A lightweight WebAssembly runtime that is fast, secure, and standards-compliant

NumPy & SciPy for GPU

[CVPR 2026 Oral] "INSID3: Training-Free In-Context Segmentation with DINOv3"

Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thre…

Linux device manager for Logitech devices

Change Risk Anti-Patterns (CRAP) metric for Rust projects

A conda-smithy repository for sahi.

Fast Markdown linter and formatter written in Rust

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

Qt Bridge for Rust. Qt Bridges enables developers to provide application logic written in a foreign language to Qt Quick applications by offering a simple API that follows the target language’s sty…

Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**

Interactive TUI scratchpad for building shell pipelines

Cross platfrom window and framebuffer crate for Rust

A std::time::Instant replacement that works on WASM too.

Universal Rust multiplexer with a typed SDK — drive any CLI or TUI app from code. Native on Linux, macOS, and Windows.

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

The agent that grows with you

Fast Robot Kinematics and Dynamics in JAX

NVIDIA Federated Learning Application Runtime Environment

Create beautiful, publication-quality books and documents from computational content.

Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 1,000+ medical models, 12 languages, Apple MLX + Python, no cloud, no patient data leaving your netwo…

A CLI-first interface for AI agents to work with notebooks

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Your Personal AI super intelligence. Private, Simple and extremely powerful.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

A GPU-rendered terminal emulator with inline 3D graphics 🐀🧀

An interface library for RL post training with environments.