Home▸AI & Machine Learning▸3D Agent Memory Retrieval: Recency Decay, Cosine Relevance, Importance Weights and Top-k Recall

🧠 3D Agent Memory Retrieval: Recency Decay, Cosine Relevance, Importance Weights and Top-k Recall

A Blender-built memory vault with one bay per topic: 240 cards placed by age and importance, a query terminal and a score = recency + relevance + importance rule; move the weights and the half-life and watch top-k precision and recall change, checked against heap selection, Monte Carlo and closed forms.

AI & Machine Learning3DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 2D version
3D Agent Memory Retrieval: Recency Decay, Cosine Relevance, Importance Weights and Top-k Recall ↗ Open standalone
⚙ Under the hood

A Blender-built memory vault with one bay per topic: 240 cards placed by age and importance, a query terminal and a score = recency + relevance + importance rule; move the weights and the half-life and watch top-k precision and recall change, checked against heap selection, Monte Carlo and closed forms.

Agent MemoryRetrievalCosine SimilarityRecency DecayImportance ScoreTop-kPrecision and RecallEmbeddings

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)