intari

seaweedfs

SeaweedFS is a fast distributed storage system for blobs, objects, files, and data lake, for billions of files! Blob store has O(1) disk seek, cloud tiering. Filer supports Cloud Drive, cross-DC active-active replication, Kubernetes, POSIX FUSE mount, S3 API, S3 Gateway, Hadoop, WebDAV, encryption, Erasure Coding.

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Obtainium

Get Android app updates straight from the source.

certificates

🛡️ A private certificate authority (X.509 & SSH) & ACME server for secure automated certificate management, so you can use TLS everywhere & SSO for SSH.

ipatool

Command-line tool that allows searching and downloading app packages (known as ipa files) from the iOS App Store

StabilityMatrix

Multi-Platform Package Manager for Stable Diffusion

Windrecorder

Windrecorder is a memory search app by records everything on your screen in small size, to let you rewind what you have seen, query through OCR text or image description, and get activity statistics.

willow

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

LLamaSharp

A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.

cloudserver

Zenko CloudServer, an open-source Node.js implementation of the Amazon S3 protocol on the front-end and backend storage capabilities to multiple clouds, including Azure and Google.

dns-over-wikipedia

Redirect `.idk` domains using Wikipedia

ByeDPIAndroid

App to bypass censorship on Android

distributed-llama

Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and increase inference speed.

esp-box

The ESP-BOX is a new generation AIoT development platform released by Espressif Systems.

Windows10-CustomKernelSigners

Load self-signed drivers without TestSigning or disable DSE. Transferred from https://github.com/DoubleLabyrinth/Windows10-CustomKernelSigners

Hermes-Function-Calling

action-upterm

Debug your GitHub Actions via SSH by using upterm/tmux to get access to the runner system itself.

willow-inference-server

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

ChatterUI

Simple frontend for LLMs built in react-native.

ssde

SSDE is a collection of utilities that help in having Windows load your custom signed kernel drivers when Secure Boot is on and you own the system's platform key, instead of using test mode.

FUS

SumGPT

Bulk summarization of documents using ChatGPT API

llama-3-quant-comparison

Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.

tubearchivist-plex

Tube Archivist Plex Integration

gptslop

A community list of common phrases generated by GPT and Claude models

RU_Bookmate_downloader

osca

OS Cert Auth - provides info on managing CA certs on various operating systems

docker-mirror

enhanced-cherry-py

simple prompt script to convert hf/ggml files to gguf, and to quantize