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.

A Go client library providing support for the pgvector PostgreSQL extension to enable vector similarity search and storage in Go applications.

A PyTorch library implementing Differentiable Neural Computers (DNC), Sparse DNC (SDNC) and Sparse Access Memory (SAM) with install instructions, API usage, debugging support, and example training tasks (copy, addition, argmax).

A library of ready-to-run deep learning training recipes that provide production-ready baselines for common tasks to eliminate repetitive glue code.

An MCP server that provides AI-driven semantic code search for AI clients, using Windsurf's Devstral API to iteratively find relevant code snippets via local commands.

A toolkit for running AWS DeepRacer training environments on cloud VMs or local computers, enabling independent, scalable reinforcement learning for autonomous racing.

A Python API for OpenML that allows users to download and upload datasets, machine learning experiment results, and curated benchmarking tasks.

SmartPDF is an AI-powered tool that instantly summarizes and sections PDF documents using the DeepSeek V4 Flash model.

A native macOS desktop client for Claude Code that brings the CLI agent workflow into a project-centric GUI for non-developers.

An on-device, fully offline SDK for iOS that provides face detection, recognition, and liveness detection to enable secure identity verification without network access.

A JAX-based Learning-to-Rank library providing off-the-shelf ranking losses, metrics, and transformations for optimizing the relative order of items.

A reinforcement learning library that uses Adversarial Motion Priors to help humanoid agents learn motor skills from motion capture data.

A minimal coding agent harness with a tiny core prompt and a small built-in toolset, designed for lightweight and configurable AI-assisted development.

A multi-agent deep reinforcement learning framework using MADDPG to optimize spectrum sharing and power control for V2V and V2I communications in high-mobility vehicular networks.

An open-source AI storytelling platform that generates multiple story variations from a single prompt and provides tools for analysis and comparison.

Superinterface is a React library that provides components and hooks for building AI assistant interfaces, such as chats and wizards, into apps and websites.

A machine learning pipeline framework that ensures reproducibility and manages task dependencies by tracking metadata and automating reruns.

modelrelay is a free, OpenAI‑compatible local router that benchmarks and auto‑selects the fastest, highest‑quality free LLMs from many providers. Install via npm or Docker, then point your existing OpenAI‑based tools at `http://localhost:7352/v1` and let the router handle model choice, tagging, and QoS scoring.

A PyTorch implementation of QANet, a convolutional neural network architecture for question answering tasks.

Python bindings for whisper.cpp that provide a simple API for high-performance speech-to-text transcription with support for multiple hardware acceleration backends.

An optimization-based MPC motion planner that uses ADMM to enable real-time, collision-free navigation for robots in cluttered environments.

A Go client library for the Qdrant vector search engine, providing utilities to manage collections and perform similarity searches.

Official ROS 2 description package for Universal Robots manipulators, offering URDF/Xacro models, visual meshes, and launch helpers, with builds for all current ROS 2 distributions.

A lightweight Python interface that connects learning agents with interactive fiction games for testing reading comprehension and strategic decision-making.

A privacy-focused, offline document translation tool that translates various file formats while preserving original layouts using local LLMs and OCR.

A Python ROS Bridge library that enables interaction with ROS robots over WebSockets, allowing control from any platform without requiring a local ROS installation.

An MLX port of Moonshot's Kimi-K3 multimodal MoE model, featuring a streaming converter and REAP pruning to enable execution on Apple Silicon.

A knowledge graph visualization tool that transforms codebases into searchable graphs to analyze dependencies and enable GraphRAG-powered chat for developers.

A Julia package that enables programming and executing computations on AMD GPUs using the ROCm platform.

A Vision-Language-Action-Critic model that provides dense reward feedback and trajectory quality screening for real-world robotic reinforcement learning.

A library of utilities for deploying and managing Dask workers on CUDA-enabled systems to facilitate multi-GPU parallel computing.

A JavaScript SDK for integrating Microsoft Cognitive Services speech capabilities, enabling speech-to-text and text-to-speech functionality in browsers and Node.js.

Aligator is a C++/Python library for fast, constrained trajectory optimization in robotics. It offers a modelling API, efficient solvers (ProxDDP, FeasibleDDP), Pinocchio integration, optional Crocoddyl compatibility, and parallel CPU optimisations. Install via conda or build from source (CMake/Pixi). Use it to generate motion plans or run model‑predictive control on complex robots.

An AI-native console for ClickHouse that enables natural language query generation, intelligent visualization, and cluster diagnostics.

An iOS SDK for real-time pose estimation and skeleton tracking, providing pre-built tools for exercise counting and range-of-motion analysis.

A Python library for deep learning on tabular data that provides a scikit-learn compatible API and a zoo of 15+ neural architectures.

A command line interface extension for ROS 2 that allows users to query and execute robotics commands using natural language via OpenAI or Ollama.

An open-source, low-cost differential drive robot platform integrated with ROS 2 for educational purposes and robotics experimentation.

A ComfyUI wrapper for Meta's SAM 3D Body that enables full-body 3D human mesh recovery from a single image.

ControlAR provides controllable image generation for autoregressive models, allowing spatial guidance via edges, depth, or masks with support for arbitrary resolutions.

An API providing access to Sabiá LLMs, specifically optimized for the Portuguese language and Brazilian context, with full OpenAI API compatibility.

A local-first, multi-provider coding agent that defaults to DeepSeek V4 Flash and features OS sandboxing for secure, cost-aware software development.

A Python implementation of Local Outlier Probabilities (LoOP) that provides interpretable outlier scores as probabilities between 0 and 1.

A Python SDK for developing custom actions for Rasa, allowing chatbot developers to implement complex, custom logic in Python.

A high-level Python wrapper for Anthropic's SDK that simplifies stateful chat, tool use, and prompt caching for Claude models.

A research exploration into training open-source LLMs to extract patient history and use clinical calculators for medical risk assessment.

An LLM-powered application that retrieves, aggregates, and rewrites RSS feeds to create curated, high-quality content streams.