New Grok Build is ABSURD!

Laguna XS 2.1: New FREE + Opensource Local AI!

Laguna XS 2.1: New Local Agentic Coding Model (Benchmarks, Demos, Setup Options)Julian tests the newly released Laguna XS 2.1 local agentic coding model from Poolside, highlighting its speed, lightweight setup, 256K context window, and availability on Hugging Face. He compares benchmark results (including SWE-bench) against Qwen 3.6, North Mini Code, Claude Haiku 4.5, and GPT-OSS, then demonstrates real outputs: a clean landing page, a functional to-do app, and another simple page, noting UI limitations but solid working code. He shares his hardware setup (Mac Studio M4 Max, 36GB) and plans to run broader evaluations on Goldie Bench. He explains ways to use the model via Agent OS local engine, Free Claude Code, or Hermes agent profiles, plus offline privacy benefits and a free OpenRouter API option.00:00 [https://www.youtube.com/watch?v=WHdfspBEdyk] Laguna XS 2.1 Intro00:26 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=26s] Benchmarks Breakdown02:20 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=140s] Real World Builds02:47 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=167s] Landing Page Demo03:16 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=196s] To Do App Test04:18 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=258s] Setup and Limits04:33 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=273s] Goldie Bench Plans05:24 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=324s] Ways to Use It06:19 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=379s] Offline and Privacy06:50 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=410s] OpenRouter Free API07:26 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=446s] Hermes Terminal Setup07:57 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=477s] Wrap Up and Next Tests08:05 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=485s] Agent OS and Boardroom09:11 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=551s] Community Examples10:41 [https://www.youtube.com/watch?v=WHdfspBEdyk&t=641s] Final Thanks

Gemma 4 is now 90% FASTER + FREE + Local 🤯

Gemma 4 Just Got Up to 90% Faster on Mac (Ollama + MLX)Google’s Gemma 4 has a new update that makes it up to nearly 90% faster on a Mac when run through Ollama using MLX, enabling much faster local model performance. The script explains that Gemma 4 is free on Ollama and MLX is a free open-source project, and that Ollama now supports MLX models directly so you can install via a simple command after updating. The creator reports seeing roughly 60% faster speeds in many tests, with a jump from about 50 to 95 tokens/sec in a shown comparison, and says coding prompts can hit the 90% boost. They also show Gemma 4 integrated into their Agent OS (with Hermes), letting it build and preview simple apps locally and autonomously.00:00 [https://www.youtube.com/watch?v=cTXdg-V4MII] Gemma 4 Speed Boost00:49 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=49s] MLX and Ollama Setup01:58 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=118s] Agent OS Integration02:33 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=153s] Real Speed Benchmarks04:07 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=247s] Live Build Demo05:27 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=327s] Why It Runs Faster05:56 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=356s] Install in Terminal06:13 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=373s] Projects Built With Gemma07:25 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=445s] Limits and Best Uses07:56 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=476s] Free Local Builds Anytime08:41 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=521s] Agent OS and Boardroom Pitch09:43 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=583s] Community and Support Features10:13 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=613s] What Members Are Building10:41 [https://www.youtube.com/watch?v=cTXdg-V4MII&t=641s] Wrap Up and Thanks

How to Run Hermes FREE Forever!

Run Hermes Free Forever: Gemma 4 MLX Update Makes It Up to 90% Faster (Ollama + Apple Silicon)Julian demonstrates how to run Hermes for free using a new Gemma 4 update with Ollama on Apple Silicon via MLX, claiming up to 90–95% faster local performance compared to before. He shows Gemma 4 set up as a free profile inside an agent OS, with examples like quickly responding to prompts, building a simple to‑do list app, and using Hermes’s /learn command to turn a tutorial into a reusable skill that runs in the background. For non‑Mac users, he notes an alternative: using a free OpenRouter API option for the 31B model. He explains that local models keep workflows private, offline, and suitable for long-running agent loops without token or subscription costs, and he briefly outlines setup by updating Ollama and selecting the newer MOX Gemma 4 models.00:00 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg] Run Hermes Free Faster00:33 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=33s] Agent OS Demo Setup01:14 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=74s] Free API Alternative02:08 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=128s] Hermes Learn Skill03:40 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=220s] Install Ollama Gemma05:20 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=320s] Loops and Subagents06:55 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=415s] Local Loop Engine08:05 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=485s] Easy Commands Objections08:58 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=538s] Wrap Up and Offer09:20 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=560s] Boardroom Walkthrough10:35 [https://www.youtube.com/watch?v=u_qZ5Q9jhYg&t=635s] Final Thanks

