A comprehensive R package for training and plotting classification and regression models, providing a unified interface for machine learning tasks.

A desktop application that uses ChatGPT to translate subtitle files while maintaining context between sentences.

A performant, portable execution engine and serialization format for deploying machine learning pipelines from Spark and Scikit-learn without their heavy dependencies.

A Backend-as-a-Service infrastructure that provides AI-native backend capabilities, allowing developers to build full-stack AI applications without writing backend code.

A library for performing large-scale kernel operations on GPUs using symbolic matrices to avoid memory overflows and achieve linear memory footprints.

A high-performance Python framework for network flow analysis that extracts statistical features and application metadata from live or offline traffic for machine learning.

A compositional framework for gradient-based Bi-Level Optimization that allows users to automatically compose over 85 solver variants from 19 atomic gradient operations.

A Java-based package for statistical natural language processing, providing tools for topic modeling, document classification, and sequence tagging.

An LLM assistant for Emacs that provides chat, agentic coding workflows, and deep context integration across buffers and files.

A backbone C++ library that provides the essential building blocks for creating efficient and scalable distributed machine learning systems.

A lightweight, high-performance in-memory KV store optimized for deterministic LLM caching and fast local AI inference experimentation.

An R package for the quantitative analysis of textual data, providing high-performance tools for natural language processing and text management.

A collection of optimized blueprints for deploying and scaling data platforms—including Spark, Flink, and Kafka—on Amazon EKS.

A lightweight Python library for audio activity detection that splits audio streams into events using energy thresholding or WebRTC VAD.

A ROS framework for live sensor fusion on robots using nonlinear least squares optimization to handle state estimation, localization, and calibration.

A sample Amazon Lex web interface that provides a responsive chatbot UI component for integration into websites via text or voice.

Arena is a CLI tool that allows data scientists to run and monitor machine learning training jobs on GPU clusters without needing deep Kubernetes knowledge.

EasyEdit is a prompt-based image editing tool powered by Flux 2 and Together AI that allows users to modify images with a single text prompt.

An online machine learning platform for sharing and organizing data, algorithms, and experiments to foster open science and collaborative research.

A machine learning package for processing and classifying multivariate data using the Riemannian geometry of symmetric positive definite matrices, primarily for biosignals and remote sensing.

A Python library for simulating Active Inference agents in Markov Decision Process environments, enabling agents to balance curiosity-driven exploration and reward maximization.

A Ruby library and CLI tool for text classification and term scoring using five different algorithms, including Bayesian and LSI, with native performance extensions.

A Kubernetes DRA driver for NVIDIA GPUs that enables flexible device allocation and secure multi-node NVLink connectivity for AI workloads.

A differentiable tokamak core transport simulator built in JAX for fast forward modelling, trajectory optimization, and controller design in fusion research.

Litex is a set-theory-based formal language designed for readable, machine-checked mathematics that allows users to write facts in a natural order and optionally compiles to Lean.

A Rust procedural macro that uses ChatGPT to generate and fill in code implementations and tests at compile-time.

A Rust-based text splitting library that breaks long documents into semantically sensible chunks for LLM context windows, supporting plain text, Markdown, and source code.

A Python library for creating and managing Semantic Hypergraphs to represent natural language sentences as ordered, recursive hyperlinks.

An intelligent hearable system that allows users to isolate and hear a target speaker in noisy environments by looking at them for a few seconds.

Atlas is a decentralized coordination layer that allows AI agents across different blockchain ecosystems to discover each other, negotiate tasks, and settle payments.

A collection of advanced PyTorch optimization algorithms, including Distributed Shampoo and GPA-AdamW, designed for efficient large-scale model training.

A 3D body and skeletal tracking library that provides a unified API for various depth sensors across multiple platforms, enabling human-centric spatial understanding.

A Java library and command-line tool that converts Scikit-Learn machine learning pipelines into the PMML standard for portable model deployment.

OpenClaw A2A Gateway – a Node.js plugin that implements Google’s Agent‑to‑Agent v0.3.0 protocol for OpenClaw agents. Provides zero‑config installation, automatic peer discovery (DNS‑SD/mDNS), multi‑transport fallback (JSON‑RPC, REST, gRPC), bio‑inspired routing, circuit‑breaker resilience, bearer‑token auth, and file‑transfer tooling.

A .NET wrapper for NVIDIA's CUDA Driver API and libraries, enabling C# and Visual Basic developers to integrate GPU acceleration into their applications.

An end-to-end, distributed Structure-from-Motion pipeline based on GTSAM and Dask that reconstructs 3D scenes from 2D images with native parallel computation support.

A minimal, performant library for writing GPU-like kernels that can target multiple execution backends, including NVIDIA, AMD, Intel, and Apple GPUs.

Matecat is an enterprise-level, web-based Computer-Assisted Translation tool that simplifies post-editing and outsourcing workflows using machine translation and translation memories.

An open-source User and Entity Behavior Analytics (UEBA) framework for security analytics that provides transparent, white-box security models and a visual rule builder.

A ROS interface stack that bridges the Point Cloud Library (PCL) with ROS for 3D geometry processing and n-D point cloud handling.

A PDDL-based planning system for ROS2 that allows robotics developers to generate intelligent behaviors for robots through high-level task planning.

A Python package that simplifies using Amazon Textract to extract text, tables, forms, and identity data from documents.

An educational Python library for manipulator motion planning that uses Pinocchio for robot kinematics and dynamics.

A global optimization package for Julia that uses stochastic and meta-heuristic algorithms to optimize non-differentiable functions.

A recommender system for GitHub repositories that suggests new projects to users based on their starred repositories.

Fusion‑Fable is a Claude Code skill that runs a prompt in parallel on multiple LLMs (Opus 4.8, GPT‑5.5, Gemini 3.1 Pro), lets Opus 4.8 judge the independent answers, and synthesises a final, structured response. It installs as a Claude skill with slash commands, saves provenance files, and includes an iterative planning mode (`/fusion‑plan`) that integrates with the OMC planning system. Zero‑setup panel (two Opus 4.8 runs) works out‑of‑the‑box; richer panels need the `codex` and `agy` CLIs. The trade‑off is higher token cost and latency, but the result is a higher‑quality, auditable answer.

A scalable sandbox environment management framework designed for agentic reinforcement learning, providing tools for building, deploying, and scheduling isolated runtimes.

Open ChatGPT Atlas is an open‑source Chrome/Edge extension (and optional Electron app) that lets an AI control the browser (via Gemini 2.5 Computer‑Use) and call over 500 third‑party services (via Composio). Install with Node, load the built `dist` folder, add your Google and optional Composio API keys, then use the sidebar chat to give natural‑language commands like “click this button” or “create a GitHub issue.” It offers visual feedback, safety confirmations, and runs entirely client‑side.