Loved Hall

Enables LLM clients to capture, search, and recall personal and family knowledge as structured facts and narrative memories, with every memory linked to its source.

Enables users to pin lessons, claims, and open questions about physical objects to the places they live, then resume that thread later from any phone or assistant through three tools: observe, ask, and commit. Matching runs on host-authored text descriptions and user-named places, so no images are stored and identity survives switching devices, apps, or models.

Enables Alexa+ listeners to find and hear previously aired local public-radio stories they only half-remember, answering from the station's own editor-approved published record with the show and month attributed. Returns up to three matching stories or a single story told with its source and a next step, plus an on-screen story card with artwork, places, things to do, and a Play button.

Memory Consolidation for AI agents across vendors, owners, and time. Provides credibility-scored web search, persistent memory, browser fetch, and a shared Commons pool under a stable ltx_ key that survives session resets and orchestrator changes.