A macOS CLI tool for on-device speech transcription of files, live system audio, and microphone input using Apple's Speech.framework.

A full-stack SaaS boilerplate using Fastify, React, and tRPC that provides a pre-configured foundation for building AI-powered web applications with OpenAI integration.

Flounder is an open‑source framework that lets LLM coding agents run autonomous, sandboxed security audits. Given a repo, contract address, transaction hash, or similar clue, it prepares a workspace, maps the attack surface, lets the model write and execute PoC tests in an OCI sandbox, verifies findings locally, optionally confirms them against a real target, and generates markdown reports. It supports many scenarios (blind audits, incident investigations, bug‑bounty work) and works with various model providers via a daemon‑based control plane.

A GUI and packaging tool for ByteDance's piano transcription system that converts piano audio and video recordings into MIDI files with pedal data.

PlateRecognition is an open‑source, multi‑region licence‑plate detection and OCR system built on YOLO‑v5/v7/v8 and TensorRT. It runs on desktops, servers, Android/iOS and many edge AI chips, delivering >99 % accuracy with sub‑50 ms latency on modern hardware. The project provides C/C++ and Python APIs, supports many languages, and includes a web demo and test code.

A centralized guardrail system for AI agents that enforces runtime safety rules to block prompt injections and PII leaks without changing agent code.

A Neo4j plugin that enables the lossless import, export, and validation of RDF data, bridging the system between W3C semantic web standards and property graphs.

Guitarix is a Linux‑only, modular virtual guitar amp that combines classic DSP effects with AI‑based amp models (Neural Amp Modeler and RTNeural). It runs as a standalone app, VST3, or LV2 plugins, can be controlled via MIDI, and even operates headless on devices like a Raspberry Pi. The README provides build steps, dependencies, and links to documentation and a Docker‑based container for optimized deployment.

A GPU-accelerated GTO poker solver that uses a DCFR engine to calculate equilibrium strategies with advanced analysis tools for blockers and runouts.

BCPD is a MATLAB‑compatible, command‑line suite for Bayesian non‑rigid registration of point clouds and functions (DET), with accelerated “++” modes, multiple kernel options, and demos for 3‑D reconstruction, shape transfer, and spatial‑omics data.

A portable Markdown instruction pack that transforms AI coding assistants into disciplined multi-agent workflows with planning, self-review, and persistent memory.

An AI-powered cybersecurity tool that automates threat data analysis, CVE exploit creation, and bug fixing in JIRA tickets.

DIPY is a Python library designed for the analysis of MR diffusion imaging, providing researchers with tools to process medical imaging data.

HIPIFY provides command‑line tools (primarily `hipify-clang`) that automatically translate CUDA C++ code into portable HIP code, enabling the same source to run on AMD and NVIDIA GPUs. It also can generate Markdown or CSV documentation of the supported CUDA‑to‑HIP API mappings.

A Python library for processing and gridding spatial data using a machine-learning-inspired interface similar to scikit-learn.

A Rust-native GPU memory allocator that provides a unified interface for managing memory across Vulkan, DirectX 12, and Metal.

A robotics library for detecting loop closures in mapping by using point cloud density maps to improve map accuracy and reduce drift.

The official Python SDK for Vulners, providing programmatic access to a vulnerability intelligence graph to prioritize security fixes and audit software assets.

A Python library for reading, exporting, and visualizing geospatial embeddings from the Tessera Earth foundation model, supporting both cloud-native streaming and local tile downloads.

A ROS2-based control, estimation, and simulation system for multirotor helicopters designed for reproducible robotics research and real-world deployment.

A collection of Claude Code skills that provide multi-agent academic reviews for research papers, grant proposals, and pre-analysis plans, including paper-code reproducibility checks.

A modular sim racing administration tool that provides AI-powered race assistants, telemetry analysis, and hardware automation to help drivers manage races and strategy.

A library of foundational algorithms and numerical optimization solvers for human kinematic motion and body tracking.

ComfyUI‑Apt_Preset is a plugin for the visual AI workflow tool ComfyUI. It bundles loading, control‑net, and sampling steps into preset‑driven nodes, offering universal loaders for many model families, controller stacks for video/animation/control‑net, combined sampler nodes, and utility image/mask tools. Install by cloning into `custom_nodes` and running `install.bat`; optional companion plugins and a resource pack add extra features. The plugin streamlines complex image‑generation graphs, making them easier to build and maintain.

An agentic crypto trading stack that uses a multi-agent LangGraph workflow and a strict Risk Guard veto system to implement hedge-fund-style trading discipline.

A desktop app that bridges AI subscriptions like Claude, ChatGPT, and GitHub Copilot to any OpenAI-compatible coding tool via a local proxy.

A unified Julia interface that brings together numerous local and global optimization packages into a single API, featuring integration with automatic differentiation.

An IO-aware, batched K-Means clustering implementation using Triton GPU kernels that enables fast, memory-efficient clustering of massive and high-dimensional datasets.

An AI architecture and code intelligence platform that catches code defects and business-logic drift by combining static analysis with LLM-generated scenario tests bound to documentation.

An open-source atomistic simulation engine built in PyTorch that accelerates Machine Learning Interatomic Potentials (MLIPs) through automatic batching and GPU acceleration.

A lightweight UI agent that enables cross-platform automation and UI testing using natural language instructions instead of scripts.

An image-generation model based on Kuramoto dynamics that generates images by integrating coupled oscillators instead of using diffusion or iterative denoising.

An AI-powered Obsidian plugin that transforms LLM-generated insights into a persistent knowledge base by automatically creating wiki-links, concept notes, and diagrams directly in your vault.

An AI-native infrastructure that uses a universal metadata standard to enable the instant generation of enterprise software from text descriptions.

A JAX-based library for probabilistic state space models that provides tools for inference and learning across various model types like HMMs and Gaussian SSMs.

A dimensionality reduction method for visualization that preserves both the local and global structure of high-dimensional data.

A Python framework for building distributed video and stream processing pipelines that can run locally or on Kubernetes using NATS JetStream.

A high-performance analysis engine for Oxford Nanopore reads that provides GPU-accelerated basecalling, alignment, and error correction for genomic data.

An open-source map data conflation tool that uses machine learning to merge multiple geospatial datasets into a single seamless map.

A GPU-driven communication stack that provides customizable, 0-copy inter-GPU communication primitives to improve performance for scalable AI applications and LLM serving.

A monorepo providing a workflow to generate presentation content and convert HTML previews into editable PowerPoint or bento slides using AI agents.

An open-source signal processing machine learning toolkit based on PyTorch that simplifies the creation, augmentation, and transformation of RF signals for ML research.

Mega-ASR is a foundation ASR model designed for robust speech recognition in challenging real-world environments by scaling up acoustic simulations of noise, echo, and distortion.

A local visualization toolkit for AgentScope developers to develop, debug, and evaluate agent-based applications through real-time interaction and tracing.

A Python MCP server that exposes Yahoo Finance data (prices, statements, options, news, holders, analyst ratings) as typed tools for LLMs like Claude, enabling AI‑driven stock and market research.

An on-device Android AI agent that runs a Node.js runtime to autonomously manage phone controls, Solana crypto trading, and paid API payments within user-defined caps.

A deep-research agent written in Go that provides verifiable claims with verbatim quotes, enforced spending budgets, and privacy-preserving local data analysis.

A framework for training any-to-any multimodal foundation models that uses tokenization and masked modeling to scale across tens of modalities and tasks.