Astrid is an operating-system project for WASM-based capsules that provides an OS-grade security boundary for AI agents, separating decision-making from execution authority.

An intelligent automation platform that automates the discovery, downloading, and organization of self-hosted music and video libraries.

A collection of CUDA kernel implementations and educational resources for PyTorch users to learn GPU programming and hardware optimization.

A unified Python CLI and SSH workflow skill designed for AI agents to securely execute commands and manage files across remote servers on Windows, macOS, and Linux.

An enterprise-grade AI data preprocessing platform that converts unstructured documents, images, audio, and video into structured Markdown or JSON for AI applications.

An MCP server that enables AI models to generate over 26 types of professional charts and diagrams using the AntV visualization library.

A high-performance Rust-based decoding tool that automatically identifies and decrypts encoded text using A* search and optional BERT-powered plaintext detection.

A set of skills, agents, and diagnostic tools that give AI coding assistants deep expertise in Apple OS development to prevent bugs and accelerate debugging.

A fast, lightweight, and unsupervised text tokenizer and detokenizer that implements subword units for neural network-based text generation systems.

An open-source framework that provides both inherently interpretable glassbox models and tools to explain complex blackbox machine learning systems.

An interactive visualization tool for large-scale embeddings and multimodal metadata, featuring WebGPU-powered rendering and AI agent access via MCP.

A TypeScript runtime and CLI tool that allows developers and integrate Model Context Protocol (MCP) tools into scripts, terminals, and standalone CLIs.

A quota and token tracking tool for OpenCode that provides real-time visibility into AI model usage and usage limits across multiple providers.

An AI-native APM backend built on OpenTelemetry that uses multi-agent AI to automate root-cause analysis and troubleshooting via natural language queries.

A collection of AI agent plugins and skills that enable GitHub Copilot, Claude Code, and other agents to build, test, and package native WinUI 3 Windows applications.

An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.

A production-grade high-performance inference engine that supports diverse hardware backends and scalable deployment for large language models.

Memgraph is an in‑memory graph database (C/C++) that combines sub‑millisecond graph traversals with built‑in vector, text, and geospatial indexes. It ships a 40+ algorithm library (MAGE), an “Atomic GraphRAG” query model, and an AI Toolkit for LLM‑aware workflows, while offering enterprise features like Raft HA, multi‑tenancy, and fine‑grained security.

A production-ready project generator that scaffolds full-stack AI agent applications using FastAPI and Next.js, featuring built-in RAG, authentication, and enterprise integrations.

An open-source AI work system that integrates local desktop workbenches with cloud agents and remote machines for collaborative AI-assisted coding.

A low-latency, open-source time-series database that ingests millions of events per second and provides high-performance SQL queries over live and historical data.

An extensible quantitative finance framework that integrates data collection, factor mining, machine learning, and backtesting for quantitative investment research.

An antivirus software written in Python and C++ that uses machine learning and a kernel-mode minifilter driver to block security threats.

A Rust-based terminal SSH manager that syncs ~/.ssh/config with 18 cloud providers and manages remote Docker/Podman containers fleet-wide.

A macOS utility that monitors Claude AI usage limits in real time via the menu bar, desktop widgets, and a floating overlay for Claude Code sessions.

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

XLA is an open-source machine learning compiler that optimizes models from PyTorch, TensorFlow, and JAX for high-performance execution on GPUs, CPUs, and ML accelerators.

A deterministic orchestration framework that enforces strict, code-defined workflows for AI agents to prevent hallucinations and ensure reliability.

An extension of vLLM that enables hybrid GPU and NUMA-aware CPU inference for MoE models, allowing them to span across VRAM and system memory.

A portable, single-file memory layer for AI agents that provides persistent long-term memory and instant retrieval without requiring a database.

An AI-first security scanner with 40,000+ detection patterns to identify vulnerabilities in AI/ML apps, agents, and leaked secrets in AI chat histories.

An MCP server that connects AI assistants to the Godot editor, providing 175 tools to automate scene management, scripting, and game testing.

An AI-enhanced terminal development environment that integrates coding agents directly into the shell via a TUI, CLI, or ZSH plugin.

A quantitative factor mining center that uses deep reinforcement learning to automatically search for interpretable trading factor formulas and provides tools for training, backtesting, and real-time signal analysis.

A Python and TypeScript library for creating evaluations for LLM applications, featuring LLM-as-judge capabilities and prebuilt prompts for quality, safety, and RAG.

Ventus is an open-source GPGPU processor based on the RISC-V ISA and its vector extension, designed for high-performance computing and FPGA deployment.

A storage system for Hugging Face Hub that uses chunk-based deduplication to efficiently upload and download large AI models and datasets.

A toolkit for scaling the creation of training data and environments for software engineering agents, enabling the training of LLMs to solve real-world GitHub issues.

A unified Python SDK that provides a single interface to communicate with multiple LLM providers, allowing developers to switch models without changing their code.

An experimental framework from AMD Research that enables fast, scalable inference of quantized neural networks on FPGAs by generating customized dataflow architectures.

A toolkit for creating MCP servers on the 1C:Enterprise platform, allowing AI assistants to automatically access and interact with 1C database data and functionality.

An open foundation for agentic modeling research that provides a Kubernetes-native sandbox service and RL training stack to develop portable agent recipes across multiple domains.

A port of TensorFlow Lite designed to run machine learning models on microcontrollers and DSPs with limited memory.

A mail-like coordination layer for AI coding agents that provides identities, asynchronous messaging, and file reservation leases to prevent conflicts during parallel work.

An open-source secure virtual desktop designed for AI agents to perform 'Computer Use' tasks via programmatic GUI control and screen streaming.

A high-fidelity vulnerability scanner that combines deterministic native scanning with autonomous AI agents to audit codebases and web applications.

The official CLI for the Claude Platform that enables sending messages, managing API resources, and treating AI agents as version-controlled code.

An MCP server that enables AI agents to programmatically create and edit Draw.io diagrams, automating the creation of architectural diagrams and flowcharts.