Compare LLM responses side-by-side in your terminal.

AI-Assisted Novel Development System - A BMAD module for writing novels with 8 specialized agents and 17 workflows

Visual tool to compare LLM responses side-by-side

Official implementation of the paper: Attention Debiasing for Token Pruning in Vision–Language Models.

Text as a Universal User Representation for Transferable Personalization

A lightweight observability tool for visualizing and comparing RAG retrieval strategies. Features real-time embedding visualization and side-by-side performance metrics.

Virtual Agent Control System | Multi‑head LoRA‑based Python backend + Unity WebSocket integration | Enables autonomous dialogue insertion, multi‑scene switching & real‑time behavior control

About A ground-up implementation of the Llama 3 architecture (RoPE, RMSNorm, SwiGLU, GQA) in PyTorch. Features a from-scratch RAG engine, dynamic LoRA adapter switching, and a React visualization d…

A production-ready full-stack AI evaluation platform that lets enterprises compare LLMs (Claude, GPT-4, Gemini) side-by-side before making procurement decisions.

Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex (NeurIPS 2025)

Benchmarks multiple vector databases for movie semantic search using a shared dataset and query set. Includes a CLI tool and a web UI for side-by-side comparisons.

Official code for "Vision Transformers with Self-Distilled Registers" (NeurIPS 2025 Spotlight)

With the Termux MQTT Battery Monitor, you can transform your Android device into a powerful, wireless battery sensor for your smart home network. This project was born out of the need to seamlessly…

GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

Compare multiple LLMs side-by-side using a shared knowledge base, with real-time scoring and live response updates.

Team Unagi's repository for ICFPC 2025

Google's LangExtract works with any model providers

Siitool generates your SII/EEPROM files from the ESI/XML description files of your EtherCAT devices. The program is also capable of interpreting a raw SII/EEPROM file and print it in a human-friend…

A Rust library for extracting structured data from unstructured text using Large Language Models (LLMs), featuring precise source attribution and interactive visualization capabilities.

A Flask-based web application that **tests Gemini model outputs** against pre-defined expected outputs. It supports optional **system prompts**, configurable generation parameters, and provides a *…

让大模型在思考过程中使用搜索和代码工具