Yufeng He
@he-yufengAI Researcher @ Moonshot AI (Kimi) | MS CS @ HKU | Champion, Shanghai Global AI Contest | 3× ACM-ICPC Silver | Former Intern @ Baidu, Maimai, Kuaishou
Language Breakdown
Lines of code distribution across 22 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in HTML
Collaboration Network
Global Impact visualization
Repos
110
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Xinhao Chen
@blablabiu
Songlin Yang
@sustcsonglin
Ruochen Pan
@RC-CHN
Teng Ma
@stmatengss
chaohuang-ai
@chaohuang-ai
Top Repositories
Minimal AI coding agent (~1,400 LoC Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with adaptive difficulty.
Open-source DeepWiki alternative — generate comprehensive wiki documentation for any codebase from terminal or browser
AI agent that reads the fine print so you don't have to. Upload any contract → get red flags, unfair terms, and plain-English explanations in seconds.
AI-powered open source contribution finder and repo radar
Drop-in pytest plugin for regression-testing AI agents — snapshot baselines, semantic comparison, mock LLMs
AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 lines of Python.
Pit AI coding agents against the same bug. Score them on tests, diff, cost, and time — pick the winning patch.
A pip-installable benchmark runner for LLMs and agents. Five minutes to your first eval.
Open Source Impact
Contributions to external projects
