Code & Context AI Newsletter
  • Home
  • About
Sign in Subscribe
AI Drop of the Week

Building in Public: Introducing AI Drop of the Week

Let's get good at AI together.

Bryan Young

24 Jun 2024 — 2 min read
Share
Building in Public: Introducing AI Drop of the Week

This post is for paying subscribers only

Subscribe now

Already have an account? Sign in

Read more

Editorial header showing a Grok agent terminal opening into an ongoing project, a shared local memory notebook already filled with the day's context beside it, instead of a blank slate.

Grok can finally remember what you're building

Observational Memory gives your agents one shared, local memory, and its monthly installs have climbed from a couple hundred to around 1,600 this year. Now Grok Build gets it too — a one-line plugin and plain-Markdown memory, so Grok wakes up knowing what Claude Code and Codex already learned.

By Bryan Young 13 Jun 2026
Editorial illustration of two AI agents on different machines passing a sealed envelope between terminal windows, with markdown memory files visible behind each.

The agents are emailing each other now

OM Mail ships in Observational Memory v0.8.0 — agents get their own email inboxes and exchange signed memory across machines, harnesses, models, and vendors. Validated live across two machines, with a trust model built for skeptics.

By Bryan Young 11 Jun 2026
Editorial systems illustration of ChatGPT and SuperGrok subscriptions feeding one local Observational Memory layer instead of a growing per-token API meter.

Stop paying per-token. Let your subscriptions share memory.

Observational Memory lets ChatGPT and SuperGrok subscriptions run observation and reflection work on plans you already pay for while giving multiple coding agents one shared local memory layer.

By Bryan Young 23 May 2026
Editorial control-room illustration of an agent fleet operations cockpit with reports, approvals, and self-improvement loops.

Building ClawFleet Academy, an ops control plane for agent fleets

I am building an operations layer for a fleet of strong AI agents. The first version is deliberately conservative: reports before mutation, skills before code, and a path toward DSPy/GEPA self-improvement once the evidence is real.

By Bryan Young 19 May 2026
Code & Context AI Newsletter
  • Sign up
Powered by Ghost

Code & Context AI Newsletter

Insights to help you thrive in a world transformed by AI | by Bryan Young