Notes from a CTO who has to put agents into production. Every post says what I ran, what it cost, and whether I'd use it.
The DeepInfer inference engine is DeepSeek's open-source Apache-2.0 serving code. What the README gives you, what it leaves out, and what I would steal.
The deslop model, qwen3-4b-deslop, is a free Apache-2.0 fine-tune that drops em dashes and "not X, but Y". How it was built and what its score hides.
The Postgres 19 delay explained: 8 to 10 features reverted in beta, release now Nov 19, and what AI code review costs a small team.
Python 3.15 lazy imports took my test AI CLI from 2,514.6 ms to 14.1 ms at startup. The benchmark, three traps I hit, and when to skip it.
SolidCraft MCP is an open-source CAD server for AI agents. I ran it: great design, one trap where ok:true meant nothing changed. How to guard against it.
ESP32 iPhone Agent lets a vision model tap a real iPhone through a $7 board. I ran its tests and did the token maths for one 20-step task.
Talorys is an MIT-licensed free AI agent that runs in your Cloudflare account. I did the Neuron maths to see how many chat turns a day it really buys.
I ran Cactus Whistle, a 16.9 MB open speech-to-text model, on Québec French, accented English and noise. Here is what it got wrong.
