FutureSmart Agent
A complete AI Agent system for real use cases. RAG, NL2SQL, API actions, multi-agent logic — everything in one place.
Read more
P
Participant
Multi-Agent Debugger
Multi-Agent Debugger
AI Demos for Creators Youtube
Votes1
Score5
🧠Community1×5= 5
🌐Public0×1= 0
Individual
December 4, 2025 at 12:25 AM
Project Demo
Submission Details
hear-about-us
AI Demos for Creators Youtube
name
Pruthviraj Mahlaunge
College / University Name
Working professional
linkedIn-profile
- https://www.linkedin.com/in/pruthviraj-mahalunge-446b742b2/
Project Title
Multi-Agent Debugger
Describe what your project does?
My project is a Multi-Agent Python Debugger that uses LangGraph and Groq-powered LLMs to automatically analyze, fix, and re-run broken code in a closed loop. Instead of giving one-shot suggestions like a chatbot, it behaves like a mini CI pipeline: an Analyzer agent detects bugs, a Fixer agent rewrites the code, and a Runner agent executes it safely in a sandbox. The system keeps iterating until the script works or a retry limit is reached. This matters because it demonstrates how LLMs can move beyond static prompts into structured, autonomous workflows, making debugging faster, more reliable, and closer to real developer tooling.
Share a 3–5 minute HD demo video
- https://www.veed.io/view/7d369f4b-95e0-4a36-bd59-61d1c9c76698?source=editor&panel=share
Hosted Project Link (if any)
GitHub Repository (if any)
artifacts/ supporting material
Is this project your original and proprietary work?
Yes
Does your project include any private, sensitive, or restricted code or content?
No
Do you give us (AI Demos & partners) permission to feature your work on our website and share it with our community (with full credit)?
Yes
Do you consent to us showcasing your name/profile on our social media platforms and YouTube
Yes
Are you open to freelance, internship, or collaborative opportunities based on this project?
Yes, I’m interested