Starred repositories
Sparse Decoupled Attention for Efficient Long-Context LLM Inference
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
The open-source CapCut alternative
Mellea is a library for writing generative programs.
Lightweight MCP server for computer use in MacOS
Refine and translate selected text in any macOS app. Services menu, global hotkeys, and a floating action bar over your selection — powered by your favorite LLM provider.
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude mod…
Batch-generate bilingual external subtitles for local media files using MLX Whisper on Apple Silicon
iOS terminal app with SSH support, powered by the Ghostty engine (libghostty), with a custom on-screen keyboard.
A suite of plugins for legal workflows
Codex++ tweak system for the Codex desktop app
Headless control for Apple's Simulators — 3D models, taps, swipes, multi-finger gestures, 60 fps streaming, and a multi-device farm
Orchestrate multiple coding agents from desktop and mobile
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Open source UI framework written in Python, running on Windows, Linux, macOS, Android and iOS
High-quality long audio transcription using Google's Gemini API with intelligent chunking
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
This project explores transformer improvements through Super-Transformers (scalable softmax, positional encoding ablation) and MiniDeepSeek (multi-latent attention, KV cache, weight absorption) to …
Unofficial Scalable-Softmax Is Superior for Attention
Official code implementation of Context Cascade Compression: Exploring the Upper Limits of Text Compression
Unofficial Implementation of Selective Attention Transformer
Implementation of paper Data Engineering for Scaling Language Models to 128K Context
Implementation of "Efficient Training of Language Models to Fill in the Middle"
A Reproduction of GDM's Nested Learning Paper
Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determining generation length and maintaining KV-cache compatibility, achieving high eff…
Curated list of open source alternatives to proprietary software.
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning