
A curated list of awesome LLM agents frameworks.

A comprehensive library for implementing LLMs with a unified training pipeline and model evaluation.

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI.

Official GitHub repository for SafetyBench, a benchmark to evaluate the safety of large language models (LLMs).

Self-evaluating interview for AI coders.

A customizable framework for efficient large model evaluation and performance benchmarking.

A collection of benchmarks and datasets for evaluating large language models (LLMs).

VideoMind is a Chain-of-LoRA Agent designed for long video reasoning using human-like processes.

A third-party music player providing local services, desktop lyrics, music downloads, and high sound quality.

AI模型接口管理与分发系统,支持多种大模型统一调用,并提供企业和个人使用的分发管理服务。

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance.

Code for Segment Any Motion in Videos, enabling motion segmentation in video sequences.