A codebase knowledge graph tool that indexes structural dependencies and exposes them via a visual dashboard and MCP tools for AI agents.

An AI-powered job hunting assistant that automates resume submission and HR communication on Boss Zhipin using LLMs to act as a candidate's digital twin.

An open-source web application for AI model security assessments that uses probes to test for vulnerabilities and jailbreaks before deployment.

A graph deep learning library for materials science that provides various GNN architectures to predict material properties and simulate potential energy surfaces.

A free, lightweight desktop application that provides a unified interface for interacting with multiple LLM providers and local models using your own API keys.

A self-hosted universal LLM API proxy that provides OpenAI and Anthropic compatible endpoints for multiple providers with built-in key rotation and failover.

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

TAEHV is a tiny auto‑encoder that speeds up and memory‑optimizes video VAE decoding for many diffusion models (Hunyuan, MiniMax‑H3, Wan‑Video, CogVideoX, Open‑Sora, LTX‑2, etc.). It reduces decoding of a 61‑frame 512×320 clip from ~2‑3 s / 6‑9 GB to ~0.5 s / <0.5 GB, with a small quality trade‑off. The repo ships model checkpoints, Python API (`TAEHV`, `StreamingTAEHV`), example notebooks, and integration notes for ComfyUI, stable‑diffusion.cpp, SDNext, and Diffusers.

torch_musa is a PyTorch extension that adds a **MUSA** backend for Moore Threads GPUs. It mirrors the standard PyTorch API, so you only replace `cuda` with `musa`. The package includes tools for building C/C++ extensions, distributed training via the **mccl** backend, and Docker images for easy setup. It also provides MUSA‑compatible builds of torchvision, torchaudio, and a curated list of other popular PyTorch libraries. Installation can be done from pre‑built wheels or by building from source after installing the MUSA SDK. The project is BSD‑licensed.

A PyTorch implementation of Rectified Flow and its variants, enabling more efficient generative modeling by straightening the paths between noise and data.

AIDA is an open‑source autonomous pentesting platform that lets any LLM (Claude, Gemini, OpenAI, etc.) drive a Docker‑based security‑testing environment. The agent can run reconnaissance, scanning, custom Python exploits, and raw HTTP manipulations, logging every command and its output in a persistent notebook. Findings are auto‑scored with CVSS 4.0 and can be exported as PDF reports. The project includes a web dashboard, JWT authentication, notification hooks, and supports swapping the built‑in `aida-pentest` container for the larger Exegol image. Real CVEs discovered by AIDA are listed, showing practical impact. Licensed under AGPL‑v3.

A deployment framework for running a persistent, 24/7 Claude Code agent with a real browser on your own VPS, controllable via Telegram.

A library of optimized neural network kernels for Arm Cortex-M processors that maximizes performance and minimizes memory footprint for on-device AI.

A GPT-style humanoid motion Transformer pre-trained on 2 billion frames to enable zero-shot whole-body motion tracking for humanoid robots like the Unitree G1.

A community-driven project providing 79 specialized AI agents across multiple platforms to automate accessibility auditing and enforce WCAG AA standards in code and documents.

A collection of ~100 specialized skills for Claude Code that automate complex workflows across development, research, media generation, and personal analytics.

A library for creating pixel-based gridworld environments where large numbers of agents interact in competitive scenarios to study collective intelligence.

A lightweight background daemon that connects local AI agents to Telegram and WeChat, allowing users to to monitor and control agents remotely via mobile notifications.

An open-source agent development kit that integrates Volcengine capabilities to simplify the building, deployment, and management of AI agents.

A universal environment framework that runs AI agents against task environments and scores them through a standardized contract, treating benchmarks as frozen environments.

A suite of developer primitives using the Model Context Protocol (MCP) to integrate Tableau's data and analytics into AI applications.

A local AI music generation studio that creates full songs with vocals, lyrics, and music videos using the ACE-Step 1.5 XL model.

A diffusion-based framework for high-quality singing voice synthesis and text-to-speech generation from lyrics, MIDI, and pitch data.

An HTTP(S) mock server and proxy for testing that simulates API dependencies, records traffic, and provides specialized mocking for AI/LLM chat-completion APIs.

A cross-platform spatial perception SDK for ZED cameras that provides real-time depth sensing, object detection, and positional tracking.

A PyTorch-based library for time series forecasting that provides a high-level API and state-of-the-art deep learning architectures like Temporal Fusion Transformers and N-BEATS.

A set of libraries for logging and visualizing multimodal robotics data via streaming or MCAP files, with support for Python, C++, Rust, and ROS.

A lightweight macOS menubar app that tracks Claude Code usage limits and provides notifications when AI agent sessions need user attention.

Open-RMF is a multi-fleet robot management platform that allows robots from different vendors to coordinate and operate together in the same environment.

A lightweight web-based visualization tool for ROS1 and ROS2 that allows users to monitor robot topics and data via a browser on any device.

An MCP server that connects AI agents and coding assistants to Postman workspaces, collections, and specifications to automate API testing and client code generation.

A Discord bot that transforms servers into collaborative LLM frontends, using Discord's reply chains to manage conversation history without a database.

A self-hostable framework for creating proactive, multimodal personal AI assistants that feature long-term memory, persona tracking, and autonomous planning.

An ultra-fast neural video codec that uses a chunk-based coding framework to achieve high compression efficiency and rapid encoding/decoding speeds.

An extension for ComfyUI's WanVideo pipeline that enables seamless video connection and multi-reference image injection for improved consistency in AI video generation.

VoiceBench is a benchmark suite for evaluating LLM‑based voice assistants. It supplies a Hugging‑Face dataset with audio‑driven QA and instruction‑following tasks, a command‑line toolkit to run a model, collect spoken responses, and automatically score them (via GPT‑4o‑mini for open‑ended sets). Results are posted on a public leaderboard, and the repo includes a curated list of recent voice‑assistant papers.

A DuckDB extension that integrates LLMs and RAG pipelines into SQL, enabling multimodal semantic analysis and analytics directly within the database.

A PyTorch-based library for training Generative Flow Networks (GFlowNets) to sample diverse, high-reward objects, primarily for applications in scientific discovery.

A CLI skill manager for AI coding agents that allows users to install, update, and sync portable prompt packages across tools like Claude Code, Cursor, and Copilot.

A framework for the symbolic distillation of deep neural networks, using PySR to approximate model components with symbolic equations for better interpretability.

An AI-powered penetration testing tool that uses autonomous agents to perform blackbox and whitebox security audits directly from the terminal.

A lightweight, ROS-agnostic planning framework for robotics that provides tools for kinematics, collision checking, and environment management.

A tool for integrating safe runtime monitors into systems like NASA's Core Flight System and ROS, automating the generation of real-time C99 glue code.

A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products and enterprise resources.

A serverless, AI-powered personal bookmarking system that uses RAG for automatic summarization and tagging across web, mobile, and browser extensions.

A lightweight CLI tool that reduces AI token costs by filtering CLI output and compressing file content before it reaches an AI agent.

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.

An AI fitness assistant that uses RTMPose for real-time pose detection and automatic exercise repetition counting via a webcam.