Pyserini is a Python toolkit that wraps the Anserini Lucene search engine and FAISS to provide easy, reproducible first‑stage retrieval (sparse, dense, or hybrid) for information‑retrieval research and RAG pipelines. It includes pre‑built indexes, evaluation scripts, and a REST server, and can be installed via `pip`.

A collection of GPU-accelerated graph analytics packages that enable the creation and manipulation of graphs and the execution of scalable graph algorithms.

A model-agnostic Python library for quantifying uncertainty and controlling risks in machine learning models using conformal prediction.

A modular library of samplers for JAX that enables composable Bayesian inference on CPU, GPU, and TPU without requiring a full probabilistic programming language.

Kineto is a profiling library used in the PyTorch Profiler to provide performance observability and GPU timeline tracing for machine learning workloads.

A local-first microVM sandbox for AI agents that provides isolated, ephemeral Linux environments for secure code execution.

A collection of optimized model checkpoints and training recipes for scaling biological foundation models using TransformerEngine and FSDP.

A flexible Python library for implementing Reservoir Computing architectures like Echo State Networks for time-series prediction and classification.

A JAX-based library for nonlinear solvers that provides modular tools for root finding, minimisation, fixed points, and least squares.

A library of high-performance CUDA kernels for linear attention variants like KDA and Lightning Attention, optimized for NVIDIA Blackwell and Hopper GPUs.

An official Model Context Protocol (MCP) server and Agent Skills set that allows AI agents to operate 12 different freee business APIs, including accounting and HR.

A visual management and security auditing tool for Claude Code skills, providing a curated marketplace and a multi-layer scanning engine to prevent malicious code execution.

An MCP server that exposes read-only Apache Doris database capabilities to AI agents, providing a structured and secure way to query and monitor database data.

An experimental multimodal router that analyzes user prompts to recommend the optimal LLM or VLM based on trade-offs between accuracy, speed, and cost.

A compact, agent-native MoE training framework that provides production-grade performance and 4D parallelism in a codebase designed for easy readability by humans and AI agents.

An open-source tool for hardening GenAI applications by simulating dynamic LLM-based attacks to test and refine system prompt security.

A numerical computing library for Elixir that provides multi-dimensional arrays and high-performance backends like XLA and LibTorch for machine learning.

A web-based client for Claude Code that provides a modern interface for managing sessions, searching conversation history, and monitoring tasks in real-time.

A JIT-compiled framework for computational neuroscience and brain-inspired computation that enables efficient simulation, training, and analysis of brain dynamics models.

A production-ready API that instantly turns a PostgreSQL database into a REST and Model Context Protocol (MCP) API without requiring a custom backend.

An AI-powered code completion plugin for Neovim that supports multiple LLM providers and various completion frontends like virtual text and nvim-cmp.

A lightweight agent workstation and command center for Codex CLI, Claude Code, and ACP-compatible agents, featuring task scheduling and a unified project workspace.

An interface between Hugging Face libraries and OpenVINO that accelerates AI model inference and optimization on Intel architectures.

A zero-code HTTP interface testing and development tool that automates API documentation, code generation, and regression testing.

A comprehensive, annotated dataset and evaluation resource for training and evaluating protein-ligand docking algorithms to accelerate drug discovery.

An open-source identity and access layer for AI agents that provides standardized authentication, permissions, and observability across thousands of external system integrations.

Polyaxon is a platform for building, training, and monitoring large-scale deep learning applications, solving problems related to reproducibility, automation, and scalability.

An open-source, high-performance alternative to Yahoo Finance APIs that provides reliable market data, automated DCF valuations, and LLM-powered financial analysis.

A Python library for Difference-in-Differences causal inference providing a wide range of econometric estimators for measuring campaign lift, policy impact, and staggered rollouts.

A terminal-based tool to run open-source AI models locally or via hosted consoles, supporting text, vision, speech, and embeddings across multiple hardware backends.

An AI-powered disk cleanup assistant for Windows that uses an LLMs to analyze disk usage and identify removable junk files.

A toolkit for converting Excel data into Neo4j knowledge graphs, featuring both legacy educational examples and modern GraphRAG and vector-search implementations.

A CLI scaffolding tool that generates full-stack, domain-specific AI applications with integrated Neo4j knowledge graphs and agent frameworks.

A visual orchestration system for ML experiments and production pipelines that allows users to build and run containerized batch workflows via a drag-and-drop interface.

An agentic ML engineering system that uses Monte Carlo Graph Search and multi-agent collaboration to automatically solve Kaggle-style competitions and mathematical optimization tasks.

Rust bindings for Apple's MLX library, enabling high-performance machine learning and array operations optimized for Apple Silicon.

A stealthy browser automation tool based on Playwright that bypasses bot detection and solves CAPTCHAs using AI and computer vision.

A cross-platform desktop manager for AI accounts, subscriptions, and emails, providing one-click account switching and subscription tracking.

A flexible Bayesian dynamic linear model library for Python that enables time series decomposition and forecasting through additive components.

A specialized knowledge set for AI coding agents that provides expert guidance on Core Data persistence, performance optimization, and schema migration for Apple platforms.

A desktop gateway and configuration tool that allows the OpenAI Codex APP to use third-party AI models by translating its internal API requests into standard chat/completions protocols.

An analytics engine that analyzes billions of GitHub events to track trends, rankings, and developer activity in the AI-native open source ecosystem.

An MCP server that integrates DeepSeek's V4.1 Flash API into MCP-compatible clients, enabling text and visual chat and file management.

A modular AI plugin system for Claude Code and other AI CLIs that provides domain-specific agents, skills, and rules to improve the quality of AI-generated code across various frameworks.

A Python library for genetic programming that uses symbolic regression to discover mathematical expressions that describe relationships between variables.

A framework for generating knowledge-driven synthetic data using knowledge graphs to fill knowledge gaps in LLMs for improved supervised fine-tuning.

A distributed multi-agent reinforcement learning research library built in JAX that provides high-performance implementations of state-of-the-art MARL algorithms.

An MCP server that enables AI IDEs to safely execute SQL, manage schemas, and handle authentication for Supabase projects.