better-mem0-mcp 1.1.0b22__tar.gz → 1.1.3__tar.gz

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/.github/workflows/cd.yml

@@ -46,49 +46,12 @@ jobs:
           chmod +x .github/scripts/check-ci-cd-status.sh
           ./.github/scripts/check-ci-cd-status.sh --branch=dev
 
-      - name: Sync main into dev (resolve version conflicts)
-        run: |
-          git config user.name "github-actions[bot]"
-          git config user.email "github-actions[bot]@users.noreply.github.com"
-          git checkout dev
-          git fetch origin main
-          git merge origin/main --no-edit -X ours || true
-          git push origin dev
-
-      - name: Create PR to promote dev to main
+      - name: Merge dev to main
         env:
-          GH_TOKEN: ${{ secrets.GH_PAT }}
+          AUTO_RESOLVE_FILES: "CHANGELOG.md,pyproject.toml"
         run: |
-          # Check if PR already exists
-          EXISTING_PR=$(gh pr list --base main --head dev --json number --jq '.[0].number')
-          if [ -n "$EXISTING_PR" ]; then
-            echo "PR #$EXISTING_PR already exists for dev -> main"
-            echo "URL: https://github.com/${{ github.repository }}/pull/$EXISTING_PR"
-            exit 0
-          fi
-
-          # Get latest release version from dev
-          LATEST_TAG=$(git describe --tags --abbrev=0 origin/dev 2>/dev/null || echo "")
-          if [ -z "$LATEST_TAG" ]; then
-            PR_TITLE="chore: promote dev to main"
-          else
-            PR_TITLE="chore: promote dev to main ($LATEST_TAG)"
-          fi
-
-          # Create PR
-          gh pr create \
-            --base main \
-            --head dev \
-            --title "$PR_TITLE" \
-            --body "## Promote dev to main
-
-          This PR promotes the latest changes from \`dev\` branch to \`main\`.
-
-          ### Pre-checks passed:
-          - ✅ CI workflow passed on dev
-          - ✅ CD workflow passed on dev
-
-          ### Latest beta version: $LATEST_TAG"
+          chmod +x .github/scripts/merge-with-auto-resolve.sh
+          ./.github/scripts/merge-with-auto-resolve.sh --source=dev --target=main --files="$AUTO_RESOLVE_FILES"
 
   release:
     name: Semantic Release
@@ -108,7 +71,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: "24"
+          node-version: "22"
 
       - name: Install uv (for toml-cli)
         uses: astral-sh/setup-uv@v5

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/.mise.toml

@@ -5,7 +5,7 @@
 
 [tools]
 python = "3.13"
-node = "24"
+node = "22"
 uv = "latest"
 
 [settings]

better_mem0_mcp-1.1.3/.vscode/better-mem0-mcp.code-workspace

@@ -0,0 +1,8 @@
+{
+	"folders": [
+		{
+			"path": ".."
+		}
+	],
+	"settings": {}
+}

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/CHANGELOG.md

@@ -1,30 +1,9 @@
-# [1.1.0-beta.22](https://github.com/n24q02m/better-mem0-mcp/compare/v1.1.0-beta.21...v1.1.0-beta.22) (2026-02-05)
+## [1.1.3](https://github.com/n24q02m/better-mem0-mcp/compare/v1.1.2...v1.1.3) (2026-01-05)
 
