🧠 Browser Vector Memory — IndexedDB + Semantic Search
🧠 Browser Vector Memory — IndexedDB + Semantic Search
Launcher for the standalone AI: vector memory in IndexedDB scored like Generative Agents — relevance, importance and recency — with tiers, reflections, consolidation and import/export.
Memory in the standalone AI is a real store: 64-dimension hashed embeddings in IndexedDB, scored 0.5·relevance + 0.3·importance + 0.2·recency with an Ebbinghaus decay, tiered long/semantic/episodic/preference, and recalled automatically during answers.
Open in the standalone AIOpens at: Memory mode · runs entirely in your browser · no account, no API key, nothing uploaded
What the standalone AI gives you for this
- Score breakdown per hit so you can see why a memory surfaced
- Reflection: consolidate a week of memories into one summary item
- Import and export as JSON; wipe without touching anything else
The interactive tool that used to live on this card now runs inside the standalone AI at ai.html, where it shares your indexed documents, stored memories and every reasoning method. This card stays in the catalogue as a launcher so existing links keep working.