An LLM post-training framework with vLLM for RL Scaling

Connect remotely to your Home Assistant instance without opening any ports using Cloudflared.

Homeassistant custom integration that integrates with CVnet smarthome.

Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.

페이퍼로지

A curated directory of open-source AI agent skills for Swift and Apple platform development.

A self-hosted HuggingFace alternative

MLX-based experimental inference engine

Aurora optimizer release

DFlash: Block Diffusion for Flash Speculative Decoding

Remote Control for Codex.

eLLM can infer LLM on CPUs faster than on GPUs

A terminal workspace with batteries included

Warp is an agentic development environment, born out of the terminal.

AI가 쓴 글이 아닌 것처럼 윤문해주는 스킬

Your First LLM-Wiki Conversation Knowledge Base

A lightweight, powerful framework for multi-agent workflows

아래한글 hwp viewer and editor by rust and wasm

Best harness + editor + linter for generating slides in Claude Code / Codex - Claude Design Open Source Alternative

IBM Plex Mono에 IBM Plex Sans KR을 더하여 코딩창과 터미널에서 로마자에 어울리는 한글을 보여주는 글꼴입니다.

DMax: Aggressive Parallel Decoding for dLLMs

Use Codex from Claude Code to review code or delegate tasks.

Official repository of DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

A compositor-based terminal UI framework. Fast. Layered. Unstoppable.

An MCP server for interacting with Google Colab

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar