superlocalmemory 2.8.1 → 2.8.2

package/ATTRIBUTION.md

@@ -0,0 +1,50 @@
+# Attribution
+
+## SuperLocalMemory
+
+**SuperLocalMemory** is part of the Qualixar research initiative — advancing agent development through research.
+
+### Creator
+
+**Varun Pratap Bhardwaj** — Solution Architect & Original Creator
+- GitHub: [@varun369](https://github.com/varun369)
+- ORCID: 0009-0002-8726-4289
+
+### License
+
+This software is licensed under the MIT License. See [LICENSE](LICENSE) for full terms.
+
+### Output Attribution
+
+All tool outputs carry provenance metadata:
+
+```
+Generated by SuperLocalMemory | Part of Qualixar
+```
+
+Outputs may include:
+- **Layer 1 (Visible):** Human-readable attribution in reports and exports.
+- **Layer 2 (Cryptographic):** SHA-256 content hash and signature in the `_qualixar` metadata block.
+- **Layer 3 (Steganographic):** Invisible zero-width character watermark in text outputs.
+
+### Verification
+
+Output provenance can be verified programmatically:
+
+```python
+from qualixar_attribution import QualixarSigner
+is_valid = QualixarSigner.verify(signed_output)
+```
+
+### Research Initiative
+
+Qualixar is a research platform for AI agent development tools. SuperLocalMemory is one of several research initiatives under the Qualixar umbrella. For more information, visit qualixar.com.
+
+### Third-Party Acknowledgments
+
+SuperLocalMemory uses the following open-source libraries:
+- scikit-learn (BSD-3-Clause) — TF-IDF vectorization and similarity search
+- SQLite (Public Domain) — Local database storage
+- NumPy (BSD-3-Clause) — Numerical operations
+
+See [requirements.txt](requirements.txt) for the full dependency list.

package/CHANGELOG.md

@@ -16,6 +16,14 @@ SuperLocalMemory V2 - Intelligent local memory system for AI coding assistants.
 
 ---
 
+## [2.8.2] - 2026-03-04
+
+### Fixed
+- Windows compatibility for repository cloning (#7)
+- Updated test assertions for v2.8 behavioral feature dimensions
+
+---
+
 ## [2.8.0] - 2026-02-26
 
 **Release Type:** Major Feature Release — "Memory That Manages Itself"

package/README.md

@@ -38,7 +38,7 @@
 </p>
 
 <p align="center">
-  <b>Created by <a href="https://github.com/varun369">Varun Pratap Bhardwaj</a></b> •
+  <b>A <a href="https://github.com/varun369">Qualixar</a> Product</b> · Created by <a href="https://github.com/varun369">Varun Pratap Bhardwaj</a> •
   <a href="https://github.com/sponsors/varun369">💖 Sponsor</a> •
   <a href="LICENSE">📜 MIT License</a>
 </p>
@@ -201,10 +201,10 @@ You: *sighs and explains everything again*
 npm install -g superlocalmemory
 
 # Save a memory
-superlocalmemoryv2:remember "Fixed auth bug - JWT tokens were expiring too fast, increased to 24h"
+superlocalmemoryv2-remember "Fixed auth bug - JWT tokens were expiring too fast, increased to 24h"
 
 # Later, in a new session...
-superlocalmemoryv2:recall "auth bug"
+superlocalmemoryv2-recall "auth bug"
 # ✓ Found: "Fixed auth bug - JWT tokens were expiring too fast, increased to 24h"
 ```
 
@@ -230,7 +230,7 @@ Both methods auto-detect and configure **17+ IDEs and AI tools** — Cursor, VS
 ### Verify Installation
 
 ```bash
-superlocalmemoryv2:status
+superlocalmemoryv2-status
 # ✓ Database: OK (0 memories)
 # ✓ Graph: Ready
 # ✓ Patterns: Ready
@@ -343,7 +343,7 @@ Not another simple key-value store. SuperLocalMemory implements **cutting-edge m
 
 | Tool | Integration | How It Works |
 |------|-------------|--------------|
-| **Claude Code** | ✅ Skills + MCP | `/superlocalmemoryv2:remember` |
+| **Claude Code** | ✅ Skills + MCP | `/superlocalmemoryv2-remember` |
 | **Cursor** | ✅ MCP + Skills | AI uses memory tools natively |
 | **Windsurf** | ✅ MCP + Skills | Native memory access |
 | **Claude Desktop** | ✅ MCP | Built-in support |
@@ -365,7 +365,7 @@ Not another simple key-value store. SuperLocalMemory implements **cutting-edge m
    - "Remember that we use this framework" just works
 
 2. **Skills & Commands** — For Claude Code, Continue.dev, Cody
-   - `/superlocalmemoryv2:remember` in Claude Code
+   - `/superlocalmemoryv2-remember` in Claude Code
    - `/slm-remember` in Continue.dev and Cody
    - Familiar slash command interface
 
@@ -466,15 +466,15 @@ Auto-clustering discovers 6-7 natural topic communities from your memories.
 
 ```bash
 # Memory Operations
-superlocalmemoryv2:remember "content" --tags tag1,tag2  # Save memory
-superlocalmemoryv2:recall "search query"                 # Search
-superlocalmemoryv2:list                                  # Recent memories
-superlocalmemoryv2:status                                # System health
+superlocalmemoryv2-remember "content" --tags tag1,tag2  # Save memory
+superlocalmemoryv2-recall "search query"                 # Search
+superlocalmemoryv2-list                                  # Recent memories
+superlocalmemoryv2-status                                # System health
 
 # Profile Management
-superlocalmemoryv2:profile list                          # Show all profiles
-superlocalmemoryv2:profile create <name>                 # New profile
-superlocalmemoryv2:profile switch <name>                 # Switch context
+superlocalmemoryv2-profile list                          # Show all profiles
+superlocalmemoryv2-profile create <name>                 # New profile
+superlocalmemoryv2-profile switch <name>                 # Switch context
 
 # Knowledge Graph
 python ~/.claude-memory/graph_engine.py build            # Build graph
@@ -544,11 +544,20 @@ MIT License — use freely, even commercially. Just include the license.
 
 ## 👨‍💻 Author
 
-**Varun Pratap Bhardwaj** — Solution Architect
+**Varun Pratap Bhardwaj** — Founder, Qualixar · Solution Architect
 
 [![GitHub](https://img.shields.io/badge/GitHub-@varun369-181717?style=flat-square&logo=github)](https://github.com/varun369)
 
-Building tools that make AI actually useful for developers.
+Building the complete agent development platform at Qualixar — memory, testing, contracts, and security for AI agents.
+
+### Part of the Qualixar Agent Development Platform
+
+SuperLocalMemory is part of **Qualixar**, a suite of open-source tools for building reliable AI agents:
+
+| Product | What It Does |
+|---------|-------------|
+| **SuperLocalMemory** | Local-first AI agent memory |
+| **SkillFortify** | Agent skill supply chain security |
 
 ---
 

package/bin/aider-smart

@@ -35,11 +35,11 @@ echo ""
 if command -v slm &> /dev/null; then
     # Use slm command if available
     slm context > "$CONTEXT_FILE" 2>/dev/null || {
-        "$SLM_DIR/bin/superlocalmemoryv2:recall" "$project" --limit 5 > "$CONTEXT_FILE" 2>/dev/null || true
+        "$SLM_DIR/bin/superlocalmemoryv2-recall" "$project" --limit 5 > "$CONTEXT_FILE" 2>/dev/null || true
     }
 else
     # Fallback to direct command
-    "$SLM_DIR/bin/superlocalmemoryv2:recall" "$project" --limit 5 > "$CONTEXT_FILE" 2>/dev/null || true
+    "$SLM_DIR/bin/superlocalmemoryv2-recall" "$project" --limit 5 > "$CONTEXT_FILE" 2>/dev/null || true
 fi
 
 # Get coding patterns if available

package/bin/slm

@@ -6,7 +6,7 @@
 # Licensed under MIT License
 #
 # This is a CONVENIENCE wrapper. Original commands still work:
-#   superlocalmemoryv2:remember, superlocalmemoryv2:recall, etc.
+#   superlocalmemoryv2-remember, superlocalmemoryv2-recall, etc.
 
 set -e
 
@@ -24,13 +24,13 @@ case "$1" in
     remember|save|store)
         shift
         # Calls existing command - no duplicate logic
-        "$SLM_DIR/bin/superlocalmemoryv2:remember" "$@"
+        "$SLM_DIR/bin/superlocalmemoryv2-remember" "$@"
         ;;
 
     recall|search|find)
         shift
         # Calls existing command - no duplicate logic
-        "$SLM_DIR/bin/superlocalmemoryv2:recall" "$@"
+        "$SLM_DIR/bin/superlocalmemoryv2-recall" "$@"
         ;;
 
     list|ls)
@@ -38,44 +38,44 @@ case "$1" in
         # Convert positional number to --limit flag
         # e.g., "slm list 5" becomes "--limit 5"
         if [ -n "$1" ] && [[ "$1" =~ ^[0-9]+$ ]]; then
-            "$SLM_DIR/bin/superlocalmemoryv2:list" --limit "$1"
+            "$SLM_DIR/bin/superlocalmemoryv2-list" --limit "$1"
         else
-            "$SLM_DIR/bin/superlocalmemoryv2:list" "$@"
+            "$SLM_DIR/bin/superlocalmemoryv2-list" "$@"
         fi
         ;;
 
     status|info|stats)
         # Calls existing command - no duplicate logic
-        "$SLM_DIR/bin/superlocalmemoryv2:status"
+        "$SLM_DIR/bin/superlocalmemoryv2-status"
         ;;
 
     profile)
         shift
         # Calls existing command - no duplicate logic
-        "$SLM_DIR/bin/superlocalmemoryv2:profile" "$@"
+        "$SLM_DIR/bin/superlocalmemoryv2-profile" "$@"
         ;;
 
     switch-profile)
         shift
         # Convenience alias: "slm switch-profile <name>" -> "slm profile switch <name>"
-        "$SLM_DIR/bin/superlocalmemoryv2:profile" switch "$@"
+        "$SLM_DIR/bin/superlocalmemoryv2-profile" switch "$@"
         ;;
 
     list-profiles)
         # Convenience alias: "slm list-profiles" -> "slm profile list"
-        "$SLM_DIR/bin/superlocalmemoryv2:profile" list
+        "$SLM_DIR/bin/superlocalmemoryv2-profile" list
         ;;
 
     create-profile)
         shift
         # Convenience alias: "slm create-profile <name>" -> "slm profile create <name>"
-        "$SLM_DIR/bin/superlocalmemoryv2:profile" create "$@"
+        "$SLM_DIR/bin/superlocalmemoryv2-profile" create "$@"
         ;;
 
     reset)
         shift
         # Calls existing command - no duplicate logic
-        "$SLM_DIR/bin/superlocalmemoryv2:reset" "$@"
+        "$SLM_DIR/bin/superlocalmemoryv2-reset" "$@"
         ;;
 
     ui|dashboard)
@@ -103,7 +103,7 @@ case "$1" in
     context)
         # NEW: Get context for current directory/project
         project=$(basename "$PWD")
-        "$SLM_DIR/bin/superlocalmemoryv2:recall" "$project" --limit 5
+        "$SLM_DIR/bin/superlocalmemoryv2-recall" "$project" --limit 5
         ;;
 
     graph)
@@ -361,12 +361,12 @@ ADVANCED:
   slm reset hard --confirm Hard reset (nuclear option)
 
 ORIGINAL COMMANDS (still work):
-  superlocalmemoryv2:remember <content>
-  superlocalmemoryv2:recall <query>
-  superlocalmemoryv2:list [N]
-  superlocalmemoryv2:status
-  superlocalmemoryv2:profile <command>
-  superlocalmemoryv2:reset <type>
+  superlocalmemoryv2-remember <content>
+  superlocalmemoryv2-recall <query>
+  superlocalmemoryv2-list [N]
+  superlocalmemoryv2-status
+  superlocalmemoryv2-profile <command>
+  superlocalmemoryv2-reset <type>
 
 EXAMPLES:
   slm remember "Use FastAPI for REST APIs" --tags python,backend

package/configs/continue-skills.yaml

@@ -5,19 +5,19 @@
 slashCommands:
   - name: "slm-remember"
     description: "Save to SuperLocalMemory"
-    run: "~/.claude-memory/bin/superlocalmemoryv2:remember \"{{input}}\""
+    run: "~/.claude-memory/bin/superlocalmemoryv2-remember \"{{input}}\""
 
   - name: "slm-recall"
     description: "Search SuperLocalMemory"
-    run: "~/.claude-memory/bin/superlocalmemoryv2:recall \"{{input}}\""
+    run: "~/.claude-memory/bin/superlocalmemoryv2-recall \"{{input}}\""
 
   - name: "slm-list"
     description: "List recent memories"
-    run: "~/.claude-memory/bin/superlocalmemoryv2:list"
+    run: "~/.claude-memory/bin/superlocalmemoryv2-list"
 
   - name: "slm-status"
     description: "SuperLocalMemory system status"
-    run: "~/.claude-memory/bin/superlocalmemoryv2:status"
+    run: "~/.claude-memory/bin/superlocalmemoryv2-status"
 
 # Usage in Continue.dev:
 #   /slm-remember Use FastAPI for REST APIs

package/docs/ARCHITECTURE.md

@@ -61,7 +61,7 @@ Simple Storage → Intelligent Organization → Adaptive Learning
 │  • Continue.dev - MCP context providers                    │
 ├─────────────────────────────────────────────────────────────┤
 │ TIER 2: Skills & Commands                                  │
-│  • Claude Code - /superlocalmemoryv2:*                     │
+│  • Claude Code - /superlocalmemoryv2-*                     │
 │  • Continue.dev - /slm-* slash commands                    │
 │  • Cody - Custom commands via settings                     │
 ├─────────────────────────────────────────────────────────────┤
@@ -148,8 +148,8 @@ Installation automatically detects and configures:
 Provides simple syntax for all operations:
 
