Stars
OpenMPTCProuter is an open source solution to aggregate multiple internet connections using Multipath TCP (MPTCP) on OpenWrt
OpenWrt 25.12 for the Xiaomi CB0401V2 (Magenta 5G AX5400 V2) 5G CPE: modem, WiFi, LEDs, NFC, sysupgrade
Proxmox VE Helper-Scripts (Community Edition)
All parts of Claude Code's system prompt, builtin tool descriptions, subagent prompts (Plan/Explore/Task), and utility prompts. Updated for each Claude Code version.
The best way to control Claude Code, Codex and more from any computer or phone
The agent skills I use every day. Works with Claude Code and Codex.
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io
Next generation Matrix client for iOS built with SwiftUI on top of matrix-rust-sdk.
Fast, private, local-first voice app for Apple Silicon Macs — dictation, file/media transcription, meeting recording, Transforms, and a public automation CLI. Free and open-source.
Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens
Conduit — native SwiftUI iOS client for Hermes Agent
A curated directory of open-source AI agent skills for Swift and Apple platform development.
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Desktop UI for the NInfer local LLM inference engine
A pleasant note-taking platform with native speed, majoring in Markdown, MindMap, Typst, and plain text.
Open-source multi-agent orchestration harness for OpenCode — specialized agents, durable workflows, research, planning, implementation, review, and validation.
Windows/macOS/Linux GUI client for GIT users
gzenz / ninfer
Forked from Neroued/ninferHigh-performance single-GPU inference for selected model checkpoints and GPUs.
cometkim / ninfer
Forked from Neroued/ninferHigh-performance single-GPU inference for selected model checkpoints and GPUs.
natpate / ninfer-windows
Forked from Neroued/ninferHigh-performance single-GPU inference for selected model checkpoints and GPUs.
LLM inference in C/C++
MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8 GB cards. Expert cache with LRU hot experts, OpenAI-compatible proxy, GGUF multi-shard.
Free MIDI Pattern Generator VST3 for Electronic Music Producers
Open Source (MIT License) VST Plugin. Load an impact sample and create a custom reversed swoosh into hit transition. This project serves as useful proof of concept for the technology stack intended…
An open-source Windows Digital Audio Workstation (DAW) for remixing, mashups, and sample-driven music making.
Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis