A Rust-based terminal coding agent that provides interactive chat, shell command debugging, and an OpenAI-compatible HTTP server for AI-assisted development.

FPO++ Code Release provides reproducible RL experiments for robot locomotion (Isaac Lab) and dexterous manipulation (LeRobot/robosuite). It includes setup scripts, training commands, and expected results for the Flow Policy Optimization algorithm, with all dependencies managed via per‑experiment conda environments.

Argus is a persistent autonomy framework for research and engineering that uses a multi-role architecture to enable long-running AI agent work with minimal human intervention.

A Zotero plugin that uses Tesseract OCR to add a searchable text layer to scanned PDFs within a Zotero library.

A local-first AI conversation memory and knowledge hub that captures interactions across multiple AI platforms to create a searchable, interconnected personal knowledge base.

A simple, compact Python-based chess engine that serves as a platform for experimenting with search algorithms and neural network evaluations.

A voice-to-text utility for Apple Silicon Macs that transcribes speech on-device and pastes the result into any active application.

An agent-first local web debugging runtime that provides a unified timeline of server logs, browser errors, and network activity for AI coding agents.

A workflow orchestration system for Pi that enables the execution of repeatable, multi-step AI agent workflows for tasks like research and code review.

A collection of example programs and libraries for MLX Swift, demonstrating how to build LLM, VLM, and image generation apps on iOS and macOS.

A family of medical multimodal large language models that unify medical text, 2D images, and 3D volumes for advanced healthcare comprehension and generation.

An open-source platform for generating secure full-stack apps and AI agents from natural language, featuring a compiled runtime and built-in MCP server for self-hosted deployment.

A set of tools for Mistral AI models that provides open-source tokenizers and Pydantic-based validation for text, images, and audio.

An open framework for confidential AI that allows deploying AI applications in hardware-isolated confidential VMs with cryptographic privacy guarantees.

A self-hosted family office engine that combines a Python analysis engine with AI agent skills to manage and analyze financial portfolios locally.

A local-first AI filmmaking workspace that integrates coding agents with a visual canvas and a unified API for generating images, video, and voice.

A machine learning runtime written in Rust that enables the execution of ONNX models trained in Python on various platforms, including WebAssembly.

A high-fidelity digital twin project for Unitree Go2 and G1 robots in Nvidia Isaac Sim, enabling real-time synchronization between physical robots and their virtual counterparts.

RHVoice is an open-source speech synthesizer that uses statistical parametric synthesis to provide lightweight, intelligible text-to-speech across multiple languages and platforms.

A lightweight Go-based gateway that transforms existing APIs and MCP servers into MCP-compliant endpoints via configuration without requiring code changes.

A Prometheus exporter that collects NVIDIA GPU metrics using nvidia-smi or NVML, supporting Linux, Windows, and macOS.

A Python package for fast and robust image stitching that creates panoramas from overlapping images using OpenCV.

A collection of over 100 PyTorch metrics implementations that automate accumulation and synchronization across distributed devices to reduce boilerplate in ML pipelines.

Rust bindings for the PyTorch C++ API (libtorch), enabling the use of PyTorch's tensor operations and deep learning tools in Rust.

A machine learning experiment tracking and visualization platform that helps developers monitor hyperparameters and metrics across the entire ML pipeline.

A PostgreSQL extension for high-performance, cost-effective vector search that enables billion-scale vector hosting on modest hardware using RaBitQ compression.

A native desktop environment for agentic development that organizes terminals, code, and context files on an infinite spatial canvas to reduce context switching.

A tool that converts YouTube videos into structured archival Markdown notes, capturing transcripts and metadata for use in knowledge bases like Obsidian.

An AI-native data analysis platform that uses LLMs to allow users to explore, query, and visualize data from multiple sources via natural language conversations.

An open-source library for 6 dof tracking on Lighthouse and Vive-based systems, enabling hardware to work independently of SteamVR.

AllData is a comprehensive data middle-platform that provides an end-to-end suite for data integration, storage, governance, and AI application development.

An AI-native SecOps platform that uses multi-agent collaboration and a rich toolset to automate security operations tasks.

An open-source deception runtime that deploys LLM-powered decoy services across multiple protocols to collect threat intelligence and detect prompt injection attacks against AI agents.

An image processing development platform for Espressif chips that provides examples for face and pedestrian detection and QR code recognition.

An enhanced version of Ragflow tailored for industry applications in Chinese contexts, adding administrative management, improved document parsing via MinerU, and multimodal output.

A Python package for text normalization and inverse text normalization, used to prepare text for speech processing systems.

A Thunderbird add-on that integrates LLMs to help users analyze, write, summarize, and automatically organize their emails directly within the mailbox.

An asynchronous FastAPI-based RAG API that uses pgvector or MongoDB to provide ID-based document indexing and retrieval with built-in ownership security.

xLSTM is a novel recurrent neural‑network architecture that extends LSTM with exponential gating and a matrix memory, enabling large‑scale language models (e.g., a 7 B‑parameter model). The repo provides PyTorch code, custom CUDA/Triton kernels (via the `mlstm_kernels` package), a single‑file 7B implementation, configuration utilities, and pretrained weights on Hugging Face. Installation is via conda + pip, and the library works on NVIDIA GPUs (fast Triton kernels) with fallbacks for AMD or Apple Silicon.

A lightweight Python library for efficient automated machine learning (AutoML) and hyperparameter tuning to find high-quality models with minimal computational resources.

A macOS utility that monitors Claude AI usage limits in real time via the menu bar, desktop widgets, and a floating overlay for Claude Code sessions.

HappyClaw is a self‑hosted platform that runs Anthropic Claude Code agents as long‑living, multi‑user services. It wraps the Claude Agent SDK (TypeScript) and Claude Code CLI, offering web‑based and eight instant‑messaging channel interfaces, isolated workspaces (host or Docker), full Claude Code capabilities (file access, shell, browser, plugins), scheduling, usage tracking, and enterprise‑grade RBAC and backup.

An adversarial AI-agent skill for code review and security auditing that uses a Hunter-Skeptic-Referee pipeline to eliminate false positives.

A benchmark and baseline agent for assessing the ability of LLMs to perform root cause analysis by analyzing telemetry data like logs, metrics, and traces.

An AI assistant for reMarkable tablets that captures handwritten input via screenshots and responds by drawing or typing directly back onto the screen.

A series of ultra-efficient reasoning models (1.5B and 3B parameters) that achieve frontier-level performance in math and coding through a Spectrum-to-Signal post-training methodology.

An AI workstation that enables autonomous AI agents to operate a local browser, terminal, and knowledge base to automate complex workflows 24/7.

A lightweight multimodal LLM inference engine optimized for mobile and edge devices, supporting various NPUs and GPUs with advanced quantization.