omni-cortex 1.0.1__tar.gz → 1.0.4__tar.gz

{omni_cortex-1.0.1 → omni_cortex-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: omni-cortex
-Version: 1.0.1
+Version: 1.0.4
 Summary: Universal Memory MCP for Claude Code - dual-layer activity logging and knowledge storage
 Project-URL: Homepage, https://github.com/AllCytes/Omni-Cortex
 Project-URL: Repository, https://github.com/AllCytes/Omni-Cortex
@@ -43,7 +43,7 @@ A universal memory system for Claude Code that combines activity logging with in
 
 - **Zero Configuration**: Works out of the box - just install and run setup
 - **Dual-Layer Storage**: Activity logging (audit trail) + Knowledge store (memories)
-- **15 MCP Tools**: Full-featured API for memory management, activity tracking, and session continuity
+- **18 MCP Tools**: Full-featured API for memory management, activity tracking, session continuity, and cross-project search
 - **Semantic Search**: AI-powered search using sentence-transformers (optional)
 - **Hybrid Search**: Combines keyword (FTS5) + semantic search for best results
 - **Full-Text Search**: SQLite FTS5-powered keyword search with smart ranking
@@ -163,6 +163,14 @@ pip uninstall omni-cortex
 | `cortex_review_memories` | Review and update memory freshness |
 | `cortex_export` | Export data to markdown or JSON |
 
+### Global Tools (3)
+
+| Tool | Description |
+|------|-------------|
+| `cortex_global_search` | Search memories across all projects |
+| `cortex_global_stats` | Get global index statistics |
+| `cortex_sync_to_global` | Manually sync to global index |
+
 ## Memory Types
 
 Memories are automatically categorized into:
@@ -197,6 +205,69 @@ auto_provide_context: true
 context_depth: 3
 ```
 
+## Web Dashboard
+
+A visual interface for browsing, searching, and managing your memories.
+
+![Dashboard Preview](docs/images/dashboard-preview.png)
+
+### Features
+- **Memory Browser**: View, search, filter, and edit memories
+- **Ask AI**: Chat with your memories using Gemini
+- **Real-time Updates**: WebSocket-based live sync
+- **Statistics**: Memory counts, types, tags distribution
+- **Project Switcher**: Switch between project databases
+
+### Quick Start
+
+```bash
+# Backend (requires Python 3.10+)
+cd dashboard/backend
+pip install -e .
+uvicorn main:app --host 0.0.0.0 --port 8765 --reload
+
+# Frontend (requires Node.js 18+)
+cd dashboard/frontend
+npm install
+npm run dev
+```
+
+Open http://localhost:5173 in your browser.
+
+### Ask AI Setup (Optional)
+
+To enable the "Ask AI" chat feature, set your Gemini API key:
+
+```bash
+export GEMINI_API_KEY=your_api_key_here
+```
+
+See [dashboard/README.md](dashboard/README.md) for full documentation.
+
+## Documentation
+
+- [Tool Reference](docs/TOOLS.md) - Complete documentation for all 18 tools with examples
+- [Configuration Guide](docs/CONFIGURATION.md) - Configuration options and troubleshooting
+- **Teaching Materials** (PDF):
+  - `docs/OmniCortex_QuickStart.pdf` - 3-page quick start guide
+  - `docs/OmniCortex_FeatureComparison.pdf` - Comparison with basic memory MCPs
+  - `docs/OmniCortex_Philosophy.pdf` - Design principles and inspiration
+  - `docs/OmniCortex_CommandReference.pdf` - All tools with parameters
+
+### Regenerating PDFs
+
+To regenerate the teaching material PDFs:
+
+```bash
+# Requires reportlab
+pip install reportlab
+
+# Generate all 4 PDFs
+python docs/create_pdfs.py
+```
+
+The PDFs use a light theme with blue/purple/green accents. Edit `docs/create_pdfs.py` to customize colors or content.
+
 ## Development
 
