A highly optimized inference acceleration engine for Llama and its variants.

A lightweight, functional, and composable framework for building AI agents. No PhD required.

Code for FreeScale, a tuning-free method for higher-resolution visual generation

English pronunciation correction teacher built with gemini

A Model Context Protocol (MCP) server providing path-based task management with dependency tracking & more for Large Language Models (LLM) Agents

A modular web scraping app

ChatGPT 中文版：国内免费使用指南及镜像网站推荐（支持 GPT-4o 和 o1）【2025年1月更新】

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

Roblox Electron Executor is one of the most favorite Roblox Executors at the moment. Before I tell you how to download Electron Executor, let me tell you that it is currently available safely for Windows. But it is not officially available for Android users as of now but the update is coming and will be launched soon.

📊 Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. ⭐ Performance-focused research framework.

Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms

For SDXL, SD1.5, Flux. Nuke T5 and let CLIP guide Flux.1 on its own! Or let let random guide Flux.1! Or load a CLIP crazy opinion embedding about your image and let that guide the AI!

GLM_vision 是一款适用于 chatgpt-on-wechat 的图像和视频分析插件，基于智谱GLM-4V视觉模型，支持通过URL链接分析图片和视频内容。

【ChatGPT 中文版】国内镜像网站免费推荐（支持 4o、o1 和 GPT-4）【2025年1月更新】

implements the methodology outlined in the paper *Cultural Evolution of Cooperation among LLM Agents*. The paper explores whether a society of large language model (LLM) agents can develop cooperative norms through cultural evolution, using the classic *Donor Game*. The goal is to evaluate multi-agent interaction dynamics

RAG-Diffusion re-implemented in sdxl

📚 This Library Management System for Karagastalawa Maha Vidyalaya simplifies book management and borrowing processes. 📖✨ It ensures efficient organization of library resources, 📂 tracks borrowed books, and enhances the overall library experience for students and staff. 🏫💡

Simple project to enable rapid evaluation of different prompts & models

llama.cpp + ROCm + llama-swap

Analyse multiple images simultaneously using local inference on a multimodal LLM.

ChatGPT 中文版：国内免费使用（支持 GPT-4 和 4o、o1）【2025.1.1】

【 ChatGPT 中文版】国内镜像网站推荐 (支持 GPT-4、4o和o1，无需翻墙)【12月最新更新】

Gemini generate, Svelte , React, Vue example

This repo contains AI AGENT using LangChain, Google Gemini LLM and DuckDuckGo

This repository is hosting blog pages

A file-based AI chat tool designed to integrate with Visual Studio Code (VS Code), enabling you to engage with a Large Language Model (LLM) directly within a Markdown file.

The website for the paper "VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving"

Just a bunch of SORA creations .

A script that can run Stable Diffusion on Amazon Sagemaker Studio Lab

Stable Diffusion from Scratch | A PyTorch-based implementation of the full Stable Diffusion pipeline

Running Stable Diffusion in under 400MB in the browser in under half a second

ChatGPT 中文版：国内免费使用与镜像网站推荐（支持 GPT-4 和 4o，无需翻墙）【2024/12/17】 全面整理 ChatGPT 中文版 的国内使用攻略，并为用户推荐无需翻墙的镜像网站。

【ChatGPT 中文版】国内镜像网站免费使用（支持 GPT-4o、o1 和 GPT-4）【2024/12/18】

Okos is a Telegram AI Assistant built with TypeScript, LangGraph, and multiple AI model providers. It maintains conversation context and provides summaries of interactions.

An MCP server that provides LLMs with the latest stable package versions when coding

An AI-powered metrics monitoring and incident management system integrating Prometheus, Grafana, and a self-hosted LLM for dynamic queries, anomaly detection, and intelligent recommendations.

a simple llm load balancer. 利用sglang_router的cache-aware 的负载均衡，实现多模型，多节点的负载均衡

A simple class library used to streamline making 2D applications using OpenGL, GLEW, GLM, SDL, and Box2D.