 ```bash
-slm remember "content"    # Calls superlocalmemoryv2:remember
-slm recall "query"        # Calls superlocalmemoryv2:recall
+slm remember "content"    # Calls superlocalmemoryv2-remember
+slm recall "query"        # Calls superlocalmemoryv2-recall
 slm list                  # Recent memories
 slm status                # System health
 slm profile list          # Profile management

package/docs/CLI-COMMANDS-REFERENCE.md

@@ -6,7 +6,7 @@
 
 SuperLocalMemory V2 offers three access methods:
 1. **Universal CLI** - Simple `slm` commands (NEW in v2.1.0)
-2. **Original CLI** - Full `superlocalmemoryv2:*` commands
+2. **Original CLI** - Full `superlocalmemoryv2-*` commands
 3. **MCP/Skills** - IDE-specific integration (auto-configured)
 
 All methods use the same local SQLite database.
@@ -105,9 +105,9 @@ All original commands continue to work unchanged. Use these if you prefer explic
 
 ### Check System Status
 ```bash
-superlocalmemoryv2:status
+superlocalmemoryv2-status
 # OR
-~/.claude-memory/bin/superlocalmemoryv2:status
+~/.claude-memory/bin/superlocalmemoryv2-status
 ```
 Shows: total memories, graph stats, clusters, patterns, database size
 
@@ -119,38 +119,38 @@ Shows: total memories, graph stats, clusters, patterns, database size
 
 ### List All Profiles
 ```bash
-superlocalmemoryv2:profile list
+superlocalmemoryv2-profile list
 # OR
-~/.claude-memory/bin/superlocalmemoryv2:profile list
+~/.claude-memory/bin/superlocalmemoryv2-profile list
 ```
 Shows all profiles with active marker (→)
 
 ### Show Current Active Profile
 ```bash
-superlocalmemoryv2:profile current
+superlocalmemoryv2-profile current
 # OR
-~/.claude-memory/bin/superlocalmemoryv2:profile current
+~/.claude-memory/bin/superlocalmemoryv2-profile current
 ```
 Shows current profile details and memory count
 
 ### Create New Profile
 ```bash
 # Empty profile
-superlocalmemoryv2:profile create work --description "Work projects"
+superlocalmemoryv2-profile create work --description "Work projects"
 
 # Copy from current profile
-superlocalmemoryv2:profile create personal --from-current
+superlocalmemoryv2-profile create personal --from-current
 ```
 
 ### Switch Profile
 ```bash
-superlocalmemoryv2:profile switch work
+superlocalmemoryv2-profile switch work
 ```
 **⚠️ Restart your IDE after switching if using MCP integration.**
 
 ### Delete Profile
 ```bash
-superlocalmemoryv2:profile delete old-project
+superlocalmemoryv2-profile delete old-project
 ```
 - Cannot delete "default" profile
 - Cannot delete currently active profile
@@ -165,15 +165,15 @@ superlocalmemoryv2:profile delete old-project
 ```bash
 slm status
 # OR
-superlocalmemoryv2:status
+superlocalmemoryv2-status
 ```
 **Always check status before any reset operation!**
 
 ### Soft Reset
 ```bash
-superlocalmemoryv2:reset soft
+superlocalmemoryv2-reset soft
 # OR
-~/.claude-memory/bin/superlocalmemoryv2:reset soft
+~/.claude-memory/bin/superlocalmemoryv2-reset soft
 ```
 - Clears all memories from current profile
 - Clears graph, patterns, tree structure
@@ -183,9 +183,9 @@ superlocalmemoryv2:reset soft
 
 ### Hard Reset
 ```bash
-superlocalmemoryv2:reset hard --confirm
+superlocalmemoryv2-reset hard --confirm
 # OR
-~/.claude-memory/bin/superlocalmemoryv2:reset hard --confirm
+~/.claude-memory/bin/superlocalmemoryv2-reset hard --confirm
 ```
 - ⚠️ **NUCLEAR OPTION** ⚠️
 - Deletes entire database file
@@ -195,9 +195,9 @@ superlocalmemoryv2:reset hard --confirm
 
