Stars
Docker image for Remote Desktop server with audio support
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
Private & local AI personal knowledge management app for high entropy people.
A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
DeepSeek Coder: Let the Code Write Itself
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
Lightweight and powerful workflow engine for enterprise & small teams. Single binary with Web UI. 100% open source. No vendor lock-in. It natively supports running containers and executing commands…
🤱🏻 Turn any webpage into a desktop app with one command. 一键打包网页生成轻量桌面应用
Macro-oriented asynchronous web-framework written in Nim with ♥
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allow…
Hierarchical Navigable Small Worlds in the browser
Hands-On Graph Neural Networks Using Python, published by Packt
A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.
🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.
Ansible playbooks for IBM WebSphere Application Server, Connections 6 and others
Malebolgia creates new spawns. Structured concurrency. Thread pools and related APIs.
This is a tui widget that displays throbber. Also known as loading icons, spinner.
Use any web browser as GUI, with Nim in the backend and HTML5 in the frontend.