A loopback proxy that enables Claude Code's UltraCode mode to work with any LLM backend, featuring smart routing and orchestrator/worker splitting.

A multi-agent coordination framework that decomposes complex tasks into parallel subtasks with git-backed task tracking and semantic memory to prevent context loss.

An LV2 plugin for playing back neural network machine learning amplifier models using the NeuralAudio engine.

A Python SDK and ecosystem for creating AI projects on edge devices, providing simple APIs for AI vision, audio, and LLMs on MaixCAM hardware.

A visual debugger for Qwen3.6-27B on Apple Silicon that uses a Jacobian lens to visualize and edit the model's internal latent representations.

A developer toolkit for integrating machine learning into graphics applications, enabling the use of neural networks to represent shaders and textures.

A vectorized, differentiable 2D physics simulator built in PyTorch for efficient Multi-Agent Reinforcement Learning (MARL) benchmarking and collective robot learning.

Ovis is a Multimodal Large Language Model (MLLM) architecture that structurally aligns visual and textual embeddings to enable high-resolution perception and reflective reasoning.

A computer vision library for the detection and accurate localization of circular fiducial markers made of concentric circles.

A Rust library and CLI tool for extracting text from images using neural network models to minimize the need for image preprocessing.

A PyTorch library and evaluation platform for end-to-end deep learning-based image and video compression research.

A specialized knowledge set for AI coding agents that provides expert guidance on Core Data persistence, performance optimization, and schema migration for Apple platforms.

A Python library for genetic programming that uses symbolic regression to discover mathematical expressions that describe relationships between variables.

An AI-powered data analysis and research platform that uses a multi-agent system to automate hypothesis generation, data processing, visualization, and report writing.

An open-source fleet operations stack for PX4 drones that enables synchronized drone shows, search-and-rescue missions, and cooperative swarm autonomy.

A standalone desktop application for translating academic PDFs that preserves original formatting, formulas, and layouts while integrating deeply with Zotero.

A collection of official and community samples, model recipes, and deployment tools for LiteRT and LiteRT-LM to enable high-performance on-device ML execution.

A self-hosted AI backend that provides a unified OpenAI-compatible API to connect private data sources and tools to local or hosted LLMs for governed agent deployment.

A complete ML SDK and application suite for Apple Silicon written in Rust, providing tools for training, fine-tuning, and inference using Metal GPU and ANE.

A Python SDK for Oxylabs AI Studio, providing AI-powered web scraping, crawling, and browsing agents to extract structured data using natural language prompts.

Ceres Solver is a C++ library for modeling and solving large, complex non-linear least squares and general unconstrained optimization problems.

An open-source codebase intelligence tool that provides agents and teams with cited context from current code, git history, and technical web research.

A suite of development tools for streamlining the end-to-end cycle of LLM-based AI applications, from prototyping and prompt engineering to evaluation and production deployment.

An intelligent assistant for ComfyUI that automates the generation, debugging, and optimization of image generation workflows using an LLM-powered agent.

A portable, single-file memory layer for AI agents that provides persistent long-term memory and instant retrieval without requiring a database.

A GPU-accelerated optimization engine for solving large-scale linear, quadratic, and vehicle routing problems in near real-time.

A Kubernetes Gateway API extension that optimizes the routing and load balancing of self-hosted generative AI models to improve latency and throughput.

A pure-Python desktop application and library for chemistry and cheminformatics that implements molecular visualization, SMILES parsing, and MMFF94 optimization from scratch without external C++ dependencies.

A terminal session manager that allows AI agents to run, monitor, and interact with background dev servers and TUIs without blocking.

A framework for synthesizing synthetic data and AI feedback to create high-quality datasets for training and fine-tuning AI models.

A local token consumption and cost tracking tool for AI agents like Claude Code, Codex, and Kimi Code, featuring real-time status bars and detailed usage analytics.

A Kotlin Multiplatform SDK for the Model Context Protocol, enabling developers to build standardized clients and servers that provide context, tools, and resources to LLMs.

An open-source platform for interactive learning that provides scalable individual feedback, automatic assessment, and optional LLM-powered tutoring for universities.

A self-building, open-source database that uses AI agents to turn raw information into structured knowledge and process graphs for automation and decision-making.

An end-to-end platform for building computer vision AI models, providing tools for annotation, training, and optimization for deployment on edge hardware.

A PyTorch library for the pre-training, fine-tuning, and evaluation of Universal Time Series Transformers, enabling zero-shot forecasting across diverse datasets.

A local-first Kanban board and agent orchestration platform that provides governance, safety guardrails, and workflow management for autonomous AI coding agents.

A collection of libraries and frameworks for generating differentially private statistics over datasets to protect individual privacy in aggregate data analysis.

Microsoft’s Global Building Footprints repo releases a >1 billion‑building, open‑licensed dataset of polygon footprints (and many height estimates) generated by deep‑learning segmentation models. The data are provided as gzipped line‑delimited GeoJSON files, indexed by Bing quad‑keys, with confidence scores and documentation for large‑scale GIS or AI‑driven urban analysis.

A collection of recipes for shrinking, optimizing, and customizing cutting-edge vision and multimodal AI models to improve efficiency and performance.

A skill-centric agent runtime that allows AI agents to design, execute, and persist reusable skills to improve their performance on complex tasks through a reflection-based learning loop.

A system for decoding natural sentences from non-invasive brain recordings, enabling the reconstruction of text from brain activity during typing.

DreamLite is a compact 0.39B parameter unified diffusion model that enables ultra-fast, 1024x1024 image generation and editing fully on-device.

rtmlib is a lightweight Python library for human and animal pose estimation that wraps RTMPose and ViTPose models. It avoids heavy OpenMMLab dependencies, requiring only numpy, OpenCV and ONNX Runtime (with optional GPU/accelerator back‑ends). The package provides high‑level solution classes (Wholebody, Body, Hand, Animal, Custom, Wholebody3d) that combine a detector (YOLOX, RFDETR, RTMDet) and a pose estimator, plus utilities for drawing skeletons. Models are auto‑downloaded from OpenMMLab or a HuggingFace mirror. Install via pip or from source, and run a Gradio WebUI or use the Python API for single‑image, video, or webcam inference.

An AI-powered code review tool that integrates into CI/CD pipelines to provide inline comments, summaries, and context-aware feedback using various LLM providers.

An automated transaction categorization tool for Actual Budget that uses LLMs to integrate with various AI providers to classify expenses and suggest new categories.

ReSplat is a feed-forward recurrent model for 3D Gaussian splatting that iteratively refines scene representations using rendering error as feedback.

A browser extension for Chrome and Firefox that uses text-to-speech technology to convert webpage text into audio for improved accessibility and multitasking.