A PyTorch-based library for neural spatiotemporal forecasting that provides a unified framework for data preprocessing, model prototyping, and Graph Neural Network implementation.

A neural network based algorithm for heterogeneous cryo-EM and cryo-ET reconstruction that models continuous distributions of 3D structures.

An implementation of the ScreenAI vision-language model designed for understanding user interfaces and infographics.

SuperBench is a validation and profiling tool for AI infrastructure designed to improve the reliability of cloud AI environments.

A Node.js CLI/Web UI that uses the OpenAI ChatGPT API (or compatible services) to translate SRT subtitle files line‑by‑line, preserving timing. It batches lines, supports structured JSON output, prompt‑caching, optional moderation, and an advanced multi‑pass “agent” mode for richer translations.

A deep learning toolkit for single-cell gene expression analysis that provides a benchmark platform for reproducing experiments and automated preprocessing recommendations.

LViT is a multimodal framework that combines language and vision transformers to improve the accuracy of medical image segmentation in CT scans and other medical imagery.

A GPU-accelerated library for single-cell analysis that provides an AnnData-first API and compatibility with the Scanpy ecosystem.

An AI-powered code review tool that uses DeepSeek models to automate PR reviews via GitHub Actions or local CLI audits.

An extension of LightGBM that enables probabilistic modelling by predicting the full conditional distribution of a target variable instead of a single point estimate.

A Java SDK for interacting with Gemini Developer and Gemini Enterprise Agent Platform APIs, enabling content generation, multimodal input, and automatic function calling.

A sensitivity analysis utility package for the SciML ecosystem that helps determine how model outputs change relative to input parameters.

A Kubernetes device plugin that enables the registration and scheduling of AMD GPUs as compute resources within a container cluster.

A CLI tool that uses AI to automatically generate standardized conventional git commit messages based on code changes.

A fast robot kinematics and dynamics library written in pure Python using JAX for JIT-compilation and automatic differentiation.

A PyTorch library for offline reinforcement learning that provides a standardized framework and implementations of state-of-the-art model-free and model-based algorithms.

An open-source planning tool that turns complex project briefs into structured, editable planning baselines and interactive reports using AI.

An asynchronous data flow execution engine that lets developers build agentic applications by defining workflows as declarative YAML or JSON graphs.

A collection of Kubernetes deployment manifests that enable users to easily deploy and deploy Dify on a Kubernetes cluster.

A neural intelligence framework featuring a Rust-based neural network engine, advanced forecasting models, and a swarm orchestration system for CPU-native, ephemeral AI.

An integrated AI hardware evaluation engine that benchmarks the actual performance of AI chips across various models, frameworks, and software stacks to ensure fair and reproducible results.

An AI-powered DevOps CLI that allows users to manage, query, and deploy cloud infrastructure and Kubernetes clusters using natural language agents.

An extensible training framework for universal recurrent neural networks optimized for fast multi-GPU training and decoding.

A persistent, situated companion runtime for Claude Code that adds long-term memory, homeostatic needs, and hardware integration for cameras and speech.

A collection of Spring Boot starters that simplify the integration of LangChain4j into Java applications, reducing boilerplate for AI capabilities.

A framework and set of utilities for creating backends that allow Triton Inference Server to execute models from various deep-learning frameworks or custom C/C++ logic.

A library to wrap stdio-based Model Context Protocol (MCP) servers into AWS Lambda functions, enabling cloud-hosted MCP servers accessible via HTTPS.

A persistent memory system for AI agents that tracks and measures whether human corrections actually change agent behavior across sessions to prevent repeating mistakes.

A collection of PyTorch operators used to evaluate the performance of Triton and its integration with PyTorch.

ALF (Agent Learning Framework) is a PyTorch‑based reinforcement‑learning library offering a large collection of algorithms (A2C, PPO, SAC, MuZero, etc.), modular components, Python‑style configuration, and support for single‑ and multi‑GPU/cluster training. It includes many ready‑to‑run examples (CartPole, Atari, MuJoCo, MetaDrive) and provides Docker, Nix, and uv‑based installation options.

A PHP SDK for the Model Context Protocol (MCP) that enables the creation of MCP servers and clients, specifically optimized for stateless web hosting environments.

A robust benchmark for evaluating video understanding in MLLMs, using a three-level progressive difficulty scale and grouped non-linear scoring to measure true temporal reasoning.

DanceOPD is a research library that distills multiple diffusion‑based image‑generation capabilities (text‑to‑image, local edit, global edit, realism, etc.) into one model. It treats each teacher as a velocity field, queries the teacher on the student’s own rollout states, and trains with a simple velocity‑MSE loss. The repo supports SD‑3.5‑Medium and Z‑Image backends, includes a tiny smoke‑test, and provides scripts/configs for full training with LoRA adapters.

A Julia package that uses symbolic expressions to easily build, manipulate, and optimize complex machine learning pipelines for regression and classification.

A lifecycle plugin for OpenClaw and related hosts that integrates MemOS Cloud to provide AI agents with persistent memory recall and message storage.

A fully offline mobile AI application that enables private, on-device chat, document analysis, and multimodal interactions without cloud dependency.

An MCP server that enables AI assistants to execute local Terraform workflows and manage HCP Terraform/TFE infrastructure through a standardized set of tools.

A custom node collection for ComfyUI that enables real-time interactive AI art by integrating streaming and external controls like MIDI, OSC, and gamepads.

A security framework that documents adversary behaviors and provides mitigation strategies for agentic systems using the Model Context Protocol (MCP).

A self-hosted version of Weights & Biases for tracking machine learning experiments and metrics on private infrastructure.

Milady is a privacy‑first personal AI assistant that runs locally (or via a self‑hosted or cloud backend). It offers a desktop app with a 3‑D avatar, multi‑platform chat connectors, progressive action streaming, and built‑in BNB‑Smart‑Chain trading. Install via signed installers for macOS/Windows/Linux, or use the CLI (`milody setup`). The system is energy‑aware, plugin‑extensible, and can be securely exposed as a remote backend with an API token.

A Python framework for simulating private federated learning experiments, supporting multiple ML frameworks and differential privacy mechanisms.

A lightweight Python library for analyzing the performance of infrared small target detection models using pixel-level, target-level, and hybrid metrics.

A benchmarking framework for testing AI models on ARC-AGI tasks, featuring multi-provider adapters, rate limiting, and automated scoring.

A runtime-loadable SQLite extension that enables fast, SIMD-accelerated vector search using HNSW, providing a SQL interface for approximate nearest neighbor queries.

A unified library for Multiple Instance Learning (MIL) in computational pathology, providing a standardized framework to implement and compare numerous MIL architectures for whole-slide image analysis.

An agent-native operating system that creates a shared workspace for humans and AI agents to collaborate, preventing the loss of shared intelligence across a team.

A React-based AI chat application that uses two collaborating agents—one for logic and one for creativity—to provide more comprehensive and reasoned answers through internal debate.