Lists (7)
Starred repositories
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.
FlashKDA: high-performance Kimi Delta Attention kernels
CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Fast and memory-efficient exact attention
🚀 Efficient implementations for emerging model architectures
Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your pho…
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Youtu-Tip: Tap for Intelligence, Keep on Device.
On-device AI across mobile, embedded and edge for PyTorch
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
MoBA: Mixture of Block Attention for Long-Context LLMs
AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling
⚙️ Create and run workflows (RPA 2.0)
Examples of CUDA implementations by Cutlass CuTe
An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.
MCP Server for Computer Use in Windows
🐉 Revolutionary NPU framework for Linux | 24,988 FPS face recognition | AMD XDNA support | World's first complete NPU stack
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
An open-source coding helper. Very friendly!
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models