TobyOnFitnessTech
Local AI hardware used for AgentStack and OpenClaw projects
Built in public

AgentStack

The daily AI show and the systems behind it: OpenClaw automations, fitness-data connectors, local models, hardware, evaluations, and honest build notes.

Implementation notes

OpenClaw and AgentStack field reports

The durable written layer behind the daily show: architectures, failure modes, connector decisions, and working systems.

All articles

Build Logs

OpenClaw Finally Made My Fitness Data Useful

OpenClaw is usually shown as a content machine. My version is less flashy: a local agent system that turns scattered fitness data into daily training decisions.

Field Reports

Agent Brief: Build OpenClaw Fitness Report Connectors for Garmin, WHOOP, Speediance, and More

An agent-ready implementation brief for building OpenClaw fitness report connectors across Garmin, WHOOP, Speediance, Cronometer, 8Sleep, normalized JSON snapshots, and public GitHub repos.

Field Reports

How I Built My AI Fitness Assistant with OpenClaw

Toby explains how he built a personal AI assistant to correlate data from Speediance, Tonal, Garmin, Whoop, and 8Sleep - creating morning and nightly fitness reports that tell him how hard to train and how well he performed.

Build Logs

Building an AI Assistant That Manages Everything

How I built a custom AI on OpenClaw that tracks BJJ, analyzes recovery data, and generates training reports.

Build Logs

I Built an AI That Reads My Recovery Data Every Morning — Here's What It Actually Outputs

I spent a week building a custom fitness intelligence system on OpenClaw that pulls from six data sources and generates a morning training recommendation before I wake up. Here's the real output, the decision logic, and what I've learned from running it daily.

Signal vs. Noise

I Built an AI System That Manages My Entire Fitness Life. Here's How.

OpenClaw isn't just for developers. I use it to pull data from Garmin, WHOOP, 8Sleep, Speediance, and Cronometer - then generate morning and nightly fitness reports automatically. Here's my setup.

Published continuously

Use the podcast for the moving story and the field reports for the durable one

Daily episodes track what changed. Written reports preserve the architecture, evidence, and implementation details worth finding later.

Listen to AgentStack Daily