 ### Layer Reset (Surgical)
 ```bash
-superlocalmemoryv2:reset layer --layers graph patterns
+superlocalmemoryv2-reset layer --layers graph patterns
 # OR
-~/.claude-memory/bin/superlocalmemoryv2:reset layer --layers graph patterns
+~/.claude-memory/bin/superlocalmemoryv2-reset layer --layers graph patterns
 ```
 Available layers:
 - `graph` - Clear graph nodes, edges, clusters

package/docs/FRAMEWORK-INTEGRATIONS.md

@@ -240,7 +240,7 @@ history.clear()
 chat_store.delete_messages("user-1")
 
 # CLI: Reset entire profile
-# superlocalmemoryv2:reset soft --profile customer-support
+# superlocalmemoryv2-reset soft --profile customer-support
 ```
 
 ---
@@ -265,7 +265,7 @@ If you see "database is locked" errors:
 
 ```bash
 # Check if SuperLocalMemory is running correctly
-superlocalmemoryv2:status
+superlocalmemoryv2-status
 
 # Restart any MCP servers
 # (Close and reopen Cursor/Windsurf)
@@ -277,10 +277,10 @@ If a profile doesn't exist:
 
 ```bash
 # List available profiles
-superlocalmemoryv2:profile list
+superlocalmemoryv2-profile list
 
 # Create the profile
-superlocalmemoryv2:profile create work
+superlocalmemoryv2-profile create work
 ```
 
 ---

package/docs/UNIVERSAL-INTEGRATION.md

@@ -33,7 +33,7 @@ After installation, restart any IDE you want to use SuperLocalMemory with.
 
 ### Step 3: Start Using It
 - **In Cursor/Windsurf:** Just talk naturally - "Remember that we use FastAPI for APIs"
-- **In Claude Code:** Use `/superlocalmemoryv2:remember` or the new `slm` commands
+- **In Claude Code:** Use `/superlocalmemoryv2-remember` or the new `slm` commands
 - **In Terminal:** Use `slm remember "content"`
 
 ---
@@ -48,11 +48,11 @@ After installation, restart any IDE you want to use SuperLocalMemory with.
 
 **Usage:**
 ```
-/superlocalmemoryv2:remember "Use FastAPI for REST APIs"
-/superlocalmemoryv2:recall "FastAPI"
-/superlocalmemoryv2:list
-/superlocalmemoryv2:status
-/superlocalmemoryv2:profile list
+/superlocalmemoryv2-remember "Use FastAPI for REST APIs"
+/superlocalmemoryv2-recall "FastAPI"
+/superlocalmemoryv2-list
+/superlocalmemoryv2-status
+/superlocalmemoryv2-profile list
 ```
 
 **OR use the simpler CLI:**
@@ -169,7 +169,7 @@ Continue's AI can also call memory tools directly.
 slashCommands:
   - name: "slm-remember"
     description: "Save to SuperLocalMemory"
-    run: "~/.claude-memory/bin/superlocalmemoryv2:remember \"{{input}}\""
+    run: "~/.claude-memory/bin/superlocalmemoryv2-remember \"{{input}}\""
 
 # For MCP tools
 contextProviders:
@@ -293,7 +293,7 @@ ChatGPT: [calls fetch(42)]
 
 **Commands Installed:**
 - `slm` - Main command
-- All original `superlocalmemoryv2:*` commands still work
+- All original `superlocalmemoryv2-*` commands still work
 
 **Usage:**
 ```bash
@@ -335,7 +335,7 @@ All access methods use the **SAME local SQLite database**:
 │            ACCESS METHODS                   │
 ├─────────────────────────────────────────────┤
 │ TIER 1: Skills                              │
-│  • Claude Code: /superlocalmemoryv2:*       │
+│  • Claude Code: /superlocalmemoryv2-*       │
 │  • Continue: /slm-*                         │
 │  • Cody: /slm-*                            │
 ├─────────────────────────────────────────────┤
@@ -359,7 +359,7 @@ All access methods use the **SAME local SQLite database**:
          └───────────────────┘
 ```
 
-**Key Point:** No matter which method you use, all data goes to the same place. You can use `/superlocalmemoryv2:remember` in Claude Code, then `slm recall` in terminal, and see the same memories.
+**Key Point:** No matter which method you use, all data goes to the same place. You can use `/superlocalmemoryv2-remember` in Claude Code, then `slm recall` in terminal, and see the same memories.
 
