Claude Code is now FREE: Here’s how…
Claude Code, an AI coding tool, can now be used for free by routing it through a free open-source version called 'free Claude Code' that connects to free models via OpenRouter. The setup can be enhanced further by integrating it with Agent OS and Obsidian for persistent memory and multi-agent coordination. The stack is expected to grow more powerful as new free models are released regularly.
Summary
The transcript introduces a method for using Claude Code, Anthropic's AI-powered coding assistant, completely free of charge. Normally a paid product, Claude Code allows users to describe what they want in plain English and have the AI write and edit code on their behalf. The key to making it free is an open-source alternative called 'free Claude Code,' which can route requests to any model the user chooses, including free ones available on OpenRouter — a platform that aggregates AI models.
The recommended configuration involves plugging in a free model from OpenRouter that offers a 1 million token context window, which is particularly well-suited for agentic tasks. This combination is described as delivering the full Claude Code experience at no cost.
The setup becomes significantly more powerful when integrated with Agent OS, described as a dashboard that connects Claude Code to the user's memory, notes, and other AI agents they run. Further connecting this stack to Obsidian — a popular note-taking application — enables persistent memory, meaning the system learns and retains information over time, becoming smarter with continued use.
Finally, the transcript notes that new free models are being released at a rapid pace (nearly weekly), suggesting that this free AI coding stack will only improve and become more capable over time.
Key Insights
- The speaker claims an open-source version called 'free Claude Code' can route requests to any model, including free ones, effectively replicating the full Claude Code experience at no cost.
- The speaker identifies a free model on OpenRouter with a 1 million token context window as the optimal pairing for agentic coding tasks within this free stack.
- The speaker argues that Agent OS acts as a central dashboard that wires Claude Code into the user's memory, notes, and all other AI agents they operate, significantly expanding its utility.
- The speaker claims that connecting the stack to Obsidian enables persistent memory, so the system retains information and becomes progressively smarter the more it is used.
- The speaker asserts that new free models are released almost every week, meaning this free AI coding stack will continuously grow more powerful over time without additional cost.
Topics
Transcript
[0:00] Claude Code is now free. Here's how. You can now run Claude Code 100% free. With Claude Code, you describe what you want in plain English and it writes and edits your code for you. A free open source version called free Claude Code can route it to any model you want including free ones. Plug in a free model on open router with a 1 million token context window built for agents and you've got the full Claude Code experience for free. Then it gets crazy. Drop it inside Agent OS, a dashboard that wires Claude Code into your memory, your notes and every other AI agent you run. Connect it to Obsidian and it remembers everything. The…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
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.