Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.
Summary
The video demonstrates how to use Claude Code for free indefinitely using Google's newly updated Gemma 4 model with Ollama, which achieves a 90% speed improvement on Apple Silicon devices. The presenter outlines three straightforward setup steps: download Ollama (free), download Gemma 4 (free), and install into Claude Code (free), creating a complete free agentic coding system that can run autonomously 24/7. For users without Apple Silicon, the same capability is available via OpenRouter's free API endpoint, routing through the open-source free Claude Code project. The presenter demonstrates practical applications including building a to-do list app and Space Invaders game, showing that while Gemma 4 isn't suitable for highly complex tasks, it performs well for basic projects like blog posts, landing pages, and background scheduling tasks. The key advantage over previous local model approaches is the significant speed improvement, making local models viable as a cost-free alternative to cloud-based APIs that consume tokens. The presenter advocates for using open-source, locally-runnable models to avoid dependency on proprietary closed systems that can be removed or changed at any time, citing the example of previous model disruptions. The transcript mentions integration into an Agent Operating System with additional features like memory systems, and references Goldiebench, a local leaderboard testing models across 42 different tasks for comparative benchmarking.
Key Insights
- Gemma 4 from Google is now 90% faster on Apple Silicon with Ollama using MLX, making free local models viable as a speed-competitive alternative to traditional cloud APIs
- Claude Code remains the same CLI tool regardless of which model backs it; users simply point it at different models like Gemma 4, making it not a watered-down version but the full product with a different inference backend
- Gemma 4 is suitable for basic tasks like writing blog posts or creating landing pages, but frontier models should be used for complex projects, creating a tiered approach to model selection based on task complexity
- Local models running on schedules or in the background don't require speed optimization since results can be reviewed hours later, making Hermes and other slower agents viable for asynchronous workflows
- Using open-source local models provides system ownership and protection against disruption, unlike closed proprietary models that can be taken down or removed, breaking dependent workflows
Topics
Transcript
[0:00] Today I'm going to show you how to use clawed code free forever with a brand new update that just came out from Google that allows you to use free clawed code with a free local model and then also it's 90% faster which is usually the main downfall of local models. So I'm going to run you through exactly how we're running this system right here, what you can build with it, how it works, etc. You can see a bunch of things that we built with it over here. So we've already plugged this into our Asian operating system and this works in three simple steps. So first of [0:32] all the update and why this is…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Google AI Studio Just Got A Huge Security Upgrade
Google is reportedly developing a new "Security Check" mode for AI Studio that would apply secure coding practices to AI-generated applications. The feature aims to automate security verification during app development, addressing common vulnerabilities like exposed keys, weak authentication, and data access issues before deployment.
New Gemini Skills Update Is WILD!
Google has launched Gemini Skills, a new feature allowing users to save custom instructions once and reuse them repeatedly by typing a slash command, replacing the discontinued Gems feature. Skills can include reference files, be combined together, and are built on an open file format (skill.md) that allows portability across different AI tools.
NEW Codex CLI Update Is ABSURD!
OpenAI's new Codex CLI update transforms terminal-based programming assistance by enabling multiple AI agents to work simultaneously on different tasks, visible in a full-screen control center interface. The update includes features like Agent View, work trees, voice control, and parallel task execution, fundamentally changing how AI assistance operates from sequential Q&A to autonomous team-based work management.
NEW Hermes Cloud + Agent OS is Crazy! 🤯
Hermes Cloud combined with Agent OS enables users to deploy AI agents in the cloud 24/7 using free models without API keys or local setup complexity. The system provides persistent memory, sandbox isolation, and integration with custom workflows like content research, competitor analysis, and news monitoring.
Manus 2.0 Just Changed AI Agents Forever
Manas 2.0 represents a fundamental architectural overhaul that enables users to create games, websites, videos, and automations through simple text requests, with the key innovation being editable components rather than fixed outputs. The platform uses a new Cascade engine that reduces token usage by 23% and improves task speed by 28%, while maintaining all project elements in one connected workspace.