Instant-loading web apps, without effort

🐚 OpenDevin: Code Less, Make More

Private Web Search for Local LLMs

Create beautiful OG images, Twitter/X Header Images & more for free, in simple clicks.

OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistributi…

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. Core Capabilities: 1) domain model constr…

KAG is a knowledge-enhanced generation framework based on OpenSPG engine, which is used to build knowledge-enhanced rigorous decision-making and information retrieval knowledge services

The memory layer for Personalized AI

real time face swap and one-click video deepfake with only a single image (uncensored)

A modular graph-based Retrieval-Augmented Generation (RAG) system

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

在原版的基础上修改了显示 VLESS 配置信息转换为订阅内容。使用该脚本，你可以方便地将 VLESS 配置信息使用在线配置转换到 Clash 或 Singbox 等工具中。

Brand new TTS solution

思源笔记免登录版本；可以不登录使用同步功能

A task queue with REST API

该项目可以让你通过订阅的方式使用Cloudflare WARP+，自动获取流量。This project enables you to use Cloudflare WARP+ through subscription, automatically acquiring traffic.

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (ACL 2024)

Deterministic LLMs Outputs for AI Applications and AI Agents

The official Meta Llama 3 GitHub site

Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。

🌩支持多家云存储的云盘系统 (Self-hosted file management and sharing system, supports multiple storage providers)

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.