 ```bash
@@ -211,6 +282,14 @@ black src tests
 ruff check src tests
 ```
 
+## Security
+
+Omni Cortex v1.0.3 has been security reviewed:
+- All SQL queries use parameterized statements
+- Input validation via Pydantic models
+- Model name validation prevents code injection
+- YAML loading uses `safe_load()`
+
 ## License
 
 MIT

{omni_cortex-1.0.1 → omni_cortex-1.0.4}/README.md

@@ -6,7 +6,7 @@ A universal memory system for Claude Code that combines activity logging with in
 
 - **Zero Configuration**: Works out of the box - just install and run setup
 - **Dual-Layer Storage**: Activity logging (audit trail) + Knowledge store (memories)
-- **15 MCP Tools**: Full-featured API for memory management, activity tracking, and session continuity
+- **18 MCP Tools**: Full-featured API for memory management, activity tracking, session continuity, and cross-project search
 - **Semantic Search**: AI-powered search using sentence-transformers (optional)
 - **Hybrid Search**: Combines keyword (FTS5) + semantic search for best results
 - **Full-Text Search**: SQLite FTS5-powered keyword search with smart ranking
@@ -126,6 +126,14 @@ pip uninstall omni-cortex
 | `cortex_review_memories` | Review and update memory freshness |
 | `cortex_export` | Export data to markdown or JSON |
 
+### Global Tools (3)
+
+| Tool | Description |
+|------|-------------|
+| `cortex_global_search` | Search memories across all projects |
+| `cortex_global_stats` | Get global index statistics |
+| `cortex_sync_to_global` | Manually sync to global index |
+
 ## Memory Types
 
 Memories are automatically categorized into:
@@ -160,6 +168,69 @@ auto_provide_context: true
 context_depth: 3
 ```
 
+## Web Dashboard
+
+A visual interface for browsing, searching, and managing your memories.
+
+![Dashboard Preview](docs/images/dashboard-preview.png)
+
+### Features
+- **Memory Browser**: View, search, filter, and edit memories
+- **Ask AI**: Chat with your memories using Gemini
+- **Real-time Updates**: WebSocket-based live sync
+- **Statistics**: Memory counts, types, tags distribution
+- **Project Switcher**: Switch between project databases
+
+### Quick Start
+
+```bash
+# Backend (requires Python 3.10+)
+cd dashboard/backend
+pip install -e .
+uvicorn main:app --host 0.0.0.0 --port 8765 --reload
+
+# Frontend (requires Node.js 18+)
+cd dashboard/frontend
+npm install
+npm run dev
+```
+
+Open http://localhost:5173 in your browser.
+
+### Ask AI Setup (Optional)
+
+To enable the "Ask AI" chat feature, set your Gemini API key:
+
+```bash
+export GEMINI_API_KEY=your_api_key_here
+```
+
+See [dashboard/README.md](dashboard/README.md) for full documentation.
+
+## Documentation
+
+- [Tool Reference](docs/TOOLS.md) - Complete documentation for all 18 tools with examples
+- [Configuration Guide](docs/CONFIGURATION.md) - Configuration options and troubleshooting
+- **Teaching Materials** (PDF):
+  - `docs/OmniCortex_QuickStart.pdf` - 3-page quick start guide
+  - `docs/OmniCortex_FeatureComparison.pdf` - Comparison with basic memory MCPs
+  - `docs/OmniCortex_Philosophy.pdf` - Design principles and inspiration
+  - `docs/OmniCortex_CommandReference.pdf` - All tools with parameters
+
+### Regenerating PDFs
+
+To regenerate the teaching material PDFs:
+
+```bash
+# Requires reportlab
+pip install reportlab
+
+# Generate all 4 PDFs
+python docs/create_pdfs.py
+```
+
+The PDFs use a light theme with blue/purple/green accents. Edit `docs/create_pdfs.py` to customize colors or content.
+
 ## Development
 
 ```bash
@@ -174,6 +245,14 @@ black src tests
 ruff check src tests
 ```
 
+## Security
+
+Omni Cortex v1.0.3 has been security reviewed:
+- All SQL queries use parameterized statements
+- Input validation via Pydantic models
+- Model name validation prevents code injection
+- YAML loading uses `safe_load()`
+
 ## License
 
