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

Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断

Demo of a UI testing agent using the OpenAI CUA model and the Responses API.

LawBench的EvalScope优化版本

🐢 Open-Source Evaluation & Testing for AI & LLM systems

AI+自动化测试平台系统

AI-driven local automation assistant that uses natural language to make computers work by themselves

使用AI大模型，一键生成高清故事短视频。Generate high-definition story short videos with one click using AI large models.

Deepseek V3 and R1 private API, deep thinking, search, full requests. pow challenge reversed. deepseek api.

接口自动化测试平台,基于HttpRunner+Python+Django+Vue,已在多家公司落地使用,2018年服役至今

实时STT，连接OpenAI接口/智谱AI（流式LLM）和GPT-SOVITS/Edge-TTS，通过网页的方式，进行跨网络的服务调用，实现实时对话的效果

Python SDK for running evaluations on LLM generated responses

Label Studio is a multi-type data labeling and annotation tool with standardized output format

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

A curated list of awesome test automation frameworks, tools, libraries, and software for different programming languages. Sponsored by https://zapple.tech and https://automated-testing.info

Knowledge Table is an open-source package designed to simplify extracting and exploring structured data from unstructured documents.

llamafactory blog

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

①[ICLR2024 Spotlight] (GPT-4V/Gemini-Pro/Qwen-VL-Plus+16 OS MLLMs) A benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.

一个基于langchain实现RAG的简单示例

Android performance test

深度学习与PyTorch入门实战视频教程 配套源代码和PPT

pytest 框架【中文文档】分享给测试同事进行学习参考