MemMachine · Viranshu-30 · Dec 22, 2025 · Dec 22, 2025 · Dec 23, 2025 · Dec 23, 2025
diff --git a/examples/hipposync-ai-chat/README.md b/examples/hipposync-ai-chat/README.md
@@ -0,0 +1,139 @@
+# HippoSync - AI Chat with Persistent Memory
+
+A production-ready AI chat application demonstrating MemMachine V2's persistent memory capabilities.
+
+## Overview
+
+HippoSync showcases how to build an AI assistant that remembers user context across multiple conversations using MemMachine's advanced memory architecture.
+
+## Features
+
+- 🧠 **Cross-Chat Memory**: Conversations persist across sessions
+- 🤖 **Multi-Provider AI**: OpenAI GPT-4, Anthropic Claude, Google Gemini
+- 👥 **Team Collaboration**: Shared project workspaces
+- 📄 **Document Processing**: Upload and discuss files
+- 🔐 **Secure Authentication**: JWT-based user management
+
+## Architecture
+```
+React Frontend ←→ FastAPI Backend ←→ MemMachine V2
+                                    ├── PostgreSQL (vectors)
+                                    └── Neo4j (graph)
+```
+
+## MemMachine Integration
+
+### Storing Episodic Memory
+```python
+import requests
+
+def add_memory(user_email: str, content: str):
+    response = requests.post(
+        "http://localhost:8080/api/v2/memories",
+        json={
+            "org_id": f"user-{user_email}",
+            "project_id": "personal",
+            "agent_id": "web-assistant",
+            "content": content
+        }
+    )
+    return response.json()
+```
+
+### Storing Semantic Facts
+```python
+def add_semantic_memory(user_email: str, fact: str):
+    response = requests.post(
+        "http://localhost:8080/api/v2/memories/semantic/add",
+        json={
+            "org_id": f"user-{user_email}",
+            "project_id": "personal",
+            "content": fact,
+            "memory_type": "semantic"
+        }
+    )
+    return response.json()
+```
+
+### Searching Across Conversations
+```python
+def search_memories(user_email: str, query: str):
+    response = requests.post(
+        "http://localhost:8080/api/v2/memories/search",
+        json={
+            "org_id": f"user-{user_email}",
+            "project_id": "personal",
+            "query": query,
+            "top_k": 20,
+            "search_episodic": True,
+            "search_semantic": True
+        }
+    )
+    return response.json()
+```
+
+
+## Key Implementation Files
+
+In the full repository:
+- `backend/app/memmachine_client.py` - MemMachine V2 client
+- `backend/app/routes/chat.py` - Chat with memory integration
+- `backend/app/utils/memory.py` - Fact extraction utilities
+
+## Memory Organization
+```
+user-{email}/
+├── personal/              # Personal conversations
+│   ├── thread-1/         # Individual chat threads
+│   ├── thread-2/
+│   └── ...
+└── project-{id}/         # Team projects
+    └── shared memory
+```
+
+## Example Usage
+
+**First conversation:**
+```
+User: "My name is Sarah and I'm a software engineer"
+Assistant: "Nice to meet you, Sarah! How can I help you today?"
+[Memory stored: User's name is Sarah, occupation is software engineer]
+```
+
+**New conversation (different day):**
+```
+User: "What projects would be good for someone in my field?"
+Assistant: "As a software engineer, I'd recommend..."
+[Retrieved memory: User is a software engineer]
+```
+
+## Tech Stack
+
+**Backend:**
+- FastAPI
+- SQLAlchemy
+- MemMachine V2 API
+
+**Frontend:**
+- React 18
+- Vite
+- Tailwind CSS
+
+**Infrastructure:**
+- Docker
+- PostgreSQL (via MemMachine)
+- Neo4j (via MemMachine)
+
+## Deployment Environments
+
+- ✅ Local Development (Docker Compose)
+- ✅ AWS EC2 (Production)
+- ✅ Docker Swarm (Scalable)
+
+
+## Author
+
+**Viranshu Paruparla**
+- GitHub: [@Viranshu-30](https://github.com/Viranshu-30)
+
+
diff --git a/examples/hipposync-ai-chat/backend/.env.example b/examples/hipposync-ai-chat/backend/.env.example
@@ -0,0 +1,23 @@
+# Application settings
+SECRET_KEY=your-secret-key-here-change-this-in-production
+DATABASE_URL=sqlite:///./app.db
+
+# OpenAI API Key (default/fallback)
+OPENAI_API_KEY=sk-your-openai-api-key-here
+
+# Tavily API Key (for web search)
+# Get your free API key at: https://tavily.com
+TAVILY_API_KEY=tvly-your-tavily-api-key-here
+
+# MemMachine configuration
+MEMMACHINE_BASE_URL=http://localhost:8080
+MEMMACHINE_GROUP_PREFIX=group
+MEMMACHINE_AGENT_ID=web-assistant
+
+# CORS origins (comma-separated for multiple origins)
+CORS_ORIGINS=http://localhost:5173,http://localhost:3000
+
+# Server configuration
+API_HOST=0.0.0.0
+API_PORT=8000
+ACCESS_TOKEN_EXPIRE_MINUTES=10080
diff --git a/examples/hipposync-ai-chat/backend/Dockerfile b/examples/hipposync-ai-chat/backend/Dockerfile
@@ -0,0 +1,18 @@
+FROM python:3.12-slim
+
+# Install build dependencies for bcrypt
+RUN apt-get update && apt-get install -y \
+    gcc \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
diff --git a/examples/hipposync-ai-chat/backend/Dockerfile.txt b/examples/hipposync-ai-chat/backend/Dockerfile.txt
@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
diff --git a/examples/hipposync-ai-chat/backend/app/__init__.py b/examples/hipposync-ai-chat/backend/app/__init__.py