TimeCraft is a Microsoft‑Research diffusion‑based framework for generating synthetic time‑series data. It supports cross‑domain few‑shot adaptation via a prototype dictionary, natural‑language control, and target‑aware generation that optimises synthetic samples for downstream tasks. Extensions add causal constraints, online augmentation for foundation‑model pre‑training, and continuous‑time generation from irregular observations.

A browser-based studio that combines multitrack video editing and 3D scene direction with AI integration for automated scene composition and editing.

CodexLoom is a self‑hosted platform that adds durable identities, profiles, and organizational tooling to Codex chat agents, enabling long‑running “Domain Agents” that can be accessed from multiple devices, communicate via bounded messages, and be exposed to external chat platforms (Feishu, Slack, Parall) through Interface Agents. Targeted at advanced solo users, it provides UI, CLI, and governance features, and is released under the Elastic License 2.0.

A terminal-native runtime for durable, self-improving agentic workflows in a repository, using quality gates and codebase indexing to ensure work is actually completed.

A privacy-focused AI assistant app for Android featuring RAG-based memory, multimodal inputs, and built-in Python and JavaScript engines.

A Python library for flexible multimodal data preparation that optimizes the loading and manipulation of speech, audio, video, and image data for ML training.

An open-source agent-based framework for chatting with data and RAG, enabling users to generate data pipelines and visualizations via natural language.

Skywork-R1V is an open-source multimodal reasoning model that uses reinforcement learning and visual chain-of-thought to achieve state-of-the-art performance in complex visual logic, math, and physics tasks.

A high-performance WYSIWYG Markdown editor and kernel designed for large files, real-time collaboration, and streaming AI output.

A Python developer kit for accessing and working with the NVIDIA Physical AI Autonomous Vehicles Dataset to build end-to-end driving systems.

A tool that reduces AI agent token usage by distilling noisy command output and replacing repeated data with retrievable handles.

An AI employee platform for running durable, always-on autonomous agents that can be contacted via email or SMS and perform production browser automation.

An AI-powered computer automation tool that uses LLMs to self-drive a PC by simulating keyboard and mouse inputs based on visual feedback.

Sponsio is an open‑source library that adds deterministic, microsecond‑scale guardrails to LLM‑powered agents. It lets you write formal‑method‑backed contracts (YAML rulebooks) that are enforced on every tool call—blocking, warning, or allowing the action without invoking any model. The library integrates with LangChain, Claude, OpenAI, CrewAI, and other agent frameworks in Python or TypeScript, ships with 22 ready‑made contract bundles, and offers a hosted console for audit and review. Benchmarks show >95 % reduction of misaligned behavior and latency under 0.2 ms per call, making it a fast, reliable safety layer for production AI agents.

Harbor is a CLI‑driven Docker‑Compose orchestrator that lets you spin up a complete local LLM stack—including model back‑ends (Ollama, llama.cpp, vLLM, MLX, etc.), chat front‑ends (Open WebUI, LibreChat, AnythingLLM, …), web‑search, voice, image generation, and Boost‑based agentic workflows—with a single `harbor up` command.

A Lie theory library for robotics state-estimation that provides C++ and Python tools for handling rotations, translations, and velocities across various Lie groups.

aidevops is an MIT‑licensed AI‑DevOps framework that provides a CLI and OpenCode plugin for orchestrating AI agents across code, infrastructure, product, marketing and more. It breaks work into 14 main agents and thousands of sub‑agents, uses a pulse supervisor to route tasks, manage token budgets, keep secrets safe, and maintain Git hygiene. Install via npm or Homebrew, then run commands like `aidevops init`, `aidevops pulse`, or domain‑specific slash commands to automate builds, deployments, reports, and business processes while staying auditable.

A Python client for the Pinecone vector database that enables creating, managing, and querying vector indexes for AI applications.

A local-first stack that turns coding agents into personal AI assistants for work by leveraging existing user permissions and tool access to bypass corporate IT constraints.

A model compression toolkit for PyTorch and Keras that optimizes AI models for edge deployment using quantization, pruning, and hardware-aware optimization.