 
 ### Bug Fixes
 
-* Pin Python version to 3.13 and remove Python 3.14 compatibility from the dependency lock file. ([ec134ef](https://github.com/n24q02m/better-mem0-mcp/commit/ec134ef10ab6de3eaf800d51a441fe2b44f2d4dc))
-
-# [1.1.0-beta.21](https://github.com/n24q02m/better-mem0-mcp/compare/v1.1.0-beta.20...v1.1.0-beta.21) (2026-01-12)
-
-
-### Bug Fixes
-
-* update Node.js version to 24 in CI/CD configuration and Mise setup ([92ab0a9](https://github.com/n24q02m/better-mem0-mcp/commit/92ab0a96cd30643b9ecf927c68b46cde6472d732))
-
-# [1.1.0-beta.20](https://github.com/n24q02m/better-mem0-mcp/compare/v1.1.0-beta.19...v1.1.0-beta.20) (2026-01-05)
-
-
-### Bug Fixes
-
-* correct search response parsing and improve documentation ([d4d4753](https://github.com/n24q02m/better-mem0-mcp/commit/d4d4753a7d0d3c8eb23ef15c051a7bcb1b000310))
-
-# [1.1.0-beta.19](https://github.com/n24q02m/better-mem0-mcp/compare/v1.1.0-beta.18...v1.1.0-beta.19) (2026-01-05)
-
-
-### Bug Fixes
-
-* correct Mem0 API response parsing for search and get_all ([8a612b1](https://github.com/n24q02m/better-mem0-mcp/commit/8a612b1443c59c229e7583ffedced6d38f1b13d1))
+* Add `__main__.py` entry point and update README with `better-mem0` server configuration. ([5c44f58](https://github.com/n24q02m/better-mem0-mcp/commit/5c44f58a5357c90c586009f75ddd876c45ef6f66))
 
 # [1.1.0-beta.18](https://github.com/n24q02m/better-mem0-mcp/compare/v1.1.0-beta.17...v1.1.0-beta.18) (2026-01-05)
 

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/CONTRIBUTING.md

@@ -84,8 +84,6 @@ We use [Conventional Commits](https://www.conventionalcommits.org/):
 - `perf`: Performance improvements
 - `test`: Adding or updating tests
 - `chore`: Maintenance tasks
-- `ci`: CI/CD changes
-- `build`: Build system changes
 
 ### Examples
 
@@ -95,44 +93,6 @@ fix: handle database connection timeout
 docs: update configuration examples
 ```
 
-## Release Process
-
-Releases are automated using **Semantic Release**. We strictly follow the **Conventional Commits** specification to determine version bumps and generate changelogs automatically.
-
-### How to Release
-
-1. Create a Pull Request with your changes.
-2. Ensure your commit messages follow the convention above.
-3. Merge the PR to `main`.
-4. The CI pipeline will automatically:
-   - Analyze the new commits
-   - Determine the next version number
-   - Generate release notes
-   - Update `CHANGELOG.md`
-   - Publish to PyPI
-   - Create a GitHub Release
-   - Build and push Docker images
-
-You do **not** need to create manual tags or changelog entries.
-
-## Pull Request Guidelines
-
-- Keep PRs focused on a single feature or fix
-- Update documentation if needed
-- Add tests for new functionality
-- Ensure all checks pass
-
-### PR Checklist
-
-Before submitting your PR, ensure:
-
-- [ ] Code follows Python best practices
-- [ ] All tests pass (`uv run pytest`)
-- [ ] Linting passes (`uv run ruff check .`)
-- [ ] Formatting is correct (`uv run ruff format --check .`)
-- [ ] Commit messages follow **Conventional Commits**
-- [ ] Documentation updated (if needed)
-
 ## Code Style
 
 This project uses **Ruff** for formatting and linting.
@@ -166,15 +126,6 @@ better-mem0-mcp/
 └── README.md
 ```
 
-## Questions?
-
-Feel free to open an issue for:
-
-- Bug reports
-- Feature requests
-- Questions about the codebase
-- Discussion about architecture
-
 ## License
 
 By contributing, you agree that your contributions will be licensed under the MIT License.

