A facial expression recognition system using a Residual Masking Network to detect human emotions from images and live video feeds.

A pure‑Bash implementation of the Model Context Protocol (MCP) 2026‑07‑28, providing zero‑overhead stdio and local‑HTTP bindings for AI‑agent tool calling. It auto‑discovers `tool_*` functions, validates JSON against the official schema, includes full test suites, and offers step‑by‑step docs for building custom Bash‑based MCP servers.

A practical Python library implementing CMA-ES and its variants for black-box optimization of continuous, integer, and categorical variables.

A local-first, governed credit-risk Agent platform that transforms natural language requests into audited risk analysis, models, and strategies.

A library of traditional machine learning algorithms for Elixir, providing tools for classification, regression, clustering, and preprocessing built on top of Nx.

A scalable asynchronous reinforcement learning framework for LLM agents that uses in-flight weight updates to maximize GPU utilization while maintaining on-policy data freshness.

An open-source platform for controlling connected, automated vehicles that integrates navigation, guidance, and control to enable cooperative driving research.

An open-source AI assistant client for Android and web that allows users to connect multiple LLM providers using their own API keys.

An MCP server that connects Claude Desktop to SQL databases via SQLAlchemy, enabling the AI to explore schemas and execute queries.

A family of open-source Large Language Models and embedding models specifically optimized for Southeast Asian languages, cultures, and contexts.

A C++20 header-only abstraction library that provides performance portability for parallel kernels across various GPUs (NVIDIA, AMD, Intel) and CPUs.

A library for large-scale and reproducible hyperparameter optimization (HPO) that supports distributed execution and state-of-the-art tuning methods.

CRAB is a Python-centric framework for building and evaluating multimodal embodied AI agents across diverse environments like Docker, VMs, and physical machines.

MathVista is a benchmark for evaluating the mathematical reasoning of foundation models in visual contexts, combining 6,141 examples from 31 multimodal datasets.

A JAX and Flax NNX-based framework for the high-performance training, fine-tuning, and serving of LLMs and multimodal models on TPU/GPU clusters.

Sopify is a development process protocol for AI coding that prevents premature coding by enforcing a plan-first workflow and storing resumable project plans in git-tracked files.

An intelligent data search and enrichment library that automatically finds and integrates accuracy-improving external features into ML pipelines using LLMs and GNNs.

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.

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

Beluga is a C++17 library that implements Monte Carlo Localization (particle filters) for robots. It provides a ROS‑agnostic core, ROS bindings, an AMCL‑compatible node, benchmarking tools, and an optional OpenVDB extension for 3‑D localization.

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

An AI framework for astronomy that automates telescope observations, classifies light curves and pulsars, and provides a specialized skill pack for astronomical research.

A collection of examples and techniques for building scalable, serverless generative AI applications using prompt chaining with AWS Step Functions and Amazon Bedrock Flows.

A ComfyUI custom node for precise resolution and aspect ratio control, featuring a visual 2D canvas and model-specific optimizations for AI image generation.

Clouds Coder is a Python runtime that separates CLI execution from a browser‑based IDE, adds AI‑agent orchestration, and provides a LAN‑only collaborative workspace with versioned files, conflict‑resolution, and admin‑approved tool policies.

A set of performance optimizations for Qwen3.5-122B-A10B on NVIDIA DGX Spark, increasing inference speed from 28.3 to 52 tokens per second using hybrid quantization and speculative decoding.

A JavaScript library for performing OCR and text extraction from images and PDFs, capable of creating searchable PDFs with invisible text layers.

An infinite canvas for learning that allows users to branch into new documents by asking questions at any point in existing content.

A distributed, high-throughput pipeline for processing web-scale multimodal datasets, featuring Rust-accelerated operators for filtering, scoring, and deduplication.

ZCF is a zero-config setup tool that provides one-click initialization for Claude Code and Codex, automating the configuration of workflows, APIs, and agent systems.

A version control system and Claude Agent SDK plugin that allows developers to commit, diff, and merge agent configurations and traces to prevent performance regressions.

A high-performance n-dimensional tensor library for Nim, providing tools for scientific computing, machine learning, and deep learning across CPU, CUDA, and OpenCL backends.

A curated collection of research papers and datasets focused on anime and cartoon generation, covering topics from image synthesis to animation production.

Texar is a modular toolkit for NLP and text generation that provides easy-to-use ML modules and pre-trained models for fast prototyping and experimentation.

A toolkit that enables AI coding agents to compose, edit, and generate videos via a readable plan file, providing a deterministic pipeline for automated video production.

Fulling is a foundation for building dedicated AI workspaces that combine runtime, memory, and skills within a secure Kubernetes-based credential boundary.

An agent daemon that runs AI agents, dispatches tools, and connects to MCP servers, using restricted harnesses for secure tool execution.

A collection of microservice-based generative AI examples and deployment guides designed to simplify the scaling and testing of GenAI applications across diverse hardware platforms.

PIX is a JAX‑based image‑processing library that provides GPU/TPU‑accelerated functions (e.g., flips, resize) which can be compiled with `jax.jit`, vectorised with `jax.vmap`, or run on multiple devices with `jax.pmap`. Install JAX first, then `pip install dm-pix`. Use it just like NumPy image code, but with full JAX performance and automatic differentiation.

A Python execution engine for AI agents that records every step of a workflow, allowing users to to replay and resume from a failed step rather than restarting the entire process.

A PyTorch-based tool for detecting anime faces and estimating 28 facial landmark points using pretrained Faster R-CNN, YOLOv3, and HRNetV2 models.

A decentralized platform and SDK for creating competitive markets for machine intelligence and other digital commodities, rewarded via a blockchain-based incentive system.

A role-oriented CLI for React Native and Expo teams that automates mobile QA, performance reviews, and implementation using AI agents.

A template-first framework for building and deploying production-ready AI agents, providing built-in tools, a chat interface, and advanced debugging capabilities.

An inference-native agent harness designed for loop engineering, optimizing token usage and cache reuse to maintain efficient, long-horizon recursive AI workflows.

An open-source AI model comparison tool that provides real-time pricing and feature comparisons across multiple LLM providers.

ParoQuant is an INT4 quantization framework for LLMs that uses learned pairwise rotations to reduce weight outliers and maintain high accuracy during efficient inference.

A cross-platform inference engine for running highly accurate, compressed LLMs locally on devices ranging from mobile phones to web browsers.