hui feng

404 bio not found

Joined on Oct 9, 2026

hui feng

Oct 30

Skales: The Universal AI Agent Harness That Dumps Docker and Brings Background Virtual Agents to Every OS

#ai #opensource #python #localai

3 min read

Want to connect with hui feng?

Create an account to connect with hui feng. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

hui feng

Oct 28

Qualcomm GenieX: Run Frontier LLMs & VLMs Locally on Snapdragon Silicon with Go

#ai #opensource #python #localai

3 min read

hui feng

Oct 25

Stop Using Python Wrappers: Build Hardware-Accelerated Local AI Directly in Go with Kronk

#ai #opensource #python #localai

3 min read

hui feng

Oct 25

OGAM: The Zero-Cloud, Multi-Modal Offline AI Powerhouse for Mac and Mobile

#ai #opensource #python #localai

2 min read

hui feng

Oct 24

Text Grab: Fast, Frictionless Offline Windows OCR Powered by Native APIs

#ai #opensource #python #localai

3 min read

hui feng

Oct 23

Run and Fine-Tune Vision Language Models Locally on Apple Silicon with MLX-VLM

#ai #opensource #python #localai

2 min read

hui feng

Oct 23

Turn Any Mac, PC, or Linux Box into a Production-Ready Private AI Server with ODS V3

#ai #opensource #python #localai

3 min read

hui feng

Oct 22

Ditch Massive LLMs for Decisions: Meet jevos, the Fast C++ Inference Engine on Laptop CPUs

#ai #opensource #python #localai

2 min read

hui feng

Oct 21

Skales: The Zero-Setup Autonomous AI Agent That Controls Your Desktop Across OS and Mobile

#ai #opensource #python #localai

3 min read

hui feng

Oct 20

YoVoice: The Open-Source Local Audio and Music Studio That Replaces Costly Speech APIs

#ai #opensource #python #localai

2 min read

hui feng

Oct 19

Meet YoVoice: The 100% Offline AI Audio and Music Studio Slashing API Costs to Zero

#ai #opensource #python #localai

3 min read

hui feng

Oct 17

Lucebox: Turbocharge Local LLM Inference on Mismatched Consumer GPUs with Speculative Decoding

#ai #opensource #python #localai

2 min read

hui feng

Oct 16

Run Ultra-Fast Probabilistic Decision Models on Your Laptop CPU with jevos

#ai #opensource #python #localai

2 min read

hui feng

Oct 16

Sub-5ms Decision Inference on Apple Silicon: Inside laya-coreml

#ai #opensource #python #localai

3 min read

hui feng

Oct 15

YoVoice: The Open-Source Local Audio & Music Studio That Ditches API Fees

#ai #opensource #python #localai

2 min read

hui feng

Oct 15

Run Uncensored GGUF LLMs Offline on Android, iOS, and Desktop with Flutter

#ai #opensource #python #localai

2 min read

hui feng

Oct 14

GenieX: Run Frontier LLMs and VLMs Locally on Snapdragon Silicon with Rust

#ai #opensource #python #localai

2 min read

hui feng

Oct 14

Kronk: Embed llama.cpp, whisper.cpp, and Stable Diffusion Directly into Native Go Binaries

#ai #opensource #python #localai

3 min read

hui feng

Oct 13

Build Ultra-Fast Local AI Pipelines in Go with Kronk: Hardware Acceleration Without Python Overhead

#ai #opensource #python #localai

3 min read

hui feng

Oct 13

Turn Any Hardware Into an Autonomous AI Hub: Hands-on with Olares Personal Cloud OS

#ai #opensource #python #localai

2 min read

hui feng

Oct 13

Turn Any Mac, PC, or Linux Box into a Private AI Server: Hands-on with ODS V3

#ai #opensource #python #localai

2 min read

hui feng

Oct 12

Zero Docker, Zero Cloud: Locally Uncensored Delivers a Full Desktop AI Studio

#ai #opensource #python #localai

3 min read

hui feng

Oct 12

Turn Any Machine into a Self-Hosted AI Powerhouse with Osmantic ODS V3

#ai #opensource #python #localai

2 min read

hui feng

Oct 10

Run Full Kimi K3 on a Single Machine with Deltafin: Rust-Powered Local Inference and OpenAI-Compatible API

#ai #opensource #python #localai

2 min read

hui feng

Oct 10

Stop Renting Your Intelligence: Build Local-First RAG and AI Agents with AnythingLLM

#ai #opensource #python #localai

2 min read

DEV Community

hui feng

Badges

Writing Debut

Skales: The Universal AI Agent Harness That Dumps Docker and Brings Background Virtual Agents to Every OS

Want to connect with hui feng?

Qualcomm GenieX: Run Frontier LLMs & VLMs Locally on Snapdragon Silicon with Go

Stop Using Python Wrappers: Build Hardware-Accelerated Local AI Directly in Go with Kronk

OGAM: The Zero-Cloud, Multi-Modal Offline AI Powerhouse for Mac and Mobile

Text Grab: Fast, Frictionless Offline Windows OCR Powered by Native APIs

Run and Fine-Tune Vision Language Models Locally on Apple Silicon with MLX-VLM

Turn Any Mac, PC, or Linux Box into a Production-Ready Private AI Server with ODS V3

Ditch Massive LLMs for Decisions: Meet jevos, the Fast C++ Inference Engine on Laptop CPUs

Skales: The Zero-Setup Autonomous AI Agent That Controls Your Desktop Across OS and Mobile

YoVoice: The Open-Source Local Audio and Music Studio That Replaces Costly Speech APIs

Meet YoVoice: The 100% Offline AI Audio and Music Studio Slashing API Costs to Zero

Lucebox: Turbocharge Local LLM Inference on Mismatched Consumer GPUs with Speculative Decoding

Run Ultra-Fast Probabilistic Decision Models on Your Laptop CPU with jevos

Sub-5ms Decision Inference on Apple Silicon: Inside laya-coreml

YoVoice: The Open-Source Local Audio & Music Studio That Ditches API Fees

Run Uncensored GGUF LLMs Offline on Android, iOS, and Desktop with Flutter

GenieX: Run Frontier LLMs and VLMs Locally on Snapdragon Silicon with Rust

Kronk: Embed llama.cpp, whisper.cpp, and Stable Diffusion Directly into Native Go Binaries

Build Ultra-Fast Local AI Pipelines in Go with Kronk: Hardware Acceleration Without Python Overhead

Turn Any Hardware Into an Autonomous AI Hub: Hands-on with Olares Personal Cloud OS

Turn Any Mac, PC, or Linux Box into a Private AI Server: Hands-on with ODS V3

Zero Docker, Zero Cloud: Locally Uncensored Delivers a Full Desktop AI Studio

Turn Any Machine into a Self-Hosted AI Powerhouse with Osmantic ODS V3

Run Full Kimi K3 on a Single Machine with Deltafin: Rust-Powered Local Inference and OpenAI-Compatible API

Stop Renting Your Intelligence: Build Local-First RAG and AI Agents with AnythingLLM