AlgoWhisperer: An Open-Source AI that Guides instead of Gives
说明与用途
AlgoWhisperer 是一个开源 AI 导师,提供提示而非完整代码,帮助竞赛程序员在保持隐私的同时学习。
问题
Competitive programmers need a tutor that helps debug code without giving full solutions, preserving learning integrity.
结果
AlgoWhisperer provides targeted debugging hints without revealing full solutions, enabling private, cost‑free learning for competitive programmers.
工作流
- User pastes problem and code into React UI
- Frontend sends context to FastAPI backend
- FastAPI routes request to LangGraph agent
- LangGraph enforces guardrails and forwards to Qwen2.5-Coder-7B-Instruct via Hugging Face Inference API
- Model returns targeted hint instead of full code
- Frontend displays hint to user
证据
We built Algo Whisperer, a strict, Socratic AI programming mentor designed to help developers debug C++ and Python code without ever revealing the final solution.
When we ask the chat for help, our React frontend sends this context to a FastAPI backend.
We are using LangGraph to enforce strict guardrails before it hits the open-weight Qwen 2.5 Coder model on Hugging Face.
The reasoning engine is powered by Qwen/Qwen2.5-Coder-7B-Instruct, accessed via the serverless Hugging Face Inference API.
- 记录日期: 2026-10-04T18:40:59.700Z