HYSEN LABS DIRECTORY

#Command line

Deployment tag · curated repositories and deep analysis.

513 curated open-source projects
radixark

miles

2,886

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

PythonAI & Machine Learning496 forks
FluidInference

FluidAudio

2,762

Frontier CoreML audio models in your apps - text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

SwiftMobile Development415 forks
openclaw

wacli

2,736

WhatsApp CLI: sync, search, send. Build from source wacli requires Go 1.26.5 or newer and uses go-sqlite3, so cgo + a C compiler are required.

GoDeveloper Tools343 forks
pnnbao97

VieNeu-TTS

2,573

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

PythonDeveloper Tools777 forks
onekey-sec

unblob

2,555

Extract files from any kind of container formats. unblob Accurate, fast, and easy-to-use extraction suite for binary blobs. unblob parses unknown binary blobs for 78+ archive, compression, and file-system formats**, extracts their content recursively, and carves out unknown chunks.

PythonCloud Native & DevOps113 forks
ava-labs

avalanchego

2,358

Go implementation of an Avalanche node. If you plan to build AvalancheGo from source, you will also need the following software: Go version >= 1.25.10 gcc g++ Building From Source Clone The Repository Clone the AvalancheGo repository: This will clone and checkout the master branch.

GoDeveloper Tools863 forks
jfecher

ante

2,341

A safe, easy systems language. These tests have commands in them which the goldentests library uses to run the ante compiler and check its output for each file against the expected output contained within comments of that file.

RustSystems & Infrastructure116 forks
noonghunna

club-3090

2,239

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1 and 2 cards.

PythonDeveloper Tools140 forks