Let the AI Out: Audient — An Ambient Audio Perception Layer That Grows
An audio perception layer for AI agents: hear a sound, recognize it if familiar, learn it if not.
es617’s blog
Enrico Santagati's blog
Latest posts
My Second Brain Was Everywhere. My AI Couldn’t Get In.
My notes were on every device I own, but Claude couldn't reach them while I was on the go. So I built an MCP server to fix that.
Training Apple’s On-Device LLM: LoRA, QLoRA, and What Actually Worked
Apple's adapter toolkit assumes a beefy GPU. I got it running on a free Colab T4 and a 24GB Mac, and found a caching bug that ate 269GB along the way.
When Your AI Tools Can’t Talk to Each Other
Claude Desktop and Claude Code are separate worlds. Here's an MCP server that bridges them.
The 3B Wall: What Apple’s On-Device LLM Can and Can’t Do in Your Shell
Apple ships a 3B LLM on every Mac running Tahoe. I wired it into three zsh hooks, benchmarked multiple approaches across 100 prompts, and found the ceiling.
Let the AI Out: Agents as a Control Layer
AI agents are great at analyzing data. This post is about what happens when they start acting on it — autonomously, continuously, with judgment.
Let the AI Out: Edge AI on a Microcontroller — From Zero to Inference in 90 Minutes
Deploying a TFLite Micro keyword spotting model on an nRF52840 from a single terminal session — no code written by hand, no hardware touched.
Turning Claude Code Sessions into HTML Replays
A CLI tool that converts Claude Code session logs into interactive, self-contained HTML replays you can share, embed, or host anywhere.
Let the AI Out: Same Hardware Tools, Every AI Agent
The same MCP servers — BLE, serial, debug probe — working across Claude Code, VS Code + Copilot, and Cursor. That's the point of a protocol.
Let the AI Out: Giving the AI Agent a Hardware Debug Probe
What happens when the AI agent can halt the CPU, set breakpoints, flash firmware, and inspect memory directly?