A PyTorch implementation of Rectified Flow and its variants, enabling more efficient generative modeling by straightening the paths between noise and data.

A collection of Triton kernels for efficient low-bit matrix multiplication that accelerates LLM prefill and decoding performance.

A comprehensive collection of 470+ interactive notebooks demonstrating end-to-end MLOps, generative AI, and agent development workflows on Google Cloud Platform.

A Kubernetes operator for self-hosting OpenClaw AI agents, providing production-grade security, observability, and automated lifecycle management through a declarative API.

A Neo4j plugin that enables the lossless import, export, and validation of RDF data, bridging the system between W3C semantic web standards and property graphs.

A runtime software interface that provides an abstracted layer for managing and interacting with AMD NPUs and FPGAs across different hardware platforms.

A scalable Python library for computing matrix profiles to identify repeated patterns and anomalies in time series data.

A Rust crate providing n-dimensional containers for general and numeric elements, enabling efficient multi-dimensional array manipulation and linear algebra.

An AI-driven tool that automatically generates system-level test cases for REST, GraphQL, and RPC APIs to detect faults and create regression test suites.

A command-line interface for running and managing QA Wolf testing flows locally or in CI, featuring AI agent integration and a TypeScript Runner SDK.

A Python toolkit for affine-invariant MCMC ensemble sampling, used for Bayesian parameter estimation in scientific research.

A GPU-accelerated terminal board that puts shells, AI agents, and browsers on an infinite 2D canvas for spatial workspace organization.

A production-grade GPU monitoring and management tool that ensures hardware efficiency and reliability for AI/ML workloads.

A Rust-native GPU memory allocator that provides a unified interface for managing memory across Vulkan, DirectX 12, and Metal.

The official Python SDK for Vulners, providing programmatic access to a vulnerability intelligence graph to prioritize security fixes and audit software assets.

A unified PHP API for document parsing that provides a single interface to multiple interchangeable drivers like LiteParse and AnyDoc for converting files to Markdown and structured data.

A modular Julia library providing efficient implementations of advanced Hamiltonian Monte Carlo (HMC) algorithms, including NUTS, for probabilistic inference.

An interactive visualization tool for Kedro data science pipelines that transforms complex pipeline code into searchable, interactive diagrams.

A Julia library that provides fast tensor operations using a convenient Einstein index notation for concise and efficient tensor contractions.

An enterprise deployment framework for Claude Code and Claude Cowork on Amazon Bedrock, providing secure SSO, per-user usage monitoring, and token quota enforcement.

A high-performance DataFrame library that serves as a drop-in replacement for Pandas, using MPI and JIT compilation to accelerate large-scale data processing for AI/ML.

A JAX-based library for probabilistic state space models that provides tools for inference and learning across various model types like HMMs and Gaussian SSMs.

A web framework built on FastAPI and HTMX, specifically designed with a fully typed API to be easily written and understood by AI coding assistants.

A library for probabilistic hierarchical forecasting that ensures consistency across different levels of data aggregation using statistical and econometric reconciliation methods.

A Kubernetes operator that simplifies the deployment and management of allreduce-style distributed AI training jobs across multiple nodes.

A Docker and Podman wrapper for ComfyUI that provides pre-configured NVIDIA CUDA environments to simplify installation and GPU hardware compatibility.

A system that orchestrates multiple AI coding CLI instances in parallel using a feudal hierarchy and YAML-based communication to eliminate API coordination costs.

An extension for Gemini CLI that uses AI to analyze code changes for security vulnerabilities and scans dependencies for known risks.

A standardized protocol for AI systems to discover and call tools across various communication protocols like HTTP, WebSocket, and CLI.

A Python library for augmenting text, audio, and spectrogram data to generate synthetic training sets for machine learning models.

An end-to-end platform for applied reinforcement learning designed for large-scale distributed tasks and offline training without a simulator.

A Python library that makes machine learning models interpretable for everyone by providing user-friendly visualizations, an interactive web app, and audit reports.

A library of scikit-learn-style transformers for encoding categorical variables into numeric values using a wide variety of supervised and unsupervised techniques.

An open-source machine learning database that provides a feature platform to ensure consistent, low-latency features for both ML training and online inference.

A local governance layer for AI coding agents that provides durable, structured project memory and enforces rigorous engineering reasoning via the First Principles Framework.

A lightweight, offline RESTful API for managing vector-based knowledge bases, enabling AI agents to handle local long-term and short-term memory without cloud services.

A C++17 library for simplifying CUDA kernel benchmarking, offering parameter sweeps and detailed throughput and bandwidth measurements.

A local sandbox for AI agents that provides VM-level isolation for executing code and using tools safely on a Mac.

An inference engine and compiler framework that converts ONNX models into deterministic static libraries for resource-constrained microcontrollers.

A framework for creating agentic AI workflows where Docker containers serve as tools and Markdown files define the logic, allowing LLMs to execute complex tasks in sandboxed environments.

A local MCP server that enables AI agents to safely control any desktop GUI across Windows, macOS, and Linux using a tiered perception system that prioritizes accessibility data over vision.

modelrelay is a free, OpenAI‑compatible local router that benchmarks and auto‑selects the fastest, highest‑quality free LLMs from many providers. Install via npm or Docker, then point your existing OpenAI‑based tools at `http://localhost:7352/v1` and let the router handle model choice, tagging, and QoS scoring.

A compiler and registry that transforms verbose API specifications into compressed, agent-native formats to reduce LLM hallucinations and token costs.

R-KV is a redundancy-aware KV-cache compression method for reasoning models that reduces memory usage by up to 90% and boosts throughput without losing accuracy.

A spec-driven, agentic workflow framework for AI coding agents that persists requirements, plans, and verification evidence directly in the project repository.

A PyTorch framework for deep learning R&D that removes training loop boilerplate to accelerate experimentation and reproducibility.

A lightweight CLI tool that reduces AI token costs by filtering CLI output and compressing file content before it reaches an AI agent.

A REST API-based management platform for LLM assets, providing tools for organization, storage, and distribution of models and datasets.