 ---
 
@@ -453,11 +453,11 @@ python3 ~/.claude-memory/mcp_server.py --transport http --port 8001
 
 | Old Command | Still Works? | New Alternative |
 |-------------|--------------|-----------------|
-| `superlocalmemoryv2:remember` | ✅ Yes | `slm remember` |
-| `superlocalmemoryv2:recall` | ✅ Yes | `slm recall` |
-| `superlocalmemoryv2:list` | ✅ Yes | `slm list` |
-| `superlocalmemoryv2:status` | ✅ Yes | `slm status` |
-| `superlocalmemoryv2:profile` | ✅ Yes | `slm profile` |
+| `superlocalmemoryv2-remember` | ✅ Yes | `slm remember` |
+| `superlocalmemoryv2-recall` | ✅ Yes | `slm recall` |
+| `superlocalmemoryv2-list` | ✅ Yes | `slm list` |
+| `superlocalmemoryv2-status` | ✅ Yes | `slm status` |
+| `superlocalmemoryv2-profile` | ✅ Yes | `slm profile` |
 
 **Nothing breaks. Everything gains new capabilities.**
 

package/install.sh

@@ -848,10 +848,10 @@ echo ""
 echo "Available commands (two ways to use them):"
 echo ""
 echo "OPTION 1: Original commands (still work):"
-echo "  superlocalmemoryv2:remember  - Save a new memory"
-echo "  superlocalmemoryv2:recall    - Search memories"
-echo "  superlocalmemoryv2:list      - List recent memories"
-echo "  superlocalmemoryv2:status    - Check system status"
+echo "  superlocalmemoryv2-remember  - Save a new memory"
+echo "  superlocalmemoryv2-recall    - Search memories"
+echo "  superlocalmemoryv2-list      - List recent memories"
+echo "  superlocalmemoryv2-status    - Check system status"
 echo ""
 echo "OPTION 2: New simple commands:"
 echo "  slm remember <content>       - Save (simpler syntax)"

package/mcp_server.py

@@ -609,7 +609,7 @@ async def remember(
     """
     Save content to SuperLocalMemory with intelligent indexing.
 
-    This calls the SAME backend as /superlocalmemoryv2:remember skill.
+    This calls the SAME backend as /superlocalmemoryv2-remember skill.
     All memories are stored in the same local SQLite database.
 
     Args:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "2.8.1",
+  "version": "2.8.2",
   "description": "Your AI Finally Remembers You - Local-first intelligent memory system for AI assistants. Works with Claude, Cursor, Windsurf, VS Code/Copilot, Codex, and 17+ AI tools. 100% local, zero cloud dependencies.",
   "keywords": [
     "ai-memory",
@@ -22,7 +22,9 @@
     "chatgpt",
     "chatgpt-connector",
     "openai",
-    "deep-research"
+    "deep-research",
+    "qualixar",
+    "agent-development-platform"
   ],
   "author": {
     "name": "Varun Pratap Bhardwaj",

package/src/graph/graph_core.py

@@ -80,7 +80,7 @@ class GraphEngine:
                 logger.error(f"Missing required tables: {missing}")
                 return {'success': False, 'error': 'database_not_initialized',
                         'message': f"Database not initialized. Missing tables: {', '.join(missing)}",
-                        'fix': "Run 'superlocalmemoryv2:status' first to initialize the database, or add some memories."}
+                        'fix': "Run 'superlocalmemoryv2-status' first to initialize the database, or add some memories."}
 
             active_profile = self._get_active_profile()
             logger.info(f"Building graph for profile: {active_profile}")
@@ -91,12 +91,12 @@ class GraphEngine:
             if len(memories) == 0:
                 return {'success': False, 'error': 'no_memories',
                         'message': 'No memories found in database.',
-                        'fix': "Add some memories first: superlocalmemoryv2:remember 'Your content here'"}
+                        'fix': "Add some memories first: superlocalmemoryv2-remember 'Your content here'"}
             if len(memories) < 2:
                 return {'success': False, 'error': 'insufficient_memories',
                         'message': 'Need at least 2 memories to build knowledge graph.',
                         'memories': len(memories),
-                        'fix': "Add more memories: superlocalmemoryv2:remember 'Your content here'"}
+                        'fix': "Add more memories: superlocalmemoryv2-remember 'Your content here'"}
 
             memories = apply_sampling(cursor, memories, active_profile)
             clear_profile_graph_data(cursor, conn, memories, active_profile)

package/src/memory_store_v2.py

@@ -1201,7 +1201,8 @@ class MemoryStoreV2:
         Removing or obscuring this attribution violates the license terms.
 
