OpenClaw: Persistent AI Assistant

OpenClaw has become my AI assistant. I’ve been using it daily, over the past few weeks (so there’s long history!). In this session, I’ll walk through how it’s actually built at a high-level and dig deep into how it works behind the scenes (i.e. the file system).

I’ll start with a brief overview of my setup: architecture, orchestration layer, memory structure, and the tooling stack that makes it reliable. In the background a long running task will hopefully complete! Then I’ll walk through the filesystem and the two core capabilities: multi-step task orchestration and automated daily news synthesis.

This talk is a practical look at what a persistent AI assistant looks like under the hood. I hope to be able to do this all on a Raspberry Pi, but mine is super old and doesn’t have wifi, so I might have to buy a new one if my talk gets accepted :)