Tools to support converting a Python project into a standalone native application.

High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.

A lightweight inference engine supporting speculative speculative decoding (SSD).

Fast, small, and fully autonomous AI assistant infrastructure — deploy anywhere, swap anything 🦀

⚡A CLI tool for code structural search, lint and rewriting. Written in Rust

Claude Code hook & Telegram Bot to notify user about active CC permission request and receive the decision via Telegram bot.

Mobile, Web & Desktop client for Codex, Claude Code, OpenCode, Kimi, Augment Code, Qwen, fully end-to-end encrypted

Official Implementation of wd1

GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.

Flexible and Pluggable Serving Engine for Diffusion LLMs

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

App for Claude Code / Codex / Gemini / OpenCode, vibe coding anytime, anywhere

omo; the best agent harness - previously oh-my-opencode

A IPP server. Written in python, it implements enough of IPP to fool CUPS into thinking its a real printer.

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Stable-DiffCoder is a family of lightweight open-source code DLLMs(diffusion large language models) comprising base and instruct models, developed by ByteDance Seed.

Virtual whiteboard for sketching hand-drawn like diagrams

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

[ICLR 2026] SparseD: Sparse Attention for Diffusion Language Models

Container runtimes on macOS (and Linux) with minimal setup

Easy and Efficient dLLM Fine-Tuning

AgentBar is a macOS menu bar app that tracks AI coding assistant usage in one place.

My version of an LLM Websearch Agent using a local SearXNG server because SearXNG is great.

Experimental validation of the Bayesian BM25 paper

Show usage stats for OpenAI Codex and Claude Code, without having to login.

🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.

Know your zone. Ship with confidence.

slime is an LLM post-training framework for RL Scaling.