A lightweight C++ wrapper for OpenCL that reduces boilerplate code and the complexity of device selection, memory management, and kernel execution.

A collection of software tools for molecular dynamics simulations that integrates various interatomic potentials and tight-binding quantum mechanics, including machine-learning-based GAP potentials.

An AutoML framework that uses a declarative JSON-AI syntax to automatically generate and customize machine learning pipelines, reducing boilerplate code for data preparation and data science workflows.

A communication framework built on NCCL that allows users to execute custom, hyper-optimized collective communication algorithms for multiple accelerators to improve distributed AI performance.

A Go-based toolkit for automatically fixing malformed JSON output generated by LLMs, ensuring it becomes valid and parseable.

A PyTorch-based library for uncertainty quantification that provides scalable tools for Bayesian learning, including variational inference and Laplace approximation.

An enhancement suite and sidecar for grok2api that monitors proxy node quality and intercepts low-quality responses to prevent AI intelligence degradation.

A CLI tool that enables AI agents to build and publish Flutter iOS apps on remote Macs, eliminating the need for local Mac hardware or iOS ecosystem expertise.

A CLI tool that runs AI coding agents in a continuous loop to autonomously create, test, and merge pull requests for large-scale software projects.

A Cloudflare Worker that transforms Google's Gemini models into OpenAI-compatible endpoints, allowing Gemini to be used with any OpenAI SDK or client.

A Rust library for approximate nearest neighbor search that uses LMDB for low-memory, memory-mapped vector indexing and retrieval.

A framework for privately fine-tuning, evaluating, and running open-source LLMs using efficiency techniques like LoRA and INT4/INT8 quantization.

GigaTrain is a scalable training framework that streamlines the development of large AI models by automating distributed training, logging, and checkpointing.

A Python framework for Federated Learning that allows organizations to collaboratively train and validate ML models on sensitive data without sharing the raw data itself.

A storage-tier-aware LLM inference scheduler for Apple Silicon that enables running models larger than physical memory by streaming tensors from NVMe storage.

A framework- and backend-agnostic benchmarking platform used to compare ML inference runtime metrics and detect performance regressions across various hardware and software environments.

An R package providing fast C++ implementations of density-based clustering algorithms like DBSCAN and HDBSCAN for spatial data analysis and outlier detection.

A multi-agent system that automates end-to-end multimodal machine learning workflows, transforming raw data into ML solutions without human intervention.

A curated collection of open-source Chinese medical datasets for tasks like medical QA, entity recognition, and knowledge graph construction to support the development of medical AI.

A Julia interface for XGBoost, providing a scalable and efficient distributed gradient boosting framework for regression, classification, and ranking.

A benchmark for coding agents that evaluates their ability to build, debug, and repair interactive games by verifying actual runtime behavior across multiple game engines.

A framework for accelerating Neural Architecture Search (NAS) to generate efficient deep networks by optimizing for objectives like latency and memory.

A fast, AOT-compiling JavaScript sandbox for executing user-authored or AI-generated code with secure isolation and source map debugging.

An OpenCode plugin that automates the creation and Git worktrees, automatically spawning dedicated terminals for AI agents to work in isolation.

An R package that automatically converts fitted statistical models into LaTeX equations, reducing the manual effort of writing mathematical formulas for research papers.

A Python library for optimal binning of continuous variables using mathematical programming to improve feature engineering for predictive models and scorecards.

An R package for visualizing and analyzing causal directed acyclic graphs (DAGs) by integrating dagitty with the tidyverse and ggplot2.

LIGER is a package for integrating and analyzing multiple single-cell datasets using integrative non-negative matrix factorization to identify shared and dataset-specific factors.

A web-based image labeling tool for creating training data for object detectors, supporting formats like COCO and Pascal VOC.

A Python package that converts Scikit-Learn pipelines to PMML format to improve model portability and deployment across different environments.

A Python library providing a unified framework for 16 different graph kernels to measure similarity between graphs for use in machine learning.

A cloud-based headless browser infrastructure that provides remote browser sessions with integrated residential proxies and automated CAPTCHA solving for complex web scraping and automation.

A Slack app that connects to OpenAI’s ChatGPT (and DALL‑E 3), letting users chat, proofread, and generate images from channel threads, DMs, or the Home tab. It’s configurable via environment variables, deployable with Docker in Socket Mode, and includes optional Azure OpenAI support.

A Julia package for multivariate statistics and data analysis, providing tools for dimensionality reduction and regression.

Omnia is Dell’s open‑source Ansible‑based toolkit for automatically provisioning Linux servers, installing drivers, and deploying Slurm or Kubernetes together with AI/ML frameworks. It streamlines the creation of HPC or on‑prem AI clusters, is Apache 2.0 licensed, and is actively maintained by a community that includes Dell, Intel, universities and other partners.

A purely asynchronous, immediate-mode reactive TUI framework for Rust that brings web-like layout and styling ergonomics to terminal applications.

A Claude Code and Codex plugin that compiles scattered markdown files and codebases into a synthesized, topic-based wiki to reduce AI agent context costs.

A cross-platform desktop manager for CLIProxyAPI that centralizes AI account management, quota tracking, and configuration for AI coding agents.

A Bayesian model that integrates single-cell and spatial transcriptomics to map fine-grained cell types and their abundances across tissue architecture.

A dimensionality reduction method that uses triplet constraints to preserve the global structure of high-dimensional data, offering a better global view than t-SNE or UMAP.

A multi-agent system for automating scientific research, specializing in paper reproduction, custom data benchmarking, and budget-constrained hyperparameter and method optimization.

A Python-based search agent that allows developers to search the web using natural language and automatically scrape content from the results, including support for JavaScript rendering.

A Go language binding for TensorFlow Lite that enables the execution of pre-trained ML models in Go applications.

An agentic-first developer workspace for macOS that allows developers to run multiple projects and branches in parallel with isolated terminals, browsers, and AI agent sessions.

A Python library for semi-automated data science that automates algorithm selection and hyperparameter tuning for scikit-learn compatible pipelines.

A modular PyTorch framework for Deep Reinforcement Learning that allows users to configure and run RL experiments via JSON specs across various Gymnasium environments.

An AI-powered software engineering platform that uses multi-agent systems and knowledge graphs to automate bug fixing, feature implementation, and codebase navigation.

A Python library that abstracts infrastructure management, allowing AI/ML and scientific research code to run on any cloud or on-prem cluster with a single line of code.