AllData is a comprehensive data middle-platform that provides an end-to-end suite for data integration, storage, governance, and AI application development.

A long-term memory system for AI assistants that uses a hybrid graph-vector storage layer to persist preferences and context across different tools and sessions.

An open testing platform for Kubernetes that allows engineering teams to run, orchestrate, and analyze any automated tests directly within their cluster infrastructure.

A tool that turns software repositories into agent-ready workspaces by installing a repository protocol and structured documentation to guide AI coding agents.

A state-of-the-art deep learning library built on PyTorch and fastai for time series tasks including classification, regression, and forecasting.

A high-performance Settlers of Catan simulator and AI player designed for running large-scale simulations and training reinforcement learning agents.

An MCP-based plugin for Unreal Engine that exposes over 1,400 editor actions to AI assistants using a namespace-dispatch pattern to minimize context window usage.

An unofficial Electron wrapper for Paperclip that turns the AI agent orchestration platform into a one-click desktop application for easier installation and launch.

A Python package for simulation-based inference that estimates the posterior distribution of simulator parameters based on observed data using Bayesian methods.

An AI-powered lightweight Kubernetes dashboard that simplifies cluster management through a visual interface, AI-assisted troubleshooting, and MCP-based tool execution.

An open-source backend for MongoDB that instantly generates REST, GraphQL, and WebSocket APIs with built-in authentication and no backend code required.

A tool that lets humans act as AI models by providing an OpenAI-compatible API interface, allowing people to be called as 'models' by AI clients or agents.

A library for type annotations and runtime type-checking of array shapes and data types across JAX, PyTorch, NumPy, MLX, and TensorFlow.

A complete ML SDK and application suite for Apple Silicon written in Rust, providing tools for training, fine-tuning, and inference using Metal GPU and ANE.

A Nix-based configuration framework that provides reproducible, declarative deployments and ready-to-use packages for Model Control Protocol (MCP) servers.

A Python library and CLI tool that automates the discovery of Cloudflare Turnstile sitekeys and generates valid tokens via the Peak API to bypass security challenges.

A massive, open-source Chinese corpus project aiming to collect and provide 253TB of diverse internet text and multimodal data for training AI models.

A collection of specialized toolsets and workflows called "powers" that extend AI agent capabilities for cloud infrastructure, DevOps, and software development tasks.

A production-ready AI gateway that provides a unified, OpenAI-compatible interface for routing, monitoring, and multi-tenant management across multiple AI providers.

An open framework for confidential AI that allows deploying AI applications in hardware-isolated confidential VMs with cryptographic privacy guarantees.

A benchmark that evaluates LLM creative writing by having evaluator models compare short stories written to the same constrained creative briefs.

A VS Code extension that integrates various domestic Chinese LLM providers and custom API-compatible models into GitHub Copilot Chat.

A multi-database server implementing the Model Context Protocol (MCP) that provides AI assistants with structured and secure access to multiple database engines.

A Kubernetes operator and proxy that simplifies deploying and scaling AI models with prefix-aware load balancing to optimize LLM performance.

An open-source agentic telemetry system that ingests OpenTelemetry data and groups noisy signals into incidents for easier production debugging.

A CLI-first orchestration layer for AI coding agents that allows users to run tasks across multiple models in parallel to compare perspectives and reduce blind spots.

A framework for verified GUI automation that compiles human demonstrations into deterministic programs, allowing AI agents to execute tasks in applications without APIs with guaranteed verification.

Ludwig is a declarative deep learning framework that enables users to train, fine-tune, and deploy LLMs, multimodal, and tabular AI models using YAML configuration files instead of boilerplate Python code.

An AI-programmable, serverless content platform for AWS that allows developers to build and extend a headless CMS and website builder using TypeScript.

A cross-platform desktop widget that tracks Claude.ai usage statistics, limits, and spending in real-time with visual alerts.

A differentiable finite element package based on JAX that enables automatic inverse design and mechanistic data science through GPU-accelerated simulations.

The official Ruby SDK for the Model Context Protocol, enabling developers to build MCP servers and clients to expose tools and resources to AI hosts.

EdgeBench is a benchmark of 134 real-world tasks designed to evaluate how autonomous AI agents learn and improve through iterative interaction with an environment over long horizons.

A benchmark and baseline agent for assessing the ability of LLMs to perform root cause analysis by analyzing telemetry data like logs, metrics, and traces.

A curated collection of open datasets containing data from over 602 million cells designed to accelerate the creation of virtual cell models.

A high-accuracy Game Boy emulator written in C++ featuring an embedded MCP server for AI-assisted debugging and ROM hacking.

A tool that runs local processes inside a live Kubernetes cluster by mirroring traffic, files, and environment variables from a target pod.

A conservative AI maintenance bot for GitHub repositories that automates issue/PR reviews, code repair, and guarded automerging to reduce maintainer workload.

A federated, domain-anchored specification for cataloging and discovering agentic resources like MCP servers, skills, and APIs across networks.

A cross-platform Go wrapper for the onnxruntime library, allowing Go developers to load and execute ONNX-format neural networks with hardware acceleration support.

A GPU-accelerated machine learning library for NVIDIA GPUs that provides scikit-learn-style APIs and a transparent acceleration module for existing CPU-based workflows.

LiveBench is a contamination-free benchmark for LLMs that uses monthly updated questions and objective ground-truth answers to provide reliable performance evaluations.

A collection of utilities, notebooks, and serving components for working with IBM's Granite Time Series Foundation Models for forecasting.

Ceres Solver is a C++ library for modeling and solving large, complex non-linear least squares and general unconstrained optimization problems.

CUDA Tile IR is an MLIR‑based compiler infrastructure from NVIDIA that introduces a dedicated dialect for tile‑oriented CUDA kernels. It provides C++ and Python APIs, a binary bytecode format, and tools to translate MLIR to bytecode or cubin, enabling high‑performance kernels that target NVIDIA Tensor‑Core units. The project builds on LLVM/MLIR, aligns with CUDA Toolkit 13.1, and includes a conformance test suite. It is a genuine AI‑related compiler project, not a tutorial or list.

A C++ LLM inference engine based on ggml that enables memory-efficient local execution of multimodal models with RAG and quantization support.

A serverless, privacy-focused online document editor that allows users to edit Word, Excel, and PowerPoint files locally in the browser using WASM.

A collection of 68 ready-to-use agent skills for trading, DeFi, and quantitative finance, enabling AI agents to perform market analysis, backtesting, and on-chain research.