for AI sounds compelling: your preferences, traits, and accumulated knowledge seamlessly following you across agents. But it's fundamentally flawed. 📊 The Four Fatal Problems: ➡️ 𝗘𝗰𝗼𝗻𝗼𝗺𝗶𝗰 𝗥𝗲𝗮𝗹𝗶𝘁𝘆 - AI companies…