         Returns:
-            Dictionary with creator information and attribution requirements
+            Dictionary with creator information and attribution requirements,
+            including Qualixar platform provenance.
         """
         with self._read_connection() as conn:
             cursor = conn.cursor()
@@ -1218,6 +1219,10 @@ class MemoryStoreV2:
                 'attribution_required': 'yes'
             }
 
+        # Qualixar platform provenance (non-breaking additions)
+        attribution['platform'] = 'Qualixar'
+        attribution['verify_url'] = 'https://qualixar.com'
+
         return attribution
 
     def export_for_context(self, query: str, max_tokens: int = 4000) -> str:

package/src/qualixar_attribution.py

@@ -0,0 +1,139 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: MIT
+# Copyright (c) 2026 SuperLocalMemory (superlocalmemory.com)
+# Part of Qualixar — Advancing Agent Development Through Research
+"""
+Qualixar Attribution — Cryptographic output signing for provenance tracking.
+
+Signs tool outputs with SHA-256 content hashes and verifiable provenance
+metadata. Part of the 3-layer Qualixar attribution system:
+  Layer 1: Visible attribution (ATTRIBUTION.md, get_attribution())
+  Layer 2: Cryptographic signing (this module)
+  Layer 3: Steganographic watermarking (qualixar_watermark.py)
+"""
+
+import hashlib
+import json
+import time
+from typing import Any, Dict
+
+
+# Registry of all Qualixar research initiative tools
+TOOL_REGISTRY: Dict[str, str] = {
+    "agentassert": "AgentAssert — Behavioral Contracts",
+    "agentassay": "AgentAssay — Stochastic Testing",
+    "skillfortify": "SkillFortify — Security Validation",
+    "superlocalmemory": "SuperLocalMemory — Agent Memory",
+    "telephonebench": "TelephoneBench — Communication Benchmarks",
+    "vibecheck": "VibeCheck — Code Reliability",
+    "agentreplay": "AgentReplay — Time-Travel Debugging",
+    "agentchaos": "AgentChaos — Chaos Engineering",
+    "agentmigrate": "AgentMigrate — Migration Engineering",
+    "agentpact": "AgentPact — Composition Testing",
+}
+
+
+class QualixarSigner:
+    """Signs tool outputs with cryptographic provenance metadata.
+
+    Adds a ``_qualixar`` block to output dictionaries containing a SHA-256
+    content hash, timestamp, tool information, and a verifiable signature.
+
+    Args:
+        tool_name: Identifier for the tool (e.g. ``"superlocalmemory"``).
+        version: Semantic version string of the tool.
+
+    Example::
+
+        signer = QualixarSigner("superlocalmemory", "2.8.1")
+        signed = signer.sign({"memories": [...]})
+        assert QualixarSigner.verify(signed) is True
+    """
+
+    def __init__(self, tool_name: str, version: str) -> None:
+        self.tool_name = tool_name
+        self.version = version
+        self.tool_desc = TOOL_REGISTRY.get(tool_name, tool_name)
+
+    def sign(self, output_data: Any) -> Dict[str, Any]:
+        """Add cryptographic provenance to any output.
+
+        Args:
+            output_data: The data to sign. If a dict, provenance is added
+                in-place. Otherwise wrapped in ``{"data": ...}``.
+
+        Returns:
+            Dictionary with the original data plus a ``_qualixar`` provenance
+            block containing content_hash, timestamp, and signature.
+        """
+        timestamp = time.time()
+        canonical = json.dumps(output_data, sort_keys=True, default=str)
+        content_hash = hashlib.sha256(canonical.encode()).hexdigest()
+
+        provenance = {
+            "_qualixar": {
+                "tool": self.tool_name,
+                "tool_description": self.tool_desc,
+                "version": self.version,
+                "platform": "Qualixar",
+                "timestamp": timestamp,
+                "content_hash": content_hash,
+                "license": "MIT",
+                "attribution": (
+                    f"Generated by {self.tool_desc} v{self.version}"
+                ),
+                "signature": self._compute_signature(
+                    content_hash, timestamp
+                ),
+            }
+        }
+
+        if isinstance(output_data, dict):
+            output_data.update(provenance)
+            return output_data
+        return {"data": output_data, **provenance}
+
+    def _compute_signature(
+        self, content_hash: str, timestamp: float
+    ) -> str:
+        """Compute HMAC-style signature over content hash and timestamp.
+
+        In production, this should use Ed25519 with a private key.
+        The current implementation uses SHA-256 over a canonical string
+        as a lightweight integrity check.
+
+        Args:
+            content_hash: SHA-256 hex digest of the canonical content.
+            timestamp: Unix timestamp of signing.
+
+        Returns:
+            Hex-encoded SHA-256 signature string.
+        """
+        sig_input = (
+            f"{self.tool_name}:{self.version}:"
+            f"{content_hash}:{timestamp}"
+        )
+        return hashlib.sha256(sig_input.encode()).hexdigest()
+
+    @staticmethod
+    def verify(output_data: Dict[str, Any]) -> bool:
+        """Verify an output's provenance signature.
+
+        Re-computes the content hash from the non-provenance fields and
+        compares it against the hash stored in the ``_qualixar`` block.
+
+        Args:
+            output_data: A dictionary previously signed with :meth:`sign`.
+
+        Returns:
+            ``True`` if the content hash matches, ``False`` otherwise.
+        """
+        prov = output_data.get("_qualixar", {})
+        if not prov:
+            return False
+        content = {
+            k: v for k, v in output_data.items() if k != "_qualixar"
+        }
+        canonical = json.dumps(content, sort_keys=True, default=str)
+        expected_hash = hashlib.sha256(canonical.encode()).hexdigest()
+        return prov.get("content_hash") == expected_hash

