๐ง Building CogneeCode – AI Developer Memory Assistant
The Problem
Every developer faces the problem of lost context. “Why did I make this decision 3 months ago?” “How did I fix this bug last week?” Current AI tools forget everything between sessions. This is a real problem that wastes hours of developer time.
My Solution
CogneeCode is an AI developer memory assistant that builds a permanent knowledge graph using Cognee Cloud. It remembers every decision, bug fix, and code context you give it.
What It Does
โ
Log architectural decisions with tags and context
โ
Log bug fixes with error messages and solutions
โ
Ask natural language questions about your codebase
โ
Get answers with evidence citations from the knowledge graph
โ
Semantic search across all memories
โ
Visual timeline of all decisions and bug fixes
โ
Analytics dashboard showing memory insights
โ
Knowledge graph visualization
Tech Stack
- Backend: Flask (Python)
- Memory Layer: Cognee Cloud
- LLM: Groq Llama 3.3
- Frontend: Vanilla HTML + CSS + JS
- Icons: Tabler Icons
Cognee Cloud APIs Used
-
remember()– Save decisions and bug fixes with metadata -
recall()– Natural language queries with evidence citations -
search()– Semantic search across memories -
visualize()– Knowledge graph visualization -
improve()– Memory graph enrichment -
forget()– Remove outdated memories
Why This Matters
When you return to a project after months, all your reasoning and solutions are still there, searchable in natural language. No more “Why did I do this?” or “How did I fix this bug?”
Demo
Watch the video: https://youtu.be/TNcBIBuPW7c
Links
๐ GitHub: https://github.com/JOSESAMUEL14/cogneecode
๐ Live Demo: https://josesamuel.pythonanywhere.com
AI Assistance Disclosure
Built with assistance from Claude and Gemini AI.
Built for WeMakeDevs x Cognee Hackathon 2026
Category: Best Use of Cognee Cloud
โญ Star the repo if you find it useful!
๋ต๊ธ ๋จ๊ธฐ๊ธฐ