 MIT

omni_cortex-1.0.4/dashboard/backend/chat_service.py

@@ -0,0 +1,140 @@
+"""Chat service for natural language queries about memories using Gemini Flash."""
+
+import os
+from typing import Optional
+
+import google.generativeai as genai
+from dotenv import load_dotenv
+
+from database import search_memories, get_memories
+from models import FilterParams
+
+# Load environment variables
+load_dotenv()
+
+# Configure Gemini
+_api_key = os.getenv("GEMINI_API_KEY") or os.getenv("GOOGLE_API_KEY")
+_model: Optional[genai.GenerativeModel] = None
+
+
+def get_model() -> Optional[genai.GenerativeModel]:
+    """Get or initialize the Gemini model."""
+    global _model
+    if _model is None and _api_key:
+        genai.configure(api_key=_api_key)
+        _model = genai.GenerativeModel("gemini-2.0-flash-exp")
+    return _model
+
+
+def is_available() -> bool:
+    """Check if the chat service is available."""
+    return _api_key is not None
+
+
+async def ask_about_memories(
+    db_path: str,
+    question: str,
+    max_memories: int = 10,
+) -> dict:
+    """Ask a natural language question about memories.
+
+    Args:
+        db_path: Path to the database file
+        question: The user's question
+        max_memories: Maximum memories to include in context
+
+    Returns:
+        Dict with answer and sources
+    """
+    if not is_available():
+        return {
+            "answer": "Chat is not available. Please configure GEMINI_API_KEY or GOOGLE_API_KEY environment variable.",
+            "sources": [],
+            "error": "api_key_missing",
+        }
+
+    model = get_model()
+    if not model:
+        return {
+            "answer": "Failed to initialize Gemini model.",
+            "sources": [],
+            "error": "model_init_failed",
+        }
+
+    # Search for relevant memories
+    memories = search_memories(db_path, question, limit=max_memories)
+
+    # If no memories found via search, get recent ones
+    if not memories:
+        filters = FilterParams(
+            sort_by="last_accessed",
+            sort_order="desc",
+            limit=max_memories,
+            offset=0,
+        )
+        memories = get_memories(db_path, filters)
+
+    if not memories:
+        return {
+            "answer": "No memories found in the database to answer your question.",
+            "sources": [],
+            "error": None,
+        }
+
+    # Build context from memories
+    memory_context = []
+    sources = []
+    for i, mem in enumerate(memories, 1):
+        memory_context.append(f"""
+Memory {i}:
+- Type: {mem.memory_type}
+- Content: {mem.content}
+- Context: {mem.context or 'N/A'}
+- Tags: {', '.join(mem.tags) if mem.tags else 'N/A'}
+- Status: {mem.status}
+- Importance: {mem.importance_score}/100
+""")
+        sources.append({
+            "id": mem.id,
+            "type": mem.memory_type,
+            "content_preview": mem.content[:100] + "..." if len(mem.content) > 100 else mem.content,
+            "tags": mem.tags,
+        })
+
+    context_str = "\n---\n".join(memory_context)
+
+    # Create prompt
+    prompt = f"""You are a helpful assistant that answers questions about stored memories and knowledge.
+
+The user has a collection of memories that capture decisions, solutions, insights, errors, preferences, and other learnings from their work.
+
+Here are the relevant memories:
+
+{context_str}
+
+User question: {question}
+
+Instructions:
+1. Answer the question based on the memories provided
+2. If the memories don't contain relevant information, say so
+3. Reference specific memories when appropriate (e.g., "According to memory 1...")
+4. Be concise but thorough
+5. If the question is asking for a recommendation or decision, synthesize from multiple memories if possible
+
+Answer:"""
+
+    try:
+        response = model.generate_content(prompt)
+        answer = response.text
+    except Exception as e:
+        return {
+            "answer": f"Failed to generate response: {str(e)}",
+            "sources": sources,
+            "error": "generation_failed",
+        }
+
+    return {
+        "answer": answer,
+        "sources": sources,
+        "error": None,
+    }