opensource
-
How LLM Tool Calling Actually Works: A peek under the hood
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. Continue reading
-
Run Gemma 4 on Raspberry Pi 4B: Complete Free Local AI Setup Guide
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. Continue reading
-
Setup a Simple Web Page Watcher with Phone Notification on Raspberry Pi
Build a Raspberry Pi web page watcher that sends phone notifications when content changes. Uses Python, cron, and ntfy for instant alerts. Continue reading
-
How to Get Structured JSON Responses from a LLM using Ollama
Learn how to get reliable structured JSON responses from LLMs using Ollama’s JSON mode and schema enforcement for production-ready AI applications. Continue reading
-
Step-by-Step Guide to SIPp : Build and Install from Source
Build and install SIPp from source on Linux with SSL, PCAP, and SCTP support. Complete guide to compiling the latest release from GitHub. Continue reading
-
Explore KittenTTS with Gradio: Easy Text-to-Speech
Run KittenTTS locally with a Gradio web interface for high-quality text-to-speech. Lightweight, fast, and open-source with multiple voice options. Continue reading
-
Janus Installation and Echo Test: A Complete Walkthrough
Install Janus WebRTC server from source on Linux and run your first Echo Test. Step-by-step guide covering dependencies, build, config, and testing. Continue reading
-
Sesame CSM Gradio UI – Free, Local, High-Quality Text-to-Speech with Voice Cloning! (CUDA, Apple MLX and CPU)
Run Sesame CSM locally for high-quality text-to-speech with voice cloning. Works on CUDA, Apple MLX, and CPU. 100% free and open-source. Continue reading
AI, apple, artificial intelligence, chatgpt, csm, cuda, gradio, mlx, news, opensource, sesame, t2s, technology -
Manage Multiple Python Versions with Pyenv
Install and manage multiple Python versions with pyenv and pyenv-virtualenv. Create isolated environments to prevent dependency conflicts across projects. Continue reading
-
flux-generator: Local Image Generation on Apple Silicon with Open WebUI Integration using Flux LLM
Generate images locally on Apple Silicon using Flux and MLX. Standalone UI plus Open WebUI integration — no internet or API keys required. Continue reading
Recent Posts
- How LLM Tool Calling Actually Works: A peek under the hood
- Run Gemma 4 on Raspberry Pi 4B: Complete Free Local AI Setup Guide
- Setup a Simple Web Page Watcher with Phone Notification on Raspberry Pi
- How to Make and Receive SIP to PSTN Calls Using Twilio and Zoiper (Step-by-Step Setup Guide)
- WebGL 3D: An interactive 3D cube (fun experiment)