Every night, millions of people go to sleep feeling lost and forgotten. Today's AI tools are stateless—they forget you the moment you close the tab. Your struggles disappear. Your goals vanish. Your growth is invisible.
I built Mnemo AI, a Life Intelligence Platform that builds a permanent knowledge graph of your entire life journey. It remembers everything you share—your name, your pet's name, your goals, your journal entries, and your emotions.
I built Mnemo AI solo in 7 days. Every day was a challenge, but I never gave up.
Day 1-2: Setup Flask + Cognee integration. Hit my first roadblock with async event loops on Windows.
Day 3-4: Built the chat interface and memory recall. Fixed the "cat's name" bug.
Day 5-6: Added journal, insights, timeline. Integrated Groq LLM.
Day 7: Polished UI, added dark mode, voice input, and keyboard shortcuts.
The Hardest Moment: Getting Cognee to work on Render's free tier. After hours of debugging, I learned that Cognee Cloud requires proper authentication setup.
The Proudest Moment: Fixing the "cat's name" bug and seeing "Whiskers!" instead of "Your name is Priya!"
Mnemo AI uses Cognee V1's revolutionary memory layer with all 4 core APIs:
One of the biggest challenges was fixing the name detection bug. The app incorrectly matched any query containing the word "name", so "What's my cat's name?" would return the user's name!
The Fix: I implemented regex-based intent detection that distinguishes between "my name" and "cat's name":
def is_user_name_query(q):
patterns = [
r"^what('?s| is)? my name\??$",
r"^who am i\??$",
r"^what do you call me\??$",
]
return any(re.match(pattern, q) for pattern in patterns)
Now "What's my cat's name?" correctly returns "Whiskers!" 🎉
Key Features
🧠 Chat with Memory Recall - Ask anything about your life
📓 Journal with Emotion Detection - Write about your day
📊 Insights Dashboard - Track your growth patterns
⏳ Time Capsules - Write to your future self
🎯 Goals Tracker - Never forget your dreams
🎤 Voice Input/Output - Speak to Mnemo
🌓 Dark/Light Mode - Smooth theme switching
⌨️ Keyboard Shortcuts - Power user controls
Tech Stack
Layer Technology Cost
Backend Python Flask Free
Memory Cognee V1 Free
LLM Groq Llama 3.3 70B Free
Frontend Vanilla HTML + CSS + JS Free
Voice Web Speech API Free
PWA Service Worker Free
Total Cost: ₹0
What I Learned
Cognee's hybrid graph-vector memory is incredibly powerful for building memory-enabled AI
Async event loops on Windows require special handling
Intent detection needs to be precise (not just keyword matching)
Polished UI makes a huge difference in user experience
Never give up - the "cat's name" bug took 2 days to fix but was worth it
Demo Video
Watch Mnemo AI in action:
[Link to your YouTube demo]
Try It Yourself
GitHub: https://github.com/JOSESAMUEL14/mnemo-ai-final
Live Demo: https://mnemo-ai.onrender.com
What's Next for Mnemo AI
🚀 Mobile App - React Native version
🔗 Integration - Connect with calendar, email, notes
🧠 Advanced Analytics - Deeper life pattern recognition
🌐 Multi-language - Support for Tamil, Hindi, and more
Acknowledgments
Cognee Team — for building the most powerful open source memory layer
WeMakeDevs — for organizing this incredible hackathon
Groq — for providing free blazing-fast LLM inference
Built with ❤️ and determination. Solo. 7 days. ₹0.
"The AI That Never Forgets You"
text
---
## ✅ **WHAT I FIXED:**
| Issue | Fix |
|-------|-----|
| Missing closing backticks | Added ` ```
` after the code block (line after `return any(re.match(pattern, q) for pattern in patterns)`) |
---
## 📝 **NOW PUBLISH:**
1. Go to: https://dev.to/new
2. **Title:** `Mnemo AI: Building an AI That Never Forgets You`
3. **Tags:** `cognee, ai, hackathon, python, flask`
4. **Paste the corrected content**
5. Click **"Publish"**
---
## 🎯 **Then Update the Google Form with the Blog URL!** 🚀