The "quantified-self" topic on GitHub groups 1 open-source project in the DeepSeek Harness (DSH) ecosystem, led by dsh-aw-viz. dsh-aw-viz — Turns your own ActivityWatch records into metrics an AI can read — time allocation, fragmentation, focus blocks, hourly rhythm — so the assistant in the same session can suggest concrete changes to how you use your screens. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
Turns your own ActivityWatch records into metrics an AI can read — time allocation, fragmentation, focus blocks, hourly rhythm — so the assistant in the same session can suggest concrete changes to how you use your screens. Read-only, local, no cloud.