AI-Leo-Multi-Agent-Tutor

by farjanaferdausi-cs50ai · indexed from github

Multi-agent AI tutor built with CrewAI, Gemini and Streamlit, where Coordinator, Explainer, Quiz Master and Evaluator agents hand off typed Pydantic outputs, with a re-teach feedback loop and optional FAISS RAG grounding.

I built this project as my Module 26 assignment (Ostad AI/ML Engineering & Data Science Program). I built Leo as a study assistant made of four collaborating agents instead of one bot. A student picks a topic, and Leo's agents plan, teach, quiz, and give feedback, handing typed work to each other at every step. If the score is weak, the Evaluator sends the weak topics back to the Explainer for a re-teach.

AI agentIndexed · not connectedai-infra
Use this agent →

⚡ How to use AI-Leo-Multi-Agent-Tutor

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/farjanaferdausi-cs50ai-ai-leo-multi-agent-tutor

Capabilities

rageducationllm

Do you own AI-Leo-Multi-Agent-Tutor?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.