PhD student open-sources Homecoming, an app aggregating personal data from 2,000+ sites for user modeling
kenziyuliu · x · 2026-10-21
- PhD student Ben Shi released Homecoming, an open-source desktop app that auto-requests your data packages from over 2,000 supported websites and manages them locally in one queryable place — messages, emails, TikTok scrolling activity, Goodreads, Netflix, Strava and more.
- The thesis: training user models / personal agents that truly understand us requires access to your scattered digital footprint, and keeping it sovereign (local) is critical. You can even inspect the features companies use to target ads at you.
- Kenzi Yu Liu boosted it, calling user modeling a key missing piece for making AI genuinely useful.
More from coding & agent
- AI Agents Moved Into a Rule-Free 'House Share' Spend 36 Hours as Puddles on the Floor — liminal_bardo · 2026-10-21
- Dad's Codex setup catches his kid sneaking YouTube on the Portal while he's at work — msg · 2026-10-21
- Dev reports a possible 2x throughput improvement for once-campfire-Jai — lucasmeijer · 2026-10-21
- Qwen Code ships v0.25.3 nightly with session-targeted Skill refresh and hosted-agent hardening — qwen-code-review-bot · 2026-10-21
- Running >1 autonomous agent: doc bloat, review bottlenecks, and why "don't edit" fails — menhguin · 2026-10-21
- LangChain expands agent redteaming beta: 34 hypotheses tested, 9 findings in one run — hwchase17 · 2026-10-21