When AI Agents Dream: Memory Consolidation for the Obsidian Vault
Teaching AI agents to review their own session transcripts, catch lost decisions, and consolidate memory overnight. Part 3 of the AI memory series.
aiobsidianmcpclaude-codehooksdream
Things I broke so you don't have to_
A cloud architect's field notes on AWS, Azure, resilience patterns, and the occasional existential crisis about infrastructure costs.
Latest Posts
View allMaking AI Memory Stick: Hooks, Tiers, and the Problem with Polite Instructions
CLAUDE.md instructions are advisory. Hooks are contractual. How I made AI agent memory actually work by adding deterministic enforcement to an Obsidian vault.
aiobsidianmcpclaude-codehooks
AI Memory Without the Overhead: Using Obsidian as Your Agent's Second Brain
Why I'm using plain markdown files for AI agent memory instead of vector databases and semantic search. Sometimes the boring solution is the right one.
aiobsidianmcpproductivity
The Script That Grew Legs: Building a Deterministic AWS Discovery Tool
How a 500-line bash script evolved into an automated WAF assessment engine - and why deterministic tooling beats giving AI the wheel.
awsaiautomationwell-architected
Claude Skills: Context is King
How skills transform AI assistants from context-amnesiacs into genuinely useful collaborators - and why the token savings matter more than you'd think.
aiclaudeproductivityskills
>_
About
Cloud architect by day, infrastructure over-thinker by night. I write about the things I wish someone had told me before I learned them the hard way. Currently making clouds do things at scale.
More about me