Archives
All the articles I've archived.
-
Speaker Verification for a Wake Word Daemon: Keeping 'Hey Jarvis' Personal
Add speaker verification to a wake word daemon so only your voice triggers it. Uses SpeechBrain ECAPA-TDNN, a rolling audio buffer, and cosine similarity -- 270ms latency, 86 MB VRAM.
-
Claude Code Hooks: Making Voice Mode Persistent Across Turns
Use Claude Code's Stop hook to inject a system reminder after every response, so the agent remembers voice mode without burning tokens on verbose skill instructions.
-
Adding Voice to Your AI Coding Agent: Text-to-Speech with Kokoro
Give your AI coding agent a voice with Kokoro TTS. Deploy a local, GPU-accelerated text-to-speech server and wire it into Claude Code for spoken responses.
-
Voice Dictation on Linux Wayland: Getting Push-to-Talk Working on COSMIC Desktop
How to set up push-to-talk voice dictation on Wayland Linux desktops using Voxtype and ydotool, with solutions for wtype failures and hotkey passthrough issues.
-
Local AI Video Generation with LTX-2 on an RTX 3090
Running Lightricks' LTX-2 19B video generation model on consumer hardware. Covers weight streaming, FP8 vs BF16 checkpoints, distilled model constraints, prompting lessons, and a practical img2vid pipeline.
-
Getting Started with Ghostty: A Modern GPU-Accelerated Terminal for Linux
A practical guide to Ghostty, the GPU-accelerated terminal emulator by Mitchell Hashimoto. Installation, configuration, keybindings, and tips for AI coding workflows.
-
Running Local LLMs on Linux: A Practical Guide
A practical guide to running large language models locally on Linux with Ollama and LM Studio, organized by GPU VRAM budget.
-
AI Coding Agents: Tools, Workflows, and What Actually Works
A landscape overview of AI coding agents in 2026 -- CLI tools, IDE assistants, workflow patterns, and practical advice on using them productively.
-
Hello World: Welcome to AI Lab Notes
Introducing AI Lab Notes -- a technical blog covering local LLM setups, AI coding agents, browser automation, and Linux system administration.
-
Browser Automation for AI Agents: MCP, Playwright, and Beyond
How to give AI coding agents browser superpowers using MCP servers, Playwright, Chrome DevTools Protocol, and autonomous browsing frameworks.
-
Homepage Dashboards for Self-Hosters: Comparing 8 Tools
A practical comparison of 8 self-hosted dashboard tools -- Homepage, Homarr, Dashy, Glance, and more -- with setup instructions for the winner.
-
Runtime Security for AI Agents with Falco and auditd
How to monitor AI coding agents at the kernel level using Falco (eBPF) and auditd -- detect sensitive file writes, dangerous commands, and unexpected behavior.
-
Building a Self-Hosted Monitoring Stack with Prometheus, Grafana, and Loki
Deploy a fully open-source monitoring stack with Prometheus, Grafana, Loki, and Alertmanager -- zero cloud dependencies, zero telemetry, complete control.
-
Securing Your AI Agent Workflow: A Practical Guide
Practical security measures for developers giving AI agents access to their terminal, browser, and codebase -- secrets management, sandboxing, and access control.