03 / Writing
Blog
Sleep-Inspired Memory for LLM Agents: 6 Papers Ranked by What You Can Ship This Week
I read 6 papers on biologically-inspired memory replay for LLM agents. Only 2 are worth your time if you're building, not publishing.
Svapna or Sushupti: What Three Traditions Say About Offline Memory Consolidation
Neuroscience, recent AI papers, and an ancient Sanskrit text converge on the same insight about offline consolidation, yet disagree on which phase of sleep matters most.
Stop Designing Your AI System. Design Its Environment.
Self-evolving AI harnesses fail when they optimize a fixed evaluator. The biological model is right: what needs to evolve is the selection pressure, not just the genome.
Patanjali Had the Filtering Spec. We Just Wrote the Tests.
Memory consolidation made retrieval worse. Three design principles from agent memory benchmarks, and their unexpected parallels in yogic attention theory.
Your Agent's Memory Metrics Are Lying to You. Here's How to Ground Them.
Memory consolidation looks great on dashboards. But if your metrics can improve without retrieval getting better, you're optimizing a detached proxy.
Why AI Agents Need Sleep
AI agents capture memories but never consolidate them. Here's how MuninnDB's Dream Engine borrows from neuroscience to fix that.
Stop Putting AI in Your Apps. Put Your Apps in AI.
Why AI features inside traditional apps are backwards, and how MCP flips the architecture.
Adding OAuth 2.1 to a Self-Hosted MCP Server: 4 Gotchas from the Trenches
What broke when I wired up claude.ai to my own Reactive Resume instance via OAuth.
Shipping A2A Protocol Support in Rust: 7 Gotchas Nobody Warns You About
What I learned adding Agent-to-Agent protocol support to an open-source agent framework.