A web automation framework that combines AI agents with traditional scripting to build reliable, cost-effective agents capable of navigating websites and bypassing bot detection.

A high-performance library for approximate nearest neighbor searches in high-dimensional vector spaces, supporting graph and tree-based indexing for datasets up to billions of objects.

A comprehensive Python library of 233+ meta-heuristic algorithms for solving complex global optimization problems and tuning AI/ML parameters.

An open-source framework for packaging AI skills into runnable local agents that can be integrated with Slack and Telegram to keep team data private.

An open-source, cross-platform AI voice typing app that enables dictation into any desktop application with AI-driven text cleanup and a personal glossary.

A series of lightweight 1.9B parameter language models from Bilibili, featuring specialized versions for chat, role-playing with RAG, and 32K long-context processing.

A fast and ergonomic machine learning library for Rust that provides a comprehensive suite of classical supervised and unsupervised learning algorithms.

Cellm is an Excel add‑in that adds a `=PROMPT()` formula, letting users call LLMs (hosted or local) on cell ranges to automate data‑cleaning, extraction, translation, summarisation, and other repetitive tasks directly inside spreadsheets.

A lightweight, offline RESTful API for managing vector-based knowledge bases, enabling AI agents to handle local long-term and short-term memory without cloud services.

Generative Manim is an open‑source tool that uses LLMs (GPT‑4o, Claude, Gemini, etc.) to turn plain‑English prompts into runnable Manim animation code and rendered videos. It provides a web demo, a REST API, and a desktop app (Animo) for local rendering, plus a training pipeline and benchmark suite for fine‑tuning open‑weight models to generate Manim code.

A modular deep learning extension for PyTorch designed to build neural network models on heterogeneous tabular data containing mixed column types like text, images, and numerical values.

A Python library that allows developers to import open-source robot descriptions as modules, automatically downloading and caching them for use in simulators like MuJoCo and PyBullet.

A cloud-agnostic ML infrastructure platform for real-time feature serving, model inference, and embedding search at massive scale.

GAGAvatar is a framework for one-shot 3D head avatar reconstruction and real-time reenactment from a single image using 3D Gaussian Splatting.

A modular PyTorch framework providing reusable, high-performance building blocks for assembling state-of-the-art AI models, including attention mechanisms, quantization, and multi-modal architectures.

An open-source adversary emulation framework for red-teaming AI agents and MCP servers, providing automated vulnerability scanning based on OWASP standards.

A library providing a programming model for writing performance-critical machine learning kernels that are portable across different GPU and CPU architectures.

A self-hosted AI agent built on n8n and PostgreSQL that integrates long-term memory, task management, and web automation via Telegram or HTTP API.

A status line plugin for Claude Code that provides unified usage monitoring, cost tracking, and rate limit alerts across multiple AI CLIs.

Senna is an autonomous driving system that integrates a Large Vision-Language Model with an end-to-end model to enhance planning safety, robustness, and generalization.

A web application for isolating or removing vocals, bass, and drums from songs using AI models like Spleeter and Demucs.

A Python-based starter toolkit for deploying and operating scalable, secure AI agents on Amazon Bedrock AgentCore using any open-source framework.

An MCP server that acts as a meta-mentor for AI agents, using Chain-Pattern Interrupts to prevent over-engineering and reasoning lock-in.

A stateless API wrapper for ComfyUI that enables deploying complex generative AI workflows as scalable, production-ready microservices.

A bridge that lets you control official AI coding CLIs (Claude Code, Gemini, Grok, etc.) via Telegram, Matrix, and Slack without using API proxies.

A comprehensive benchmark for Physics-Informed Neural Networks (PINNs) that implements multiple variants and a challenging dataset to evaluate their performance in solving partial differential equations.

A PyTorch-based recommendation system framework that provides pre-implemented state-of-the-art models and scalable infrastructure for production-ready deep learning recommendations.

A cross-platform desktop application for Groq models that features a chat interface with image support and local MCP server integration for function calling.

A compiler that converts ONNX models into standalone C code for efficient neural network inference on microcontrollers.

An MCP server that integrates Microsoft Teams with LLMs, allowing AI agents to read messages, create threads, and mention members.

A framework for creating agentic AI workflows where Docker containers serve as tools and Markdown files define the logic, allowing LLMs to execute complex tasks in sandboxed environments.

A Node.js library that provides plug‑in “skills” for AI coding assistants (Claude Code, Copilot, etc.) to generate Selenium, Playwright, Cypress, and other test‑automation code and run it on the TestMu AI cloud platform.

A C++ and Python library for interfacing with Luxonis DepthAI hardware to build spatial AI and computer vision applications.

A unified deep learning framework for ultra-large-scale recommendation systems that optimizes sparse and dense computing within the PyTorch ecosystem.

A compiler and registry that transforms verbose API specifications into compressed, agent-native formats to reduce LLM hallucinations and token costs.

An API that integrates ComfyUI nodes into Nuke, allowing VFX artists to use generative AI workflows directly within their professional compositing software.

Notebook Intelligence (NBI) is an open‑source JupyterLab extension that adds AI chat, inline code generation, auto‑completion, and an autonomous notebook‑editing agent. It works with Copilot, OpenAI‑compatible APIs, local Ollama models, or Anthropic Claude (via Claude Code). Features include Claude‑specific tools, MCP‑based tool calls, multi‑language awareness, and live reload of AI‑edited files.

A Rust-based long-term memory framework for AI agents that uses a three-tier hierarchical architecture and a virtual filesystem to provide persistent, context-aware interactions.

A C++/CUDA header-only library for Model Predictive Path Integral (MPPI) control, enabling high-performance stochastic trajectory optimization on NVIDIA GPUs.

A PyTorch implementation of the pi-zero robotic foundation model, using flow matching and a pretrained PaliGemma 2B model to generate robotic actions from vision and language.

A ROS 2 hardware interface that enables real-time communication between EtherCAT modules and the ros2_control framework using the IgH EtherCAT Master.

A high-level control library for Franka robots that enables real-time trajectory and torque control from Python and C++ without requiring ROS.

GenZ-ICP is a degeneracy-robust LiDAR odometry system that uses adaptive weighting to ensure stable localization in environments with few geometric features.

A Japanese text-to-speech software that uses the AivisSpeech Engine and ONNX-based models to generate emotionally rich synthetic voices.

An MCP server that provides AI agents with a transparent and auditable way to fetch documentation via llms.txt files.

A Prometheus exporter that collects NVIDIA GPU metrics using nvidia-smi or NVML, supporting Linux, Windows, and macOS.

A package for generating synthetic tabular and time-series data using generative models like GANs and Gaussian Mixtures to ensure privacy and augment datasets.

A complete open-source repository for building the DOLY robot, providing 3D printable hardware designs, electronic schematics, and a C++/Python SDK.