The People Who Train AI Built Their Own Agent
Nous Research released Hermes Agent, an open-source agent that doesn't just answer questions; it remembers what it learns and builds its own skills over time. Every conversation becomes potential training data. Hermes Agent routes tasks to different models (including local ones), works across Telegram, Discord, Slack, and CLI from a single gateway, and stores conversations as reusable skill documents. The self-improving loop is the part that got my attention. LEARN OPENCLAW I'm hosting an exclusive in-person OpenClaw Bootcamp with Alex Finn. Small group. Hands-on. Everything from setup to advanced workflows. Seats are extremely limited. Join the waitlist: https://startmy.ai Join our Discord: https://rfer.me/discord GET THE TOOLS Hermes Agent: https://github.com/NousResearch/hermes-agent Nous Research: https://nousresearch.com Nous Portal: https://portal.nousresearch.com Key moments 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview CONNECT WITH RAY X (Twitter): https://x.com/RayFernando1337 #HermesAgent #NousResearch #AIAgent #AICoding #LocalAI #OpenSource #Programming