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: better-mem0-mcp
-Version: 1.1.0b22
+Version: 1.1.3
 Summary: Zero-setup MCP Server for AI memory - works with Neon/Supabase
 Project-URL: Homepage, https://github.com/n24q02m/better-mem0-mcp
 Project-URL: Repository, https://github.com/n24q02m/better-mem0-mcp.git
@@ -17,7 +17,7 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: ==3.13.*
+Requires-Python: >=3.13
 Requires-Dist: google-genai>=1.0.0
 Requires-Dist: litellm>=1.0.0
 Requires-Dist: loguru>=0.7.0
@@ -29,28 +29,16 @@ Description-Content-Type: text/markdown
 
 # better-mem0-mcp
 
-**Self-hosted MCP Server for AI memory with PostgreSQL (pgvector).**
+**Zero-setup** MCP Server for AI memory. Works with Neon/Supabase free tier.
 
-[![PyPI](https://img.shields.io/pypi/v/better-mem0-mcp)](https://pypi.org/project/better-mem0-mcp/)
-[![Docker](https://img.shields.io/docker/v/n24q02m/better-mem0-mcp?label=docker)](https://hub.docker.com/r/n24q02m/better-mem0-mcp)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
-
-## Features
-
-- **Self-hosted PostgreSQL** - Your data stays with you (Neon/Supabase free tier supported)
-- **Graph Memory** - SQL-based relationship tracking alongside vector memory
-- **Multi-provider LLM** - Gemini, OpenAI, Anthropic, Groq, DeepSeek, Mistral
-- **Fallback chains** - Multi-key per provider + multi-model fallback
-- **Zero manual setup** - Just `DATABASE_URL` + `API_KEYS`
-
----
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ## Quick Start
 
 ### 1. Get Prerequisites
 
-- **Database**: [Neon](https://neon.tech) or [Supabase](https://supabase.com) (free tier works)
-- **API Key**: Any supported provider ([Google AI Studio](https://aistudio.google.com/apikey) is free)
+- **Database**: [Neon](https://neon.tech) or [Supabase](https://supabase.com) (free tier)
+- **API Key**: [Google AI Studio](https://aistudio.google.com/apikey) (free tier)
 
 ### 2. Add to mcp.json
 
@@ -64,7 +52,7 @@ Description-Content-Type: text/markdown
       "args": ["better-mem0-mcp@latest"],
       "env": {
         "DATABASE_URL": "postgresql://user:pass@xxx.neon.tech/neondb?sslmode=require",
-        "API_KEYS": "GOOGLE_API_KEY:AIza..."
+        "API_KEYS": "gemini:AIza..."
       }
     }
   }
@@ -81,7 +69,7 @@ Description-Content-Type: text/markdown
       "args": ["run", "-i", "--rm", "-e", "DATABASE_URL", "-e", "API_KEYS", "n24q02m/better-mem0-mcp:latest"],
       "env": {
         "DATABASE_URL": "postgresql://...",
-        "API_KEYS": "GOOGLE_API_KEY:AIza..."
+        "API_KEYS": "gemini:AIza..."
       }
     }
   }
@@ -90,7 +78,7 @@ Description-Content-Type: text/markdown
 
 ### 3. Done!
 
-Ask your AI: "Remember that I prefer dark mode and use FastAPI"
+Ask Claude: "Remember that I prefer dark mode and use FastAPI"
 
 ---
 
@@ -98,25 +86,22 @@ Ask your AI: "Remember that I prefer dark mode and use FastAPI"
 
 | Variable | Required | Description |
 |----------|----------|-------------|
-| `DATABASE_URL` | Yes | PostgreSQL with pgvector extension |
-| `API_KEYS` | Yes | `ENV_VAR:key` pairs, comma-separated |
-| `LLM_MODELS` | No | Model fallback chain |
-| `EMBEDDER_MODELS` | No | Embedding model chain |
+| `DATABASE_URL` | Yes | PostgreSQL connection string |
+| `API_KEYS` | Yes | `provider:key,...` (multi-key per provider OK) |
+| `LLM_MODELS` | No | `provider/model,...` (fallback chain) |
+| `EMBEDDER_MODELS` | No | `provider/model,...` (fallback chain) |
 
