🚨BREAKING: You can now run Claude Code for FREE. No API costs. No rate limits. 100% local on your machine. Here's how to run Claude Code locally (100% free & fully private):

STEP 1: Select Your Local “Brain” (Ollama) First you need a local engine that can run AI models and handle tool or function calls. Here we will use Ollama so download ollama.com Once it’s installed, Ollama runs quietly in the background on both Mac and Windows.

The installer will set up Ollama and add it to your system path. After installation, verify Ollama is working: Ollama runs as a background service automatically after installation. You should see it running on http:// localhost: 1143

First, you need to get a special computer program for coding. If your computer is really powerful, you can download a bigger program like qwen3-coder:30b. If your computer isn't as strong, smaller programs like gemma:2b or qwen2.5-coder:7b will work just fine. Once you choose one, open your computer's terminal and start downloading it by typing:

Step 3: Connect Claude to Your Computer This step is super important. Normally, Claude talks to Anthropic’s servers, but now you’ll make it talk to your computer instead. First, let Claude know where your computer is by setting the base URL.

@AiwithYasir explain in details this part please

Sure! In Step 3, we redirect Claude Code from Anthropic’s cloud servers to your local Ollama (running at http://localhost:11434). Quick way: Run: ollama launch claude --model qwen2.5-coder:7b (Use a coding model that fits your hardware.) Manual way: Set these env vars then run claude: export ANTHROPIC_BASE_URL=http://localhost:11434 export ANTHROPIC_API_KEY=ollama This lets Claude Code use your local model for all agentic features (file editing, terminal, etc.) — 100% free & private. Which part is unclear? Happy to help!