How we cut token usage significantly in an F1 telemetry analyzer by rethinking what goes into the...
Two Patterns for Reducing LLM Costs in Data-Heavy RAG Apps
Related
Most agents are "state blind". I built an orchestration layer with a synthetic visual tree to give agents actual Episodic Memory (LanceDB + Postgres).
I’ve been building Atom (https://github.com/rush86999/atom), a self-hosted orchestration platform in...
A file-based work-bus for orchestrating a fleet of agent CLIs — coordination without a message broker
Coordinate independent agent CLIs without LangGraph or a message broker — atomic Task/Result files, capability-based routing, absent-worker skip for graceful degradation, and a typ...
I trusted my CLAUDE.md. WordPress.org rejected the exact thing it was supposed to prevent.
My CLAUDE.md had a rule about it. The generated code broke the rule anyway. And the thing that...