Huge win by Kevin + team

Introducing Kortix Suna: the world’s first Open-Source General AI Agent built to work like a Human.

We've had it for a while, but AgentOps 🖇️ is now officially in the LiteLLM (YC W23) docs Huge thanks to Dwij Patel 🖇️

🔁 Memory is more than just recall - it's structure At mem0, we support a structured memory layer designed for AI agents - inspired by how humans think, learn, and adapt. Here's how we break it down: 👉 Short-term memory powers context for real-time interactions 👉 Long-term

🔔Calling all investors It's peak fundraising season and founders in your portco will heavily need warm intros. At Lobby we're automating the whole intro flow. The assistant spots intro requests in email and handles them just like you would: double opt-in if needed,

A lot of developers are focusing on AI for content creation, but not enough are looking at AI for content repurposing

Cooked up some improvements to session drilldowns. Much more info density, but still WIP Bespoke Crewai + Openai agents views are coming up

Here is everything that happened this week in AI Agents from Google, AgentOps, Descript, CamelAI, Buster, Kortix, Langchain, CrewAI, Triple Whale, Pipedream & more. 🧵 (save for later)

What’s your biggest complaint/feature request for AgentOps? Cooking this week let us know and we’ll prio

everyone says they’re building agents. very few actually know how to do it right. Alex Reibman 🖇️ and I are hosting a live series — how to build, evaluate, and scale real multi-agentic systems from scratch. this week — Agents 101 (building foundations that scale) next week — Evals

Agent Academy 🎓

Visited Emory to guest lecture Prof Pesavento’s time series analysis to chat about AI - Built an AI agent with CrewAI and AgentOps 🖇️ to help new grads find jobs - Demoed a Tavus digital twin - How Interview Coder style products will affect the new grad job market

🚨𝗪𝗲 𝗷𝘂𝘀𝘁 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝘁𝗵𝗲 𝗣𝘆𝗣𝗜 𝗽𝗮𝗰𝗸𝗮𝗴𝗲 𝗳𝗼𝗿 🏝️ 𝗢𝗔𝗦𝗜𝗦, 𝗲𝗻𝗮𝗯𝗹𝗶𝗻𝗴 𝗹𝗮𝗿𝗴𝗲-𝘀𝗰𝗮𝗹𝗲 𝘀𝗼𝗰𝗶𝗮𝗹 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻𝘀 𝗼𝗻 𝘀𝗼𝗰𝗶𝗮𝗹 𝗽𝗹𝗮𝘁𝗳𝗼𝗿𝗺𝘀 𝘄𝗶𝘁𝗵 𝗺𝗶𝗹𝗹𝗶𝗼𝗻𝘀 𝗼𝗳 𝗮𝗴𝗲𝗻𝘁𝘀 𝘄𝗶𝘁𝗵 𝗽𝗿𝗲𝗯𝘂𝗶𝗹𝘁

Today, I’m excited to share our latest research on “Building production ready AI Agents with Scalable Long-Term Memory”. We’ve achieved state-of-the-art (SOTA) performance—26% more accurate than OpenAI Memory. We evaluated Mem0 on the LOCOMO benchmark and found that it

A lot of people have been asking me about the prerequisites. The only prerequisite required is that you know beginner-level python, and have used chatGPT/any other LLM. We'll help you with the rest :)

WE. WILL. NOT. LOSE.

Zuck’s yapping We’re tapping