[Build logs & notes]
Notes from the build loop.
> Agents, evals, scraping systems, robotics, and the bugs between the diagram and the running code.
Architecture, failure modes, benchmarks, and the occasional opinion.
[Published]7
// Latest post: 25 September 2026
AI systems / research / software
[Pinned]
GitHub for Review, a Home Server for CI/CD
Self-hosted CI/CD with polled refs, isolated PR tests, and exact-SHA deploys.
[Read it]Counting Tokens Without Building Another Dashboard
A local macOS view of Codex, OpenCode, and Claude Code usage.
[> READ]
Agent Memory Is a Write-Path Problem
Bounded per-user agent memory with trusted identity and transactional writes.
[> READ]
AI Chat Analytics Is a Data Pipeline, Not a Prompt
Replayable chat analytics with idempotent writes and durable cursors.
[> READ]






