A multi-agent framework that stress-tests conversational AI agents by simulating thousands of realistic edge-case interactions to uncover failure points and optimize performance.

A Python package providing production-ready templates and infrastructure automation for GenAI agents on Google Cloud, simplifying the path from prototype to production.

An open-source document intelligence API that converts PDFs, PPTs, Word docs, and images into structured, RAG-ready chunks using layout analysis and OCR.

An automated machine learning toolkit that serves as a drop-in replacement for scikit-learn estimators to automate model selection and hyperparameter tuning.

A high-performance C++ automatic differentiation library providing forward and reverse mode AD with low runtime overhead for performance-critical systems.

A cross-harness configuration organizer for AI coding tools that provides a unified dashboard to manage memories, skills, and MCP servers while optimizing token usage and detecting tool poisoning.

Duck‑UI is an open‑source, browser‑based workbench for DuckDB that lets you write SQL, run notebooks, visualise results, import many file formats, and optionally use an AI assistant for text‑to‑SQL, all without any backend server.

A reference implementation of the agentic registration protocol, enabling AI agents to authenticate with services on behalf of users via identity assertions and claim ceremonies.

An intelligent climate control integration for Home Assistant that uses a self-learning thermal model and MPC to optimize heating and cooling efficiency.

A professional open-source ECU calibration hex editor for automotive engineers that features AI-powered map identification and 3D data visualization.

A CLI tool that uses AI to analyze staged git changes and automatically generate descriptive commit messages in various formats.

The official OpenAI Go library that provides type-safe access to the OpenAI REST API for applications written in Go.

An open-source launcher for AI coding assistants that builds a local semantic graph of a codebase to pre-load relevant context into prompts, reducing token costs and response times.

A library for automatically computing provable output bounds for neural networks to verify formal robustness against input and weight perturbations.

An AI-native E2E testing tool that connects AI agents to apps via MCP, allowing them to test and explore software across 10 platforms using natural language instead of test code.

A decentralized P2P AI inference network that allows users to contribute GPU, CPU, and storage resources to run AI models and earn rewards.

A collection of experimental extensions for TabPFN that add support for image columns, interpretability tools, Bayesian optimization, and unsupervised learning to tabular data models.

Statewave is an open‑source, self‑hosted memory runtime for LLM agents. It records raw events (episodes), compiles them into typed memories (via heuristic or LLM compilers), and serves deterministic, token‑bounded context bundles with full provenance. Built on PostgreSQL + pgvector, it offers policy‑driven labeling, multi‑tenant isolation, and SDKs for Python and TypeScript.

An MCP server that exposes GraphQL operations as tools, enabling AI models to access and orchestrate APIs running with Apollo.

Helixer is a structural genome annotation tool that uses deep learning and Hidden Markov Models to perform ab initio gene calling across various species lineages.

A Docker-based deployment suite that enables Intel Arc GPU acceleration for Ollama, Stable Diffusion, and OpenAI Whisper via a unified interface.

A browser automation platform that turns websites into structured data using a visual recorder, a CLI for AI agents, and native support for MCP and Skills protocols.

An AI-native library and MCP for end-to-end testing that allows users to perform actions and verify assertions in applications using natural language via Appium, Playwright, or Selenium.

A declarative logic programming language and runtime for building world models in Neuro-Symbolic AI, designed to reduce LLM hallucinations through structured reasoning.

An auditable agent-team workflow for coding agents that turns a single AI into a structured engineering team with event-sourced runtime and quality gates.

A collection of LangChain and LangGraph components that integrate AWS services like Bedrock, SageMaker, and DynamoDB for building AI agents and RAG applications.

A fast, header-only C++ machine learning library that provides a wide array of ML methods and functions with bindings for Python, Julia, Go, and R.

A configurable end-to-end pipeline for cleaning, aligning, and integrating multimodal MIMIC-IV medical data (structured, text, waveforms, and images) for downstream ML tasks.

A real-time streaming markdown renderer for terminals that beautifies LLM output without taking over the full screen, maintaining full keyboard interactivity.

A minimal, typed JavaScript bridge that gives AI agents direct access to every Chrome DevTools Protocol method without restrictive helper functions.

A Clojure library for high-performance tabular data processing on the JVM, providing a functional alternative to Pandas or R's data.table.

A tool that converts an entire website into a single PDF, optimized for use as a knowledge source for RAG and AI-based question answering.

A web interface and management layer that brings tmux-based AI agent CLI sessions to any browser on desktop or mobile.

A web-based toolkit for Android and iOS penetration testing that simplifies Frida script execution and uses AI to generate custom instrumentation scripts.

A Python package for machine learning and optimization specializing in time series and differential algebraic equations, providing an interface to the large-scale solvers of the APMonitor suite.

A self-hosted web API that provides free, unlimited access to various LLM providers through a single HTTP interface, eliminating the need for paid API keys.

A modular PyTorch framework providing reusable, high-performance building blocks for assembling state-of-the-art AI models, including attention mechanisms, quantization, and multi-modal architectures.

A platform providing persistent and secure sandboxes for AI agents powered by Firecracker microVMs to enable safe code execution.

A JavaScript/TypeScript SDK for the Qdrant vector search engine, providing REST and gRPC clients to manage and search vector data.

A QA dataset and benchmarking tool designed to evaluate the ability of RAG pipelines to retrieve and reason across multiple documents and metadata.

A CLI tool for Triton Inference Server that automates the search for optimal model configurations to balance performance and resource usage on specific hardware.

A high-level library for PyTorch that simplifies neural network training and evaluation through a flexible engine and event-driven system.

A decentralized operating system platform for building decentralized applications and powering an AI-driven, collaborative IDE called Composer.

A codebase knowledge graph tool that indexes structural dependencies and exposes them via a visual dashboard and MCP tools for AI agents.

Skore is a Python library that structures machine learning experiments by reducing evaluation boilerplate and providing built-in methodological guidance for data scientists.

A benchmark framework for evaluating and comparing data-driven and traditional numerical global weather forecasting models using scalable evaluation code and cloud-optimized datasets.

A local AI CLI unified gateway that provides a single entry point for tools like Claude Code and Gemini CLI, featuring intelligent failover, usage tracking, and workspace isolation.

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