AI News Today | Julian Goldie Podcast

Claude + Hermes + Paperclip is INSANE!

18 min · 20. juni 2026
episode Claude + Hermes + Paperclip is INSANE! cover

Beskrivelse

Build the Ultimate AI Agent OS with Hermes & Claude Learn how to build and optimize your own Agent Operating System to orchestrate AI agents for business automation. This guide covers local AI models, loop engineering for quality control, and strategies for multi-model flexibility. 00:00 - Intro: What is an Agent OS? 02:23 - SEO Workflows for Clients 05:06 - Safely Installing AI Skills 06:13 - Running Local AI Models 07:32 - Hermes Desktop Versions Compared 09:41 - Building Antifragile Systems 11:17 - Loop Engineering for Quality 12:52 - Agent Memory with Obsidian

Kommentarer

0

Vær den første til at kommentere

Tilmeld dig nu og bliv en del af AI News Today | Julian Goldie Podcast-fællesskabet!

Kom i gang

1 måned kun 9 kr.

Derefter 99 kr. / måned · Opsig når som helst.

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts

Alle episoder

556 episoder

episode OmniRoute: New FREE Unlimited AI Coder! cover

OmniRoute: New FREE Unlimited AI Coder!

OmniRoute: Code with AI for Free Forever (90 Free Providers + Auto Fallback + Token Savings)This episode demos OmniRoute, a free open-source AI gateway that lets coding tools like Claude Code and Cursor route through a single local endpoint to 237 providers, including 90 that are free forever, with automatic fallback when limits are hit. The presenter shows OmniRoute generating projects (an animated star field, a to-do list app, a virtual keyboard, and a landing page) with code and live previews, and highlights token-minimization that can cut usage by 15–95%. Setup is shown as quick via simple terminal commands, runs across 42 languages, and supports variants like auto/fast and auto/coding plus 17 routing strategies including Fusion. The video also explains how OmniRoute is integrated into an Agent OS “free coding engine” with saving/visualizing builds, and closes by promoting the AI Profit Boardroom community, trainings, and coaching calls.00:00 [https://www.youtube.com/watch?v=EOfn7O8HV0s] OmniRoute Overview01:10 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=70s] Setup in Agent OS01:40 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=100s] Quick Install Steps01:59 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=119s] Building a To-Do App02:17 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=137s] Why Free Tiers Fail03:09 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=189s] Key Benefits Recap03:22 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=202s] Five Layer Routing04:01 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=241s] Speed Demo Build04:56 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=296s] Provider Disappear Fallback05:35 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=335s] Models and Routing Modes06:07 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=367s] Fusion Strategy Explained06:33 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=393s] Full Agent OS Pitch07:01 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=421s] Community and Training07:44 [https://www.youtube.com/watch?v=EOfn7O8HV0s&t=464s] How to Join and Outro

5. juli 20267 min
episode A1 Agent: New FREE Chinese AI is INSANE! cover

A1 Agent: New FREE Chinese AI is INSANE!

Agent A1: New Free Local Chinese Agentic Model (35B MoE) + Benchmarks, Speed & SetupThe video reviews Agent A1, a newly released free Chinese local model designed for agentic tasks, showing it running privately and offline inside an Agent Factory workflow alongside free Claude code. The host demos outputs like a landing page, a neon snake game, a “Dragon Realm” open-world game, a keyboard mini app, and a 3D solar system visualization, noting fast replies and that builds save to a workspace with optional voice control. Agent A1 is a 35B mixture-of-experts model (3B active) with a 256k context window, created by Intern Science in Shanghai and optimized for long-horizon search, engineering, scientific research, instruction following, and tool calling. It ranks #2 on the creator’s local leaderboard, outperforming Gemma 4 but trailing Qwable, and is reported around 95 tokens/sec locally on a Mac Studio M4. The video explains strengths/weaknesses, shows running via Ollama and configuring Hermes profiles, and promotes an Agent OS bundle plus OmniRoute routing across 90 free models.00:00 [https://www.youtube.com/watch?v=6z2fE0x8U8I] Meet Agent A100:31 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=31s] Live Local Build Demo00:53 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=53s] Leaderboard And Examples01:36 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=96s] What A1 Actually Is02:29 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=149s] Benchmarks Breakdown03:08 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=188s] More Builds In Action03:45 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=225s] Specs Speed And Context04:40 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=280s] How To Run Locally04:43 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=283s] Strengths And Weaknesses05:41 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=341s] Hermes Setup Steps06:13 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=373s] Agent OS And OmniRoute06:51 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=411s] Get The Full Setup07:34 [https://www.youtube.com/watch?v=6z2fE0x8U8I&t=454s] Wrap Up

5. juli 20267 min
episode Stop Paying For AI...Do This Instead! cover

Stop Paying For AI...Do This Instead!

Cut 65–69% of Tokens with Claude Code (and Any AI Agent) Using CavemanThe script explains a free, open-source “Caveman” skill that reduces output tokens for Claude Code and other agents (Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and more) by making responses short, blunt, and direct while keeping code, commands, file paths, and error messages unchanged. Installed via a one-line command, it drops a rules text file into each agent’s skills/plugin folder so the agent reads it at the start of every chat. Tests on Fable 5 using five real prompts showed about 69% fewer output tokens (e.g., 1,349 down to 324) and about 37% lower total cost while keeping answers correct; it can be toggled with /caveman and set to light/full/ultra, plus optional tools like Commit/Review/Compress. The video also promotes using Caveman across an agent operating system for compounding savings and mentions the AI Profit Ballroom community and training.00:00 [https://www.youtube.com/watch?v=QNM3lDfaAEc] Cut Tokens With Caveman01:16 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=76s] Why Token Costs Hurt01:58 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=118s] How Caveman Works02:21 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=141s] Rules And Safety03:06 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=186s] Does Shorter Mean Worse04:00 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=240s] Install Across Agents05:03 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=303s] Real Token Savings Tests07:29 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=449s] Old Replies Vs New08:49 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=529s] Modes And Commands09:47 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=587s] Agent OS And Extras10:30 [https://www.youtube.com/watch?v=QNM3lDfaAEc&t=630s] Join The Community11:29 Wrap Up

5. juli 202611 min