superlocalmemory 3.0.10 → 3.0.11

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.0.10",
+  "version": "3.0.11",
   "description": "Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.",
   "keywords": [
     "ai-memory",

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.0.10"
+version = "3.0.11"
 description = "Information-geometric agent memory with mathematical guarantees"
 readme = "README.md"
 license = {text = "MIT"}

package/src/superlocalmemory/core/engine.py

@@ -414,7 +414,8 @@ class MemoryEngine:
             }
             # Bayesian variance narrowing after 3+ accesses
             if (q_var_arr is not None
-                    and r.fact.fisher_variance is not None
+                    and r.fact.fisher_variance
+                    and len(r.fact.fisher_variance) == len(q_var_arr)
                     and r.fact.access_count >= 3):
                 import numpy as _np
                 f_var = _np.array(r.fact.fisher_variance, dtype=_np.float64)

package/src/superlocalmemory.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.0.8
+Version: 3.0.10
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: MIT
@@ -142,6 +142,16 @@ Query  ──►  Strategy Classifier  ──►  4 Parallel Channels:
 
 > All Python dependencies are installed automatically during `npm install`. You don't need to run pip manually. If any dependency fails, the installer shows clear instructions.
 
+### What Gets Installed Automatically
+
+| Component | Size | When |
+|:----------|:-----|:-----|
+| Core math libraries (numpy, scipy, networkx) | ~50MB | During `npm install` |
+| Search engine (sentence-transformers, einops, torch) | ~200MB | During `npm install` |
+| Embedding model (nomic-ai/nomic-embed-text-v1.5) | ~500MB | On first use OR `slm warmup` |
+
+**If any dependency fails during install**, the installer prints the exact `pip install` command to fix it. BM25 keyword search works even without embeddings — you're never fully blocked.
+
 ---
 
 ## Quick Start
@@ -154,15 +164,18 @@ npm install -g superlocalmemory
 
 This single command:
 - Installs the V3 engine and CLI
-- Auto-installs all Python dependencies (numpy, scipy, networkx, sentence-transformers, etc.)
+- Auto-installs all Python dependencies (numpy, scipy, networkx, sentence-transformers, einops, torch, etc.)
 - Creates the data directory at `~/.superlocalmemory/`
 - Detects and guides V2 migration if applicable
 
-Then configure:
+Then configure and pre-download the embedding model:
 ```bash
-slm setup    # Choose mode, configure provider
+slm setup     # Choose mode, configure provider
+slm warmup    # Pre-download embedding model (~500MB, optional)
 ```
 
+> **First time?** If you skip `slm warmup`, the model downloads automatically on first `slm remember` or `slm recall`. Either way works.
+
 ### Install via pip
 
 ```bash