package/src/qualixar_watermark.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: MIT
+# Copyright (c) 2026 SuperLocalMemory (superlocalmemory.com)
+# Part of Qualixar — Advancing Agent Development Through Research
+"""
+Qualixar Watermark — Steganographic attribution for text outputs.
+
+Embeds invisible zero-width Unicode characters in text to encode a tool
+identifier. The watermark is invisible to human readers but can be
+extracted programmatically to verify provenance.
+
+Part of the 3-layer Qualixar attribution system:
+  Layer 1: Visible attribution (ATTRIBUTION.md, get_attribution())
+  Layer 2: Cryptographic signing (qualixar_attribution.py)
+  Layer 3: Steganographic watermarking (this module)
+
+No external dependencies required.
+"""
+
+# Zero-width characters for binary encoding
+ZW_SPACE = '\u200b'    # Zero-width space  = bit 0
+ZW_JOINER = '\u200d'   # Zero-width joiner = bit 1
+ZW_SEP = '\ufeff'      # Byte order mark   = separator
+
+
+def encode_watermark(text: str, tool_id: str) -> str:
+    """Embed an invisible watermark in text output.
+
+    Converts ``tool_id`` to binary and encodes each bit as a zero-width
+    Unicode character. The watermark is inserted after the first paragraph
+    break (``\\n\\n``) so it remains invisible to human readers.
+
+    Args:
+        text: The text to watermark.
+        tool_id: Short identifier to embed (e.g. ``"slm"``).
+
+    Returns:
+        The original text with the invisible watermark inserted.
+    """
+    binary = ''.join(format(ord(c), '08b') for c in tool_id)
+    watermark = ZW_SEP
+    for bit in binary:
+        watermark += ZW_SPACE if bit == '0' else ZW_JOINER
+    watermark += ZW_SEP
+
+    # Insert after first paragraph break (invisible to users)
+    if '\n\n' in text:
+        idx = text.index('\n\n') + 2
+        return text[:idx] + watermark + text[idx:]
+    return text + watermark
+
+
+def decode_watermark(text: str) -> str:
+    """Extract a hidden watermark from text.
+
+    Locates the zero-width separator characters and decodes the binary
+    payload between them back into the original tool identifier string.
+
+    Args:
+        text: Text that may contain a watermark.
+
+    Returns:
+        The decoded tool identifier, or an empty string if no watermark
+        is found.
+    """
+    start = text.find(ZW_SEP)
+    if start == -1:
+        return ""
+    end = text.find(ZW_SEP, start + 1)
+    if end == -1:
+        return ""
+    encoded = text[start + 1:end]
+    binary = ''.join(
+        '0' if c == ZW_SPACE else '1'
+        for c in encoded
+    )
+    chars = [binary[i:i + 8] for i in range(0, len(binary), 8)]
+    return ''.join(chr(int(b, 2)) for b in chars if len(b) == 8)

package/src/setup_validator.py

@@ -425,9 +425,9 @@ def validate_setup(auto_fix: bool = False) -> bool:
         print("\n✓ All required checks passed!")
         print("\nQuick Start Commands:")
         print("  1. Add a memory:")
-        print("     superlocalmemoryv2:remember 'Your content here'")
+        print("     superlocalmemoryv2-remember 'Your content here'")
         print("\n  2. Search memories:")
-        print("     superlocalmemoryv2:recall 'search query'")
+        print("     superlocalmemoryv2-recall 'search query'")
         print("\n  3. Build knowledge graph (after adding 2+ memories):")
         print("     python ~/.claude-memory/graph_engine.py build")
         print("\n  4. Start UI server:")