How to Run a Local AI Coding Agent on Your Mac (Free, No Cloud)
I set up a local AI coding agent on my Mac with Pi, Ollama, and Gemma 4. Full config, a real test build, and the honest limits of a 12B model for local development.
VOIP | AI | Cloud | Kamailio | Open Source
I set up a local AI coding agent on my Mac with Pi, Ollama, and Gemma 4. Full config, a real test build, and the honest limits of a 12B model for local development.
A deep dive into how LLM tool calling actually works under the hood — from JSON schemas to grammar constraints to raw token generation. All with real logs from Gemma 4 E2B running on a Raspberry Pi 4B via llama.cpp.
Learn how to run Gemma 4 on Raspberry Pi 4B using llama.cpp. No GPU, no cloud, no monthly bill. Complete step-by-step guide with real performance numbers from an actual Pi.
Build a Raspberry Pi web page watcher that sends phone notifications when content changes. Uses Python, cron, and ntfy for instant alerts.
Step-by-step guide to making and receiving SIP to PSTN calls using Twilio and Zoiper. Set up SIP registration, TwiML Bins, and start calling in minutes.
Interactive WebGL 3D experiment rendering a spinning cube in your browser. Explore vertex shaders, fragment shaders, and real-time GPU rendering.
Learn how to get reliable structured JSON responses from LLMs using Ollama's JSON mode and schema enforcement for production-ready AI applications.
Build a live voice AI agent using OpenAI's Realtime API and Twilio SIP trunking. Covers webhook setup, SIP registration, and end-to-end call flow.
Build and install SIPp from source on Linux with SSL, PCAP, and SCTP support. Complete guide to compiling the latest release from GitHub.
Run KittenTTS locally with a Gradio web interface for high-quality text-to-speech. Lightweight, fast, and open-source with multiple voice options.