Claude Code is now FREE: Here’s how…

Use Claude Code Free Forever with Gemma 4 (90% Faster Local AI on Apple Silicon)The video explains how to run Claude Code for free by pointing the Claude Code CLI at Google’s Gemma 4 model, highlighting a new update that makes Gemma 4 about 90% faster on Apple silicon when run locally with Ollama using MLX. It outlines a simple setup: download Ollama, download Gemma 4, and connect it to Claude Code with a one-click install/one terminal command. The script shows demos of building apps (like a to-do list and a Space Invaders game) via an agent workflow and notes that Gemma 4 is best for basic tasks versus frontier models for complex work. It also describes a free alternative for non-Mac users by accessing Gemma 4 via OpenRouter’s free API and routing it into the open-source Claude Code project.00:00 [https://www.youtube.com/watch?v=LGCJdI9eUl8] Free Claude Code Setup00:30 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=30s] Gemma 4 Speed Update00:53 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=53s] Install in Three Steps01:32 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=92s] Live Build Demos02:14 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=134s] Hermes Agent Notes02:38 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=158s] No Mac Use OpenRouter03:46 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=226s] When to Use Gemma04:37 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=277s] Agent OS Local Engine05:11 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=311s] Why This Beats Tokens05:53 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=353s] Common Objections Answered06:50 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=410s] Testing and Leaderboards07:34 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=454s] Why Local Models Matter08:07 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=487s] Recap and Next Steps08:24 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=504s] Join the Boardroom09:19 [https://www.youtube.com/watch?v=LGCJdI9eUl8&t=559s] Final Thanks

Agent OS: Fable 5 vs Fusion, Windows Setup, and Free APIs

Agent OS Q&A: Fable 5 Tests, Hermes Setup, VPS/Windows Tips, and Free API OptionsThis episode answers community questions about an agent operating system setup with memory and multiple agents (including newly added NotebookLM short videos), covering what people are using Fable 5 for, its credit/token limits, gating to Opus 4.8, Claude service-busy bugs, and upcoming Goldy bench tests and leaderboard updates versus Hermes-based mixtures. It suggests ways to link separate Claude accounts (terminal vs Desktop, VPS instances), and offers solutions for older hardware such as running OpenClaw/Hermes via a VPS, Raspberry Pi, or Tailscale. The host points to an existing Hermes Desktop masterclass but recommends the Agent OS for customization, shows a member-built offline job triage/outreach system, and shares Windows setup preferences (using Claude to configure Agent OS). It also covers Owl Alpha’s removal from OpenRouter and alternatives like OpenRouter free models, Minimax/Kimi plans, Groq Build via Twitter OAuth, local/NVIDIA options, plus VPS self-hosting and Cursor integration ideas.00:00 [https://www.youtube.com/watch?v=vWPrLWEz0as] Agent OS Q&A Overview00:36 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=36s] Fable 5 Limits and Tests02:16 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=136s] Linking Claude Accounts02:48 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=168s] Running Agents on Weak Hardware03:39 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=219s] Hermes Desktop vs Agent OS04:33 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=273s] Member Build Job Outreach05:26 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=326s] Windows Setup Choices06:06 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=366s] Free APIs and Owl Alpha07:17 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=437s] VPS Self Hosting Guide07:49 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=469s] Cursor and Open Design Models08:53 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=533s] Tutorial Library and xMCP10:46 [https://www.youtube.com/watch?v=vWPrLWEz0as&t=646s] Community Access and Wrap Up