开源 AI 应用评测平台，支持 RAG、AI Agent、多轮对话、LLM-as-Judge、接口评测、评测报告和人工盲测。Open-source AI evaluation platform for RAG, AI Agents, multi-turn conversations, LLM-as-Judge, endpoint evaluation

QPP for Clarification Need Prediction in context-grounded multi-turn Conversation. Clean implementations of QPP baselines suitable for multi-turn conversational dataset with ranked documents (opt.). Designed to detect ambiguous search queries.

Emotional Support Conversations, an OpenEnv RL environment for training and evaluating AI agents on multi-turn emotional support dialogue. Features a hybrid reward signal (immediate empathy + future-oriented resolution), deterministic seeker simulation for reproducibility, skill-routed agentic policies, and a 3-tier difficulty benchmark.

A lightweight, idiomatic Go client for the Anthropic Claude API.

An AI chatbot built with Gradio and Gemini (LangChain) featuring multi-session chat history and interactive conversation management

Agentic LLM system for behavioral user modeling and personalized recommendation — DSN x BCT Hackathon 3.0 submission.