The Scots have arrived in Massachusetts for World Cup and they are playing bagpipes at 6:30 am to get ready

it's faster than ever to build agentic memory across your enterprise!

Why it matters: ⚡ Faster than ingesting items one at a time 📦 Up to 50,000 items per batch 🔌 Runs separately from real-time ingestion 👀 Track status, progress, and per-item errors in a new dashboard

still in my first month at @zep_ai and it's been fascinating seeing how enterprises are using it to solve agentic memory and context at scale. great writeup @akshay_pachaar !

Fuck it, $RVI Much shade at the IPO, similar to USVC. Prefer this route.

Agents need more than one kind of context to actually help users. Zep produces 5 distinct types in every Context Block: facts, entities, episodes, thread summaries, and the user summary. Each captures something the others can't. Here's what each is for 🧵

When your agent acts on bad context, the first question is: where did that come from? Most context systems don't track this. Zep does, enabling: → Audit trails from response to source → Inspectable debugging paths → Agents scoping their own context by source Here's how 🧵

anthropic running the exact same marketing playbook with every release. “our model is so capable and dangerous, ahh we are afraid to release it”. just put the model in the bag lil bro.

so let me get this straight all of ai twitter was telling people to buy a mac mini to run openclaw, which is literally just a framework, an orchestration layer that sends api requests to actual ai models. something you can run on a $5/month vps. which is exactly what i do btw but when google drops gemma 4, an actual large language model that you can run and fine-tune locally on that same mac mini, with no api costs, no subscriptions, no third party dependencies, completely yours under apache 2.0 the ai community is silent you were buying $800 hardware to run a wrapper but ignoring the actual ai model that would justify that hardware this tells you everything you need to know about the average iq of ai twitter

I had old coworkers who would signal whenever they were restarting their computers it drove me crazy

Meet Zookeeper, our conversational CAD agent. ✨

made this dog house for my great dane in our app using only the in-app agent & codex our mcp server, going to actually build it! it perfectly fits his therapeutic bed

growing up is realizing balaji, naval et al are basically retarded

hang this photo of Amen Thompson in the louvre 🖼️

JABARI SMITH JR BLOCK AMEN THOMPSON DUNK THE ROCKETS ARE ROLLING. 🔥🔥🔥

Core.

A dentist but the tooth water isn’t piped straight from the runoff of a glacier

An introspective emo war bro tries to kill himself, accidentally survives (which subsequently helps win the battle), is awarded the badass horse he didn’t ride in on, then self-deploys to the frontier at his own behest. And proceeds to dance… with fucking wolves 🫡

“HoW dO u KnOw If YoUr CEO cArEs AbOuT u?” She posts, unprovoked, in #general at night to let the entire company know she took it upon herself to research the entire tweet history of both my accounts to validate my use of the emdash THAT’S how I know 🥲

PREACH