-### Supported LiteLLM Providers
+### Examples
 
-Use environment variable names from [LiteLLM docs](https://docs.litellm.ai/):
-`GOOGLE_API_KEY`, `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GROQ_API_KEY`, etc.
-
-**Single provider:**
-```bash
-API_KEYS=GOOGLE_API_KEY:AIza...
+**Minimal (Gemini only):**
+```
+API_KEYS=gemini:AIza...
 ```
 
 **Multi-key with fallback:**
-```bash
-API_KEYS=GOOGLE_API_KEY:AIza-1,GOOGLE_API_KEY:AIza-2,OPENAI_API_KEY:sk-xxx
-LLM_MODELS=gemini/gemini-3-flash-preview,openai/gpt-4o-mini
+```
+API_KEYS=gemini:AIza-1,gemini:AIza-2,openai:sk-xxx
+LLM_MODELS=gemini/gemini-2.5-flash,openai/gpt-4o-mini
 EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
 ```
 
@@ -124,7 +109,7 @@ EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
 
 | Setting | Default |
 |---------|---------|
-| `LLM_MODELS` | `gemini/gemini-3-flash-preview` |
+| `LLM_MODELS` | `gemini/gemini-2.5-flash` |
 | `EMBEDDER_MODELS` | `gemini/gemini-embedding-001` |
 
 ---
@@ -133,41 +118,32 @@ EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
 
 | Tool | Description |
 |------|-------------|
-| `memory` | Memory operations: `add`, `search`, `list`, `delete` |
-| `help` | Get full documentation for tools |
+| `memory` | `action`: add, search, list, delete |
+| `help` | Detailed documentation |
 
-### Usage Examples
+### Usage
 
 ```json
 {"action": "add", "content": "I prefer TypeScript over JavaScript"}
-{"action": "search", "query": "programming preferences"}
+{"action": "search", "query": "preferences"}
 {"action": "list"}
 {"action": "delete", "memory_id": "abc123"}
 ```
 
 ---
 
-## Build from Source
+## Why better-mem0-mcp?
 
-```bash
-git clone https://github.com/n24q02m/better-mem0-mcp
-cd better-mem0-mcp
-
-# Setup (requires mise: https://mise.jdx.dev/)
-mise run setup
-
-# Run
-uv run better-mem0-mcp
-```
-
-**Requirements:** Python 3.13+
+| Feature | Official mem0-mcp | better-mem0-mcp |
+|---------|-------------------|-----------------|
+| Storage | Mem0 Cloud | **Self-hosted PostgreSQL** |
+| Graph Memory | No | **Yes (SQL-based)** |
+| LLM Provider | OpenAI only | **Any (Gemini/OpenAI/Ollama/...)** |
+| Fallback | No | **Yes (multi-key + multi-model)** |
+| Setup | API Key | **DATABASE_URL + API_KEYS** |
 
