<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI Lab Notes</title><description>AI experimentation and coding notes.</description><link>https://codeshrew.github.io/ai-lab-notes/</link><item><title>Speaker Verification for a Wake Word Daemon: Keeping &apos;Hey Jarvis&apos; Personal</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-13_speaker-verification-wake-word-daemon/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-13_speaker-verification-wake-word-daemon/</guid><description>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.</description><pubDate>Fri, 13 Feb 2026 23:00:00 GMT</pubDate></item><item><title>Claude Code Hooks: Making Voice Mode Persistent Across Turns</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-13_claude-code-hooks-persistent-voice-mode/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-13_claude-code-hooks-persistent-voice-mode/</guid><description>Use Claude Code&apos;s Stop hook to inject a system reminder after every response, so the agent remembers voice mode without burning tokens on verbose skill instructions.</description><pubDate>Fri, 13 Feb 2026 17:00:00 GMT</pubDate></item><item><title>Adding Voice to Your AI Coding Agent: Text-to-Speech with Kokoro</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-11_adding-voice-to-ai-coding-agent-tts-kokoro/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-11_adding-voice-to-ai-coding-agent-tts-kokoro/</guid><description>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.</description><pubDate>Wed, 11 Feb 2026 17:00:00 GMT</pubDate></item><item><title>Voice Dictation on Linux Wayland: Getting Push-to-Talk Working on COSMIC Desktop</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-11_voice-dictation-cosmic-wayland/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-11_voice-dictation-cosmic-wayland/</guid><description>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.</description><pubDate>Wed, 11 Feb 2026 17:00:00 GMT</pubDate></item><item><title>Local AI Video Generation with LTX-2 on an RTX 3090</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-10_local-ai-video-generation-ltx2-rtx3090/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-10_local-ai-video-generation-ltx2-rtx3090/</guid><description>Running Lightricks&apos; 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.</description><pubDate>Wed, 11 Feb 2026 05:00:00 GMT</pubDate></item><item><title>Getting Started with Ghostty: A Modern GPU-Accelerated Terminal for Linux</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-09_getting-started-with-ghostty-gpu-accelerated-terminal-linux/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-09_getting-started-with-ghostty-gpu-accelerated-terminal-linux/</guid><description>A practical guide to Ghostty, the GPU-accelerated terminal emulator by Mitchell Hashimoto. Installation, configuration, keybindings, and tips for AI coding workflows.</description><pubDate>Mon, 09 Feb 2026 17:00:00 GMT</pubDate></item><item><title>Running Local LLMs on Linux: A Practical Guide</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_running-local-llms-linux-practical-guide/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_running-local-llms-linux-practical-guide/</guid><description>A practical guide to running large language models locally on Linux with Ollama and LM Studio, organized by GPU VRAM budget.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>AI Coding Agents: Tools, Workflows, and What Actually Works</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_ai-coding-agents-tools-workflows/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_ai-coding-agents-tools-workflows/</guid><description>A landscape overview of AI coding agents in 2026 -- CLI tools, IDE assistants, workflow patterns, and practical advice on using them productively.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>Hello World: Welcome to AI Lab Notes</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_hello-world/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_hello-world/</guid><description>Introducing AI Lab Notes -- a technical blog covering local LLM setups, AI coding agents, browser automation, and Linux system administration.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>Browser Automation for AI Agents: MCP, Playwright, and Beyond</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_browser-automation-ai-agents-mcp-playwright/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_browser-automation-ai-agents-mcp-playwright/</guid><description>How to give AI coding agents browser superpowers using MCP servers, Playwright, Chrome DevTools Protocol, and autonomous browsing frameworks.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>Homepage Dashboards for Self-Hosters: Comparing 8 Tools</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_homepage-dashboards-self-hosters-comparison/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_homepage-dashboards-self-hosters-comparison/</guid><description>A practical comparison of 8 self-hosted dashboard tools -- Homepage, Homarr, Dashy, Glance, and more -- with setup instructions for the winner.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>Runtime Security for AI Agents with Falco and auditd</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_runtime-security-ai-agents-falco-auditd/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_runtime-security-ai-agents-falco-auditd/</guid><description>How to monitor AI coding agents at the kernel level using Falco (eBPF) and auditd -- detect sensitive file writes, dangerous commands, and unexpected behavior.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>Building a Self-Hosted Monitoring Stack with Prometheus, Grafana, and Loki</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_self-hosted-monitoring-prometheus-grafana-loki/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_self-hosted-monitoring-prometheus-grafana-loki/</guid><description>Deploy a fully open-source monitoring stack with Prometheus, Grafana, Loki, and Alertmanager -- zero cloud dependencies, zero telemetry, complete control.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item><item><title>Securing Your AI Agent Workflow: A Practical Guide</title><link>https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_securing-ai-agent-workflow/</link><guid isPermaLink="true">https://codeshrew.github.io/ai-lab-notes/posts/2026-02-08_securing-ai-agent-workflow/</guid><description>Practical security measures for developers giving AI agents access to their terminal, browser, and codebase -- secrets management, sandboxing, and access control.</description><pubDate>Sun, 08 Feb 2026 19:00:00 GMT</pubDate></item></channel></rss>