Stars
A modular framework for building massively parallel agentic systems
we-promise / sure
Forked from maybe-finance/maybeThe personal finance app for everyone. NOT affiliated with or endorsed by Maybe Finance Inc.
📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
AI video agents framework for next-gen video interactions and workflows.
Zero-Trust access management with true WireGuard® 2FA/MFA
Reverse Engineering: Decompiling Binary Code with Large Language Models
Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
A working machine learning framework in pure Mojo 🔥
This is our own implementation of 'Layer Selective Rank Reduction'
🥧 Savoury implementation of the QUIC transport protocol and HTTP/3
Incredibly fast Whisper-large-v3
A language for constraint-guided and efficient LLM programming.
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
Build & ship backends without writing any infrastructure files.
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
Code for Fast Training of Diffusion Models with Masked Transformers