Add mem0 Memory Implementation

.github/workflows/pytest-mem0.yml

@@ -0,0 +1,94 @@
+name: Mem0 Memory Tests
+
+on:
+  # Run on pushes to any branch
+  push:
+  # Also run on pull requests to main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    services:
+      neo4j:
+        image: neo4j:5.26.6
+        ports:
+          - 7474:7474    # HTTP
+          - 7687:7687    # BOLT
+        env:
+          NEO4J_AUTH: neo4j/password
+          NEO4J_dbms_security_procedures_unrestricted: apoc.*
+          # Add this to ensure Neo4j is ready for connections quickly
+          NEO4J_dbms_memory_pagecache_size: 100M
+          NEO4J_dbms_memory_heap_initial__size: 100M
+          NEO4J_dbms_memory_heap_max__size: 500M
+        # Try a different health check approach
+        options: >-
+          --health-cmd "wget -O /dev/null -q http://localhost:7474 || exit 1"
+          --health-interval 5s
+          --health-timeout 15s
+          --health-retries 10
+          --health-start-period 30s
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+
+      - name: Wait for Neo4j
+        run: |
+          # Give Neo4j some extra time to start up
+          sleep 10
+          # Try to connect to Neo4j
+          timeout 30s bash -c 'until curl -s http://localhost:7474 > /dev/null; do sleep 1; done'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+
+          # Install core packages first (in the right order)
+          cd python/packages/autogen-core
+          pip install -e .
+
+          cd ../autogen-agentchat
+          pip install -e .
+
+          # Now install autogen-ext with its dependencies
+          cd ../autogen-ext
+          pip install -e ".[dev,mem0,mem0-local]"
+
+          # Install test dependencies
+          pip install pytest pytest-asyncio pytest-cov
+          pip install python-dotenv
+
+          # Install dependencies for complex configuration tests
+          pip install "openai>=1.0.0"
+          pip install deepseek-ai
+
+      # Update test config to match the simplified Neo4j setup
+      - name: Update Neo4j password in tests
+        run: |
+          echo "NEO4J_PASSWORD=password" >> $GITHUB_ENV
+
+      - name: Run tests with coverage
+        # env:
+        #   MEM0_API_KEY: ${{ secrets.MEM0_API_KEY }}
+        #   SF_API_KEY: ${{ secrets.SF_API_KEY }}
+        #   DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
+        run: |
+          cd python/packages/autogen-ext
+          pytest --cov=autogen_ext.memory.mem0 tests/memory/test_mem0.py -v --cov-report=xml
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v3
+        with:
+          file: ./python/packages/autogen-ext/coverage.xml
+          name: codecov-mem0
+          fail_ci_if_error: false

python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/memory.ipynb

@@ -536,6 +536,98 @@
     "4. Optimize embedding models for your specific domain\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Mem0Memory Example\n",
+    "\n",
+    "`autogen_ext.memory.mem0.Mem0Memory` provides integration with `Mem0.ai`'s memory system. It supports both cloud-based and local backends, offering advanced memory capabilities for agents. The implementation handles proper retrieval and context updating, making it suitable for production environments.\n",
+    "\n",
+    "In the following example, we'll demonstrate how to use `Mem0Memory` to maintain persistent memories across conversations:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from autogen_agentchat.agents import AssistantAgent\n",
+    "from autogen_agentchat.ui import Console\n",
+    "from autogen_core.memory import MemoryContent, MemoryMimeType\n",
+    "from autogen_ext.memory.mem0 import Mem0Memory\n",
+    "from autogen_ext.models.openai import OpenAIChatCompletionClient\n",
+    "\n",
+    "# Initialize Mem0 cloud memory (requires API key)\n",
+    "# For local deployment, use is_cloud=False with appropriate config\n",
+    "mem0_memory = Mem0Memory(\n",
+    "    is_cloud=True,\n",
+    "    limit=5,  # Maximum number of memories to retrieve\n",
+    ")\n",
+    "\n",
+    "# Add user preferences to memory\n",
+    "await mem0_memory.add(\n",
+    "    MemoryContent(\n",
+    "        content=\"The weather should be in metric units\",\n",
+    "        mime_type=MemoryMimeType.TEXT,\n",
+    "        metadata={\"category\": \"preferences\", \"type\": \"units\"},\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "await mem0_memory.add(\n",
+    "    MemoryContent(\n",
+    "        content=\"Meal recipe must be vegan\",\n",
+    "        mime_type=MemoryMimeType.TEXT,\n",
+    "        metadata={\"category\": \"preferences\", \"type\": \"dietary\"},\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "# Create assistant with mem0 memory\n",
+    "assistant_agent = AssistantAgent(\n",
+    "    name=\"assistant_agent\",\n",
+    "    model_client=OpenAIChatCompletionClient(\n",
+    "        model=\"gpt-4o-2024-08-06\",\n",
+    "    ),\n",
+    "    tools=[get_weather],\n",
+    "    memory=[mem0_memory],\n",
+    ")\n",
+    "\n",
+    "# Ask about the weather\n",
+    "stream = assistant_agent.run_stream(task=\"What are my dietary preferences?\")\n",
+    "await Console(stream)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The example above demonstrates how Mem0Memory can be used with an assistant agent. The memory integration ensures that:\n",
+    "\n",
+    "1. All agent interactions are stored in Mem0 for future reference\n",
+    "2. Relevant memories (like user preferences) are automatically retrieved and added to the context\n",
+    "3. The agent can maintain consistent behavior based on stored memories\n",
+    "\n",
+    "Mem0Memory is particularly useful for:\n",
+    "- Long-running agent deployments that need persistent memory\n",
+    "- Applications requiring enhanced privacy controls\n",
+    "- Teams wanting unified memory management across agents\n",
+    "- Use cases needing advanced memory filtering and analytics\n",
+    "\n",
+    "Just like ChromaDBVectorMemory, you can serialize Mem0Memory configurations:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Serialize the memory configuration\n",
+    "config_json = mem0_memory.dump_component().model_dump_json()\n",
+    "print(f\"Memory config JSON: {config_json[:100]}...\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

python/packages/autogen-ext/pyproject.toml

@@ -43,6 +43,12 @@ llama-cpp = [
 
 graphrag = ["graphrag>=1.0.1"]
 chromadb = ["chromadb>=1.0.0"]
+mem0 = ["mem0ai>=0.1.98"]
+mem0-local = [
+    "mem0ai>=0.1.98",
+    "neo4j>=5.25.0",
+    "chromadb>=1.0.0"
+]
 web-surfer = [
     "autogen-agentchat==0.6.1",
     "playwright>=1.48.0",