A specialized implementation of YOLOv3 designed to train and run object detection on the xView satellite imagery dataset for remote sensing applications.

A cross-IDE repository knowledge engine that creates a grounded Q&A system for codebases, allowing AI agents to provide accurate answers with file paths and line numbers.

Norse is a PyTorch‑based library that adds spiking neural‑network primitives (LIF, LSNN, etc.) for building, training, and evaluating event‑driven models. It offers pip/conda/Docker installation, ready‑made example tasks (MNIST, CIFAR‑10, cart‑pole), and integrates with PyTorch‑Lightning for scalable training.

A library for chest X-ray datasets and models, providing pre-trained models and a uniform interface for working with multiple public chest X-ray datasets.

NetKet is a Python library built on JAX that uses neural networks and machine learning to study many-body quantum systems.

A companion library for Pydantic AI that enables agents to load modular skills from local or remote registries, execute bundled scripts, and manage resources via progressive disclosure.

A syntax-aware code navigation tool that provides structural insights for humans and AI agents, reducing the number of tool calls needed to explore codebases.

A real-time video magnification tool that amplifies subtle motion and color changes using Eulerian video magnification techniques.

An MCP-native browser control plane that gives AI agents a real browser with human-in-the-loop takeover, reusable auth profiles, and built-in safety rails.

Dingo is an open‑source Python library (and SaaS product) for evaluating AI data, model outputs, and RAG systems. It supports rule‑based, LLM‑based, and agent‑driven checks, streams data from files, databases, S3, or Hugging Face, and provides JSON reports plus optional visual dashboards. Install via `pip install dingo-python` (with optional extras), run via CLI (`dingo eval …`) or Python SDK, and extend with custom rules, LLM prompts, or agents.

A comprehensive repository of structured AI conference paper records and a local search tool for analyzing academic literature from major venues like NeurIPS and ICLR.

A Kubernetes operator for enterprise-grade LLM serving that automates model management, runtime selection, and GPU resource optimization.

An AI-native backend and deployment layer that allows coding agents to directly deploy databases, edge functions, and frontends to turn AI-generated code into live apps.

An executable, Git-native catalog for tabular data work that turns ephemeral agent-generated scripts into reproducible, content-addressed pipelines.

Torch-RecHub is a PyTorch framework for building recommender systems with 30+ models, modular design, ONNX export, and support for multiple hardware backends.

An Obsidian plugin that uses Whisper to transcribe audio recordings or uploaded files into text, with optional LLM post-processing for grammar and formatting.

A mod for Skyrim and Fallout 4 that enables natural, AI-powered conversations with NPCs using speech-to-text, LLMs, and text-to-speech.

AnyRecon is a 3D reconstruction framework that uses a video diffusion model to generate high-quality, arbitrary-view reconstructions of scenes from a set of capture views.

A unified multimodal foundation model that integrates image understanding, text-to-image generation, and instruction-guided image editing with a focus on spatial intelligence.

A voice-activated, 100% local LLM agent for Raspberry Pi that can be extended with custom tools to automate hardware actions.

A local-first data curation and annotation tool for computer vision datasets that uses embeddings to help users efficiently manage and label image and video data.

An ultra-lightweight, anchor-free real-time object detection algorithm optimized for high-speed inference on ARM CPUs and embedded devices.

A web-based management dashboard for deploying and experimenting with customizable Generative AI use cases on AWS, supporting RAG-enabled chatbots and AI agents.

A Python wrapper for ByteDance's Seedance AI video generator, enabling high-fidelity text-to-video and image-to-video generation with a focus on realistic human faces and character consistency.

An AI-powered penetration testing automation framework that orchestrates security tools and multi-agent AI to perform adaptive security assessments and evidence-backed reporting.

An end-to-end AI platform that simplifies the orchestration of unstructured data, AI pipelines, and model deployment to build RAG and AI-first applications.

A minimalist framework for training video world models based on diffusion-forcing, used for future video prediction, 3D reconstruction, and robotic planning.

An open-source machine learning platform that unifies training, fine-tuning, inference, and evaluation into a single interface for individuals and research labs.