一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出可编辑ppt - An AI-native PPT generator based on nano banana pro🍌

Removing safety / refusal behaviour from GPT-OSS.

Toolkit for linearizing PDFs for LLM datasets/training

PyTorch building blocks for the OLMo ecosystem

采用 Cloudscraper 强力绕过 Cloudflare (CF) 人机验证、通过高级请求伪装实现免 Cookie 认证、异步任务轮询实时转换为 OpenAI 兼容的多模态 SSE 流、基于 FastAPI 的高性能 ASGI 架构、集成 Nginx 反向代理并支持 Docker 一键部署

Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers

kiro2api

这是一个金融领域相关的mcp,本项目通过集成 Tushare API 和 Binance API 为语言模型（如Claude）提供全面的实时金融数据访问能力，支持股票、基金、债券、宏观经济指标、稳定币、虚拟货币等多维度金融数据分析。其中也包含了金融数据查询、财经新闻查询、国家统计局数据查询等

Improved AnimateDiff for ComfyUI and Advanced Sampling Support

Crack password hashes without the fuss 🐈

一款长亭自研的完善的安全评估工具，支持常见 web 安全问题扫描和自定义 poc | 使用之前务必先阅读文档

Scalable and user friendly neural 🧠 forecasting algorithms.

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

TradingAgents: Multi-Agents LLM Financial Trading Framework

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

Powerful AI Client

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Curated list of datasets and tools for post-training.

A quick guide (especially) for trending instruction finetuning datasets

BlueLM(蓝心大模型): Open large language models developed by vivo AI Lab

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Adds 3D acceleration support for P106-090 / P106-100 / P104-100 / P104-101 / P102-100 / CMP 30HX / CMP 40HX / CMP 50HX / CMP 70HX / CMP 90HX / CMP 170HX mining cards as well as RTX 3060 3840SP, RTX…

No fortress, purely open ground. OpenManus is Coming.

AI chat for any model.

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

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）

An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Roo Code gives you a whole dev team of AI agents in your code editor.