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.
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.
I tried to install the MXC sandbox v1.0.0 on Linux and it failed on node-pty. Here is what it takes to run LLM-written code at a small startup.
WebMCP lets a web page hand tools to a browser agent. I ran it in Chromium 153, hit one real bug, and sketched a half-day Trellis experiment.
ts-rust ported the TypeScript compiler to Rust with agents. I ran it and read its own numbers: the codebase port cost $24k after a $400k stall.
A LiteLLM budget cap does nothing without a database. I tested v1.104.0, then set up per-agent keys and a team spend limit in ten minutes.
Vectorless RAG swaps embeddings for a table-of-contents tree the LLM walks. What PageIndex does well, what a query costs, and who should skip it.
MoE expert offloading lets a 12GB GPU run a 125B model, but only for one user at a time. What Strata's numbers say, and what I'd run instead.
