superlocalmemory 3.0.7 → 3.0.9

package/README.md

@@ -38,8 +38,8 @@ SuperLocalMemory gives AI assistants persistent, structured memory that survives
 
 | Metric | Score | Context |
 |:-------|:-----:|:--------|
+| LoCoMo (Mode C, full power) | **87.7%** | On conv-30, 81 scored questions |
 | LoCoMo (Mode A, zero-LLM) | **62.3%** | Highest zero-LLM score. No cloud dependency. |
-| LoCoMo (Mode C, full) | **~78%** | Competitive with funded systems ($10M+) |
 | Math layer improvement | **+12.7pp** | Average gain from mathematical foundations |
 | Multi-hop improvement | **+12pp** | 50% vs 38% (math on vs off) |
 
@@ -159,6 +159,27 @@ Add to your IDE's MCP config:
 
 24 MCP tools available: `remember`, `recall`, `search`, `fetch`, `list_recent`, `get_status`, `build_graph`, `switch_profile`, `health`, `consistency_check`, `recall_trace`, and more.
 
+### Web Dashboard (17 tabs)
+
+```bash
+slm dashboard    # Opens at http://localhost:8765
+```
+
+The V3 dashboard provides real-time visibility into your memory system:
+
+- **Dashboard** — Mode switcher, health score, quick store/recall
+- **Recall Lab** — Search with per-channel score breakdown (Semantic, BM25, Entity, Temporal)
+- **Knowledge Graph** — Interactive entity relationship visualization
+- **Memories** — Browse, search, and manage stored memories
+- **Trust Dashboard** — Bayesian trust scores per agent with Beta distribution visualization
+- **Math Health** — Fisher-Rao confidence, Sheaf consistency, Langevin lifecycle state
+- **Compliance** — GDPR export/erasure, EU AI Act status, audit trail
+- **Learning** — Adaptive ranking progress, behavioral patterns, outcome tracking
+- **IDE Connections** — Connected AI tools status and configuration
+- **Settings** — Mode, provider, auto-capture/recall configuration
+
+> The dashboard runs locally at `http://localhost:8765`. No data leaves your machine.
+
 ---
 
 ## V3 Engine Features
@@ -215,7 +236,7 @@ Evaluated on the [LoCoMo benchmark](https://arxiv.org/abs/2402.09714) (Long Conv
 | EverMemOS | 92.3% | Yes | No | No |
 | MemMachine | 91.7% | Yes | No | No |
 | Hindsight | 89.6% | Yes | No | No |
-| **SLM V3 Mode C** | **~78%** | Optional | **Yes** | Partial |
+| **SLM V3 Mode C** | **87.7%** | Optional | **Yes** | Partial |
 | **SLM V3 Mode A** | **62.3%** | **No** | **Yes** | **Yes** |
 | Mem0 ($24M) | 34.2% F1 | Yes | Partial | No |
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.0.7",
+  "version": "3.0.9",
   "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 = "3.0.0"
+version = "3.0.8"
 description = "Information-geometric agent memory with mathematical guarantees"
 readme = "README.md"
 license = {text = "MIT"}

package/src/superlocalmemory/server/ui.py

@@ -193,7 +193,20 @@ def create_app() -> FastAPI:
 
     @application.on_event("startup")
     async def startup_event():
-        """Register Event Bus listener for SSE bridge on startup."""
+        """Initialize V3 engine and event bus on startup."""
+        # Initialize V3 engine for dashboard API routes
+        try:
+            from superlocalmemory.core.config import SLMConfig
+            from superlocalmemory.core.engine import MemoryEngine
+            config = SLMConfig.load()
+            engine = MemoryEngine(config)
+            engine.initialize()
+            application.state.engine = engine
+            logger.info("V3 engine initialized for dashboard")
+        except Exception as exc:
+            logger.warning("V3 engine init failed: %s (V3 API routes will be unavailable)", exc)
+            application.state.engine = None
+
         register_event_listener()
 
     return application

package/src/superlocalmemory/storage/v2_migrator.py

@@ -329,6 +329,32 @@ class V2Migrator:
             except Exception as exc:
                 stats["steps"].append(f"V2 conversion partial: {exc}")
 
+            # Step 4c: Create views for V2 dashboard compatibility
+            try:
+                v2_views = {
+                    "graph_nodes": "_v2_bak_graph_nodes",
+                    "graph_clusters": "_v2_bak_graph_clusters",
+                    "sessions": "_v2_bak_sessions",
+                    "memory_events": "_v2_bak_memory_events",
+                    "identity_patterns": "_v2_bak_identity_patterns",
+                    "pattern_examples": "_v2_bak_pattern_examples",
+                    "creator_metadata": "_v2_bak_creator_metadata",
+                    "agent_registry": "_v2_bak_agent_registry",
+                }
+                view_count = 0
+                for view_name, source in v2_views.items():
+                    try:
+                        conn.execute(f'SELECT 1 FROM "{source}" LIMIT 1')
+                        conn.execute(f'DROP VIEW IF EXISTS "{view_name}"')
+                        conn.execute(f'CREATE VIEW "{view_name}" AS SELECT * FROM "{source}"')
+                        view_count += 1
+                    except Exception:
+                        pass
+                conn.commit()
+                stats["steps"].append(f"Created {view_count} V2 compatibility views")
+            except Exception:
+                pass
+
             conn.close()
             stats["steps"].append("Created V3 schema")
 

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

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.0.0
+Version: 3.0.7
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: MIT
@@ -130,13 +130,35 @@ Query  ──►  Strategy Classifier  ──►  4 Parallel Channels:
 
 ---
 
+## Prerequisites
+
+| Requirement | Version | Why |
+|:-----------|:--------|:----|
+| **Node.js** | 14+ | npm package manager |
+| **Python** | 3.11+ | V3 engine runtime |
+| **pip** | Latest | Python dependency installer |
+
+> 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.
+
+---
+
 ## Quick Start
 
-### Install via npm (recommended)
+### Install via npm (recommended — one command, everything included)
 
 ```bash
 npm install -g superlocalmemory
-slm setup
+```
+
+This single command:
+- Installs the V3 engine and CLI
+- Auto-installs all Python dependencies (numpy, scipy, networkx, sentence-transformers, etc.)
+- Creates the data directory at `~/.superlocalmemory/`
+- Detects and guides V2 migration if applicable
+
+Then configure:
+```bash
+slm setup    # Choose mode, configure provider
 ```
 
 ### Install via pip