 ---
 
-## Contributing
-
-See [CONTRIBUTING.md](CONTRIBUTING.md)
-
 ## License
 
-MIT - See [LICENSE](LICENSE)
+MIT

better_mem0_mcp-1.1.3/README.md

@@ -0,0 +1,120 @@
+# better-mem0-mcp
+
+**Zero-setup** MCP Server for AI memory. Works with Neon/Supabase free tier.
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+## Quick Start
+
+### 1. Get Prerequisites
+
+- **Database**: [Neon](https://neon.tech) or [Supabase](https://supabase.com) (free tier)
+- **API Key**: [Google AI Studio](https://aistudio.google.com/apikey) (free tier)
+
+### 2. Add to mcp.json
+
+#### uvx (Recommended)
+
+```json
+{
+  "mcpServers": {
+    "better-mem0": {
+      "command": "uvx",
+      "args": ["better-mem0-mcp@latest"],
+      "env": {
+        "DATABASE_URL": "postgresql://user:pass@xxx.neon.tech/neondb?sslmode=require",
+        "API_KEYS": "gemini:AIza..."
+      }
+    }
+  }
+}
+```
+
+#### Docker
+
+```json
+{
+  "mcpServers": {
+    "better-mem0": {
+      "command": "docker",
+      "args": ["run", "-i", "--rm", "-e", "DATABASE_URL", "-e", "API_KEYS", "n24q02m/better-mem0-mcp:latest"],
+      "env": {
+        "DATABASE_URL": "postgresql://...",
+        "API_KEYS": "gemini:AIza..."
+      }
+    }
+  }
+}
+```
+
+### 3. Done!
+
+Ask Claude: "Remember that I prefer dark mode and use FastAPI"
+
+---
+
+## Configuration
+
+| Variable | Required | Description |
+|----------|----------|-------------|
+| `DATABASE_URL` | Yes | PostgreSQL connection string |
+| `API_KEYS` | Yes | `provider:key,...` (multi-key per provider OK) |
+| `LLM_MODELS` | No | `provider/model,...` (fallback chain) |
+| `EMBEDDER_MODELS` | No | `provider/model,...` (fallback chain) |
+
+### Examples
+
+**Minimal (Gemini only):**
+```
+API_KEYS=gemini:AIza...
+```
+
+**Multi-key with fallback:**
+```
+API_KEYS=gemini:AIza-1,gemini:AIza-2,openai:sk-xxx
+LLM_MODELS=gemini/gemini-2.5-flash,openai/gpt-4o-mini
+EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
+```
+
+### Defaults
+
+| Setting | Default |
+|---------|---------|
+| `LLM_MODELS` | `gemini/gemini-2.5-flash` |
+| `EMBEDDER_MODELS` | `gemini/gemini-embedding-001` |
+
+---
+
+## Tools
+
+| Tool | Description |
+|------|-------------|
+| `memory` | `action`: add, search, list, delete |
+| `help` | Detailed documentation |
+
+### Usage
+
+```json
+{"action": "add", "content": "I prefer TypeScript over JavaScript"}
+{"action": "search", "query": "preferences"}
+{"action": "list"}
+{"action": "delete", "memory_id": "abc123"}
+```
+
+---
+
+## Why better-mem0-mcp?
+
+| Feature | Official mem0-mcp | better-mem0-mcp |
+|---------|-------------------|-----------------|
+| Storage | Mem0 Cloud | **Self-hosted PostgreSQL** |
+| Graph Memory | No | **Yes (SQL-based)** |
+| LLM Provider | OpenAI only | **Any (Gemini/OpenAI/Ollama/...)** |
+| Fallback | No | **Yes (multi-key + multi-model)** |
+| Setup | API Key | **DATABASE_URL + API_KEYS** |
+
+---
+
+## License
+
+MIT

better_mem0_mcp-1.1.3/SECURITY.md

@@ -0,0 +1,27 @@
+# Security Policy
+
+## Supported Versions
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 0.x.x   | :white_check_mark: |
+
+## Reporting a Vulnerability
+
+If you discover a security vulnerability, please report it by:
+
+1. **Do NOT** create a public GitHub issue
+2. Email the maintainer directly or use GitHub's private vulnerability reporting
+3. Include detailed steps to reproduce the issue
+4. Allow reasonable time for a fix before public disclosure
+
+We take security seriously and will respond promptly to valid reports.
+
+## Security Best Practices
+
+When using better-mem0-mcp:
+
+- **Never commit API keys** to version control
+- Use environment variables or secure secret management
+- Keep dependencies updated
+- Use `sslmode=require` for production database connections

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "better-mem0-mcp"
-version = "1.1.0-beta.22"
+version = "1.1.3"
 description = "Zero-setup MCP Server for AI memory - works with Neon/Supabase"
 readme = "README.md"
 license = { text = "MIT" }
@@ -16,7 +16,7 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
 ]
-requires-python = "==3.13.*"
+requires-python = ">=3.13"
 dependencies = [
     # MCP Server
     "mcp[cli]>=1.0.0",

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/src/better_mem0_mcp/config.py

@@ -33,36 +33,43 @@ class Settings(BaseSettings):
     embedder_models: str = "gemini/gemini-embedding-001"
 
     def setup_api_keys(self) -> dict[str, list[str]]:
-        """Parse API_KEYS (format: ENV_VAR:key,...) and set env vars.
-
-        Example:
-            API_KEYS="GOOGLE_API_KEY:abc,GOOGLE_API_KEY:def,OPENAI_API_KEY:xyz"
+        """
+        Parse API_KEYS and set environment variables for LiteLLM.
 
         Returns:
-            Dict mapping env var name to list of API keys.
+            Dict mapping provider to list of API keys.
         """
-        keys_by_env: dict[str, list[str]] = {}
+        env_map = {
+            "gemini": "GOOGLE_API_KEY",
+            "openai": "OPENAI_API_KEY",
+            "anthropic": "ANTHROPIC_API_KEY",
+            "groq": "GROQ_API_KEY",
+            "deepseek": "DEEPSEEK_API_KEY",
+            "mistral": "MISTRAL_API_KEY",
+        }
+
+        keys_by_provider: dict[str, list[str]] = {}
 
         for pair in self.api_keys.split(","):
             pair = pair.strip()
             if ":" not in pair:
                 continue
 
-            env_var, key = pair.split(":", 1)
-            env_var = env_var.strip()
+            provider, key = pair.split(":", 1)
+            provider = provider.strip().lower()
             key = key.strip()
 
             if not key:
                 continue
 
-            keys_by_env.setdefault(env_var, []).append(key)
+            keys_by_provider.setdefault(provider, []).append(key)
 
-        # Set first key of each env var (LiteLLM reads from env)
-        for env_var, keys in keys_by_env.items():
-            if keys:
-                os.environ[env_var] = keys[0]
+        # Set first key of each provider as env var (LiteLLM reads from env)
+        for provider, keys in keys_by_provider.items():
+            if provider in env_map and keys:
+                os.environ[env_map[provider]] = keys[0]
 
-        return keys_by_env
+        return keys_by_provider
 
     def parse_database_url(self) -> dict:
         """Parse DATABASE_URL into connection parameters."""

{better_mem0_mcp-1.1.0b22 → better_mem0_mcp-1.1.3}/src/better_mem0_mcp/docs/memory.md

@@ -17,8 +17,6 @@ Save information to long-term memory. Mem0 automatically:
 {"action": "add", "content": "User prefers dark mode and uses FastAPI"}
 ```
 
-**Response:** `Saved: {results: [{id, memory, event}]}`
-
 ### search
 Semantic search across stored memories. Combines vector search with graph context.
 
@@ -26,8 +24,6 @@ Semantic search across stored memories. Combines vector search with graph contex
 {"action": "search", "query": "coding preferences", "limit": 5}
 ```
 
-**Response:** Formatted list of matching memories with optional graph context.
-
 ### list
 Get all stored memories for a user.
 
@@ -35,8 +31,6 @@ Get all stored memories for a user.
 {"action": "list"}
 ```
 
-**Response:** `Memories (N): - [id] memory text`
-
 ### delete
 Remove a memory by ID.
 
@@ -44,17 +38,10 @@ Remove a memory by ID.
 {"action": "delete", "memory_id": "abc12345-..."}
 ```
 
-**Response:** `Deleted: {memory_id}`
-
 ## Parameters
 - `action` - Required: add, search, list, delete
 - `content` - Required for add: information to remember
 - `query` - Required for search: what to search for
 - `memory_id` - Required for delete: ID of memory to remove
 - `limit` - Optional for search: max results (default: 5)
-- `user_id` - Optional: scope memories to a specific user (default: "default")
-
-## Technical Notes
-- Mem0 API returns `{"results": [...]}` for both `search()` and `get_all()`
-- Graph context is automatically included in search results when available
-- Embeddings use 1536 dimensions for pgvector HNSW compatibility
+- `user_id` - Optional: scope memories to a specific user