An orchestration framework that runs multiple Claude Code agents in parallel to systematically fix bugs and implement best practices across large codebases.

A framework for building MCP servers that automatically converts Python files into server capabilities, reducing boilerplate and providing built-in authentication and telemetry.

An AI-powered IDA Pro plugin that assists binary reverse engineering through LLM-driven function explanation, semantic knowledge graphs, and RAG-based document search.

YunChang provides a Unified Sequence Parallel (USP) attention mechanism that hybrids DeepSpeed-Ulysses and Ring-Attention to enable efficient long-context LLM training and inference.

A domain-specific programming language for prompting models that uses type inference to automatically generate JSON schemas and build complex prompt chains.

Clair3 is an open‑source deep‑learning variant caller for long‑read sequencing. It first scans quickly with a pileup‑based neural net, then refines uncertain sites with a full‑alignment model, delivering high accuracy while keeping runtime reasonable. Available as CPU, GPU, and Apple‑Silicon builds, it can be installed via Docker, Singularity, Bioconda, or a Conda environment, and ships pre‑trained PyTorch models for ONT, PacBio HiFi, and Illumina data.

Rust bindings for Apple's MLX library, enabling high-performance machine learning and array operations optimized for Apple Silicon.

TiRex is a pre-trained xLSTM-based model for zero-shot time series forecasting, classification, and regression, providing high-performance predictions across both long and short horizons without requiring training on user data.

An MCP server that allows AI assistants to programmatically control Adobe Photoshop on Windows to create documents, manage layers, and apply effects.

A serverless AWS solution that uses OCR and generative AI to automate the extraction of structured data from unstructured documents at scale.

Handwrite is a tool that generates a custom font based on a user's handwriting sample, allowing them to type documents that look handwritten.

A persistent AI companion and agent runtime written in Rust that integrates long-term memory, computer use, and scheduled background work.

A high-performance linear algebra library optimized for small, cache-resident matrices typically used in embedded optimization applications.

A collection of standard messages and services for ROS 2 that enables different robotics software components to communicate without creating circular dependencies.

A modular embedded control framework for RoboMaster robots that uses a three-layer architecture (BSP, Module, App) to simplify robot development and hardware abstraction.

A local-first AI image workspace that combines an infinite canvas with agentic planning for multi-step prompt-to-image generation.

SkVM is a compilation and runtime system that makes LLM agent skills portable and optimized across different models and agent harnesses.

A Cloudflare Worker that transforms Google's Gemini models into OpenAI-compatible endpoints, allowing Gemini to be used with any OpenAI SDK or client.

NNStreamer provides GStreamer plugins that let developers embed neural‑network inference directly into media pipelines, supporting many AI frameworks and hardware accelerators across Linux, Android, Tizen, and macOS.

UPage is an open‑source, Docker‑based platform that uses large language models to turn natural‑language descriptions into fully responsive web pages. It offers a visual editor, multi‑page generation, and export of clean HTML/CSS/JS, and works with any compatible LLM API.

A deep learning framework for point cloud analysis that provides a high-level API and a library of state-of-the-art models for 3D classification, segmentation, and detection.

A fast neural vocoder that synthesizes high-quality audio waveforms from acoustic features using spectral coefficients and inverse Fourier transform.

A scalable toolkit for cleansing, transforming, and enriching unstructured data to prepare it for LLM pre-training, fine-tuning, and RAG applications.

An MLX-based implementation of Nvidia's Parakeet ASR models for Apple Silicon, providing efficient local audio transcription with streaming and timestamp support.

An agentic research engine for GitHub that uses LLMs and semantic recall to find the best-fitting repositories based on intent and source code analysis rather than just keywords or stars.

A universal content reader that fetches, transcribes, and digests content from various platforms like YouTube, X, and WeChat into a structured format.

A modular C++ library with Python bindings that implements the Iterative Closest Point (ICP) algorithm for aligning 3D point clouds in robotics and computer vision.

A GPU-accelerated library for processing triangle meshes, featuring integrated matrix infrastructure and automatic differentiation for geometry processing tasks.

A cross-platform desktop manager for AI accounts, subscriptions, and emails, providing one-click account switching and subscription tracking.

A web-based image labeling tool for creating training data for object detectors, supporting formats like COCO and Pascal VOC.

A web interface and management layer that brings tmux-based AI agent CLI sessions to any browser on desktop or mobile.

A collection of minimal solvers and robust estimators for camera pose estimation, supporting various correspondences and camera models with minimal dependencies.

An image composition toolbox that provides a unified set of tools for realistic object insertion, including harmonization, shadow generation, and placement assessment.

A ComfyUI integration for Meta's SAM3 that enables open-vocabulary image and video segmentation using natural language text prompts.

An open-source meeting copilot that provides real-time AI assistance via a stealth overlay and automated post-call summaries using local storage and BYOK API keys.

An open-source project that provides a full-lifecycle training pipeline for building a lightweight 0.1B MoE large language model from scratch, including pretraining, SFT, and RLHF.

A generative AI movie studio integrated into the Blender Video Editor that allows users to prototype full film productions using AI-generated video, audio, and text.

FuxiCTR is an open‑source Python library (PyPI package) for click‑through‑rate prediction. It bundles more than 40 modern CTR models—both classic factorization‑machine style and recent sequence‑aware architectures—implemented for PyTorch and TensorFlow. The library emphasizes configurability, automatic hyper‑parameter tuning, reproducible benchmarks, and easy extensibility, making it useful for researchers and engineers working on advertising, recommendation, or sponsored‑search systems.

A collection of practical code samples and templates for building agentic workflows and AI solutions using Azure AI Foundry and Azure OpenAI Service.

A lightweight desktop application that lets Claude Desktop users manage and switch between third-party Anthropic-compatible API providers via a local gateway.

An engineering harness for Claude Code that adds multi-model routing, TDD enforcement, and isolated parallel agent execution to create a self-reviewing development system.

A Go implementation of the Model Context Protocol (MCP) SDK that enables seamless communication between external systems and AI applications.

A generic bash tool for AI agents that enables them to execute shell commands and manage files within a sandbox environment.

An AI agent development framework for Laravel that allows developers to create and maintain AI agents using an Eloquent-like API and Laravel-style tooling.

A Python LSP client library that provides a unified API to query static analysis results from multiple language servers to support AI-driven code generation and agents.

JanusVLN is a vision-language navigation framework that uses a dual implicit memory system to decouple and synergize semantic understanding and 3D spatial cognition for embodied agents.

A unified framework for benchmarking and implementing deep imitation learning algorithms like GAIL and RED using SAC as a base, tested on Gym MuJoCo environments.

A local, open-source tool for real-time audio transcription, translation, and OCR, designed for streaming overlays and in-game use.