MMorty
AI agent architecture, Jev decision layer and agent course roundups
Posts about multi-agent systems: swarms, agent loops, routing and evals, often as build logs with step-by-step numbers. A large share promotes Jev and Kimi K3, with long X Articles on Jev Engineering and agent swarms. Also shares timestamped video course roundups attributed to Karpathy, Andrew Ng, Google engineers and lab CEOs.
aiagentsdevverified
4.1kfollowers
3.7kviews per post
$100cheapest service
24 hanswers in
154kviews on record
writes for English-speaking builders and AI-curious readers interested in agents, LLM costs and orchestration · Worldwide, in English
what they post about
share of their 40 recent postsJev and Kimi promos45%
AI agent course roundups40%
Agent build logs15%
what you can buy
prices are per publicationSponsored postA post about you in their feed, written in their own voice.
ready in 3 days · 1 revision included · you get: link to the live post and the numbers 24 h after it goes out.
Long-form X articleA long piece on X — the format people find later, not only in the timeline.
ready in 7 days · 1 revision included · you get: link to the live post and the numbers 24 h after it goes out.
what usually flies
their posts by reach · 153,944 views on recordJev Engineering for Swarms: How Jev Decides and Kimi's 300 Agents Execute21 sep 26 · x post66kviews117likessee it →How to Build a 24/7 AI Employee With K3, Plus a 300-Agent Team on Call. 28 sep 26 · x post36kviews68likessee it →Jev doesn’t make the LLM smarter. it makes 193x faster. 444x cheaperand testable Jev could be the missing decision layer between LLM reasoning and real-world ag19 sep 26 · x post31kviews385likessee it →Andrew Ng just released a 1-hour course on building Agentic Systems from scratch: • 00:00 - Introduction to agentic knowledge • 14:00 - Architecture of multi-ag1 oct 26 · x post8.8kviews109likessee it →I just built a Jev X Self-Improving Agent. 12% → 88% success. 29 seconds. $0.02. Zero fine-tuning. Same agent. Same model weights. 50 attempts at a hostile chec22 sep 26 · x post6.6kviews79likessee it →Ex-Google Senior engineer explained AI agent loops, harness, evals in 20 minutes - better than 5000$ courses. trace every run → judge it with an LLM → diagnose 26 sep 26 · x post6.3kviews64likessee it → Prices are set by the celeb. Money sits in escrow and is released after the publication goes live — otherwise it’s refunded.