hlhr202

React-Combine-Provider

combine react providers in ease

Openconnect-RS

An Openconnect Lib/GUI for rust

LLM-frontend-interaction

this is a show case of LLM interacting with frontend script. it uses LangChain and llama_index

chatgpt-nextjs

Using WebSocket to communicate so it's not usable when deployed to Vercel.

hll-glog-rs

General log writer/reader in rust, built with AES/ECDH/Zlib where all logs can be encrypted and compressed. Based on hll's glog.

gen-prompt-from-url

extract keywords from url, optimize prompt for stable diffusion

nextjs-ts-mobx-playground

SSR + isomorphic

tch-gpt2-poc

toy app

avalon-serverless

Hasura/GraphQL backed Avalon game

bert.cpp

ggml implementation of BERT

bezier-easing-rs

bezier easing, rust port of https://github.com/gre/bezier-easing

ChatGPT-Next-Web

一键拥有你自己的 ChatGPT 网页服务。 One-Click to deploy your own ChatGPT web UI.

clash-rs

clash in Rust

clash-verge

A Clash GUI based on tauri. Supports Windows, macOS and Linux.

Clash.Meta

A rule-based tunnel in Go.

hlhr202

llama-node-doc-deploy

llama-rs

Run LLaMA inference on CPU, with Rust 🦀🚀🦙

llama.cpp

Port of Facebook's LLaMA model in C/C++

llm-chain

`llm-chain` is a powerful rust crate for building chains in large language models allowing you to summarise text and complete complex tasks

local-kubernetes

for local computer usage

onnx-gpt2-example

pingora

A library for building fast, reliable and evolvable network services.

regex-compile-playground

typescript regex compile alternative to timshen's c++ template version

sd-webui-controlnet

WebUI extension for ControlNet

segment-anything-web-demo

Meta Segment Anything Web Demo Fork

sing-box

The universal proxy platform

spring-data-examples

tuic

use-mobx