A Python library for building scalable synthetic data pipelines, providing bulk inference and structured output tools to curate high-quality datasets for post-training.

A cross-platform CLI tool that measures the tokens-per-second throughput of local LLMs running via Ollama based on the user's available system RAM.

An open-source, self-hosted AI model registry that serves as a private Hugging Face replacement to accelerate model distribution and secure weights for enterprise inference.

An autonomous AI agent orchestrator that manages code workers to solve issues from Linear or local trackers, featuring a Worker/Reviewer pipeline with sandboxed verification.

A multimodal data extraction package that scrapes clean markdown and structured data from complex documents using vision-language models for RAG and LLM applications.

A high-performance linear algebra library optimized for small, cache-resident matrices typically used in embedded optimization applications.

An enterprise-grade AI UI component library based on Vue 3 and Element-Plus that provides ready-to-use components for chat robots, voice interaction, and streaming interfaces.

A Python library for extracting public Spotify metadata without an API key, featuring an MCP server for AI agents and support for lyrics and transcripts.

An open-source vLLM plugin that optimizes LLM and embedding inference to increase throughput and reduce latency using advanced parallelism and speculative decoding.

AdaRubric is a framework that generates task-specific evaluation rubrics and dense reward signals to reliably evaluate and filter LLM agent trajectories for reward learning.

A local-first document management and semantic search server for AI agents that provides a private knowledge base with a built-in web UI and hybrid search.

A differentiable dynamical core for global atmospheric modeling written in JAX, designed to integrate physical equations with AI for weather and climate forecasting.

A system tray and menu bar application that provides real-time quota and token usage visibility for Claude Code, Codex, Antigravity, and Grok CLI.

A production-ready LLM inference platform for Kubernetes that simplifies deployment, scaling, and management across various inference backends.

An open-source reporting and ETL framework for creating professional reports and automating data tasks from any database or NoSQL source.

A high-performance Web Application Firewall that uses machine learning and semantic engines to provide three-layer defense against web attacks and 0-day vulnerabilities.

A high-performance cross-platform computing framework that allows developers to write computation kernels in C++ and deploy them across CUDA, DirectX, Metal, and CPU backends.

eCAL is a high-performance, brokerless middleware for interprocess communication that provides publish-subscribe and server-client patterns with zero configuration.

Salmon is a high-performance tool for transcript-level quantification from RNA-seq data, using selective alignment and statistical models to estimate transcript abundances.

A Matlab software package for highly comparative time-series analysis that extracts thousands of features from univariate time series for classification and phenotyping.

A Python implementation of the WebGPU API that provides a powerful and reliable interface for GPU graphics and compute applications.

A Python client library that wraps all Databricks REST APIs, handling authentication (PAT, Azure, GCP, OIDC), retries, pagination, and long‑running operations, enabling programmatic control of clusters, jobs, Unity Catalog, and other Lakehouse resources.

An open-source R package for latent variable analysis, supporting structural equation modeling, path analysis, and factor analysis.

A GPU-accelerated GTO poker solver that uses a DCFR engine to calculate equilibrium strategies with advanced analysis tools for blockers and runouts.

C++ bindings for the OpenCL API, providing a more native C++ interface for parallel computing on GPUs and other accelerators.

A Python toolkit for the structural modeling of economic choices of optimizing and non-optimizing heterogeneous agents, simplifying the creation of complex macroeconomic and microeconomic simulations.

A distributed task queue for testing chess engines that allows developers to crowdsource CPU power to verify the strength of engine patches.

A no-code tool that automatically creates secure REST and GraphQL endpoints for various databases, eliminating the need to write manual CRUD API code.

An AI-integrated shell for Hyprland that features an autonomous system monitoring daemon and an interactive AI-powered information capsule.

A secure JavaScript runtime designed for edge computing and AI workloads that uses WebAssembly for sandboxing to ensure safe execution.

A Python library for Microsoft Fabric notebooks that automates the management, migration, and optimization of Power BI semantic models, reports, and lakehouses.

A CUDA-based utility that occupies GPU memory and compute resources to simulate active usage and prevent resource reclamation in shared clusters.

A CLI tool for managing GPU pods and serverless endpoints on RunPod, providing automated resource lifecycle management, log streaming, and endpoint invocation.

MOFA2 is a factor analysis model that provides a general framework for the unsupervised integration of multi-omic data sets.

A Python platform for research in Integrated Information Theory (IIT) that computes integrated information (Φ) and the cause-effect structure of interacting systems.

A local, private recommendation system that learns user preferences from explicit ratings to provide personalized search and discovery across local and remote media files.

A visualization toolkit for materials informatics that provides specialized plots and interactive widgets for chemical compositions, crystal structures, and vibrational properties.

A Python library for high-performance graph visualization and analytics that leverages GPU acceleration and columnar data to handle millions of edges.

A Visual Studio Code extension that integrates Jupyter Notebook support, allowing users to run interactive notebooks using various language kernels within the IDE.

Rust bindings for the NumPy C-API that allow developers to integrate high-performance Rust numerical computing with Python's NumPy arrays.

A command-line tool and Python package for efficient, single-line querying of genomic reference databases and sequence analysis.

A low-code/no-code platform that integrates AI assistants and multi-tenant LLM management to help users quickly build enterprise business systems and dashboards.

A low-level GPU programming framework based on Vulkan and SPIR-V that provides a curated feature profile and a shared HLSL/C++ library for cross-platform graphics development.

A ComfyUI extension that replaces standard node connections with organized, circuit-board-style orthogonal lines to reduce visual clutter in complex workflows.

A web-based debugging and validation tool for developers to inspect, test, and verify servers implementing the A2A (Agent2Agent) protocol.

A PromQL-based framework for detecting anomalies in time series data using recording and alerting rules within Prometheus, requiring no external systems.

An admin panel for the RuoYi-AI platform that enables system management, AI model configuration, and knowledge-base orchestration.

Warren is a stock price predictor that uses Facebook's Prophet algorithm to forecast the future value of US-based company stocks in real time.