Nav2 is the official ROS 2 navigation stack, offering localisation, path planning, obstacle avoidance, and docking for mobile robots. It’s modular, supports multiple ROS 2 releases, and is backed by a strong community and industry sponsors.

A remote Model Context Protocol (MCP) server that transforms any public GitHub repository into a documentation hub for AI assistants to reduce hallucinations.

An enterprise-grade open-source RPA desktop application that enables low-code automation of desktop software and web pages, featuring deep integration with AI agents.

A travel search skill for AI agents that connects them to Fliggy's real-time inventory for flights, hotels, and attractions via a CLI.

A local application for writing long-form fiction with AI that helps authors manage plot outlines, world-building knowledge, and narrative consistency across chapters.

UniRL is an open‑source Python framework that applies a unified reinforcement‑learning loop to many multimodal generative models (LLMs, vision‑language models, image/video diffusion, and hybrid AR‑diffusion models). It provides four entry points, Hydra‑based configs, pluggable rollout engines, and distributed training via Ray and FSDP. The repo ships standard RL algorithms plus three novel team‑proposed methods (Flow‑DPPO, DRPO, CPPO) with tutorials. Supported models include Stable Diffusion 3, FLUX.2‑Klein, Qwen‑3, HunyuanVideo, and more. Documentation, example recipes, and a WeChat community are provided. Licensed under Apache‑2.0.

A secure, persistent personal AI agent server written in Rust that runs on your own hardware and executes all agent commands in sandboxed containers.

A shared, cloud-backed memory system for AI coding agents that captures session traces and codifies them into reusable skills shared across a team.

A fast, private, local-first voice app for Apple Silicon Macs that provides system-wide dictation, media transcription, and meeting recording using on-device ASR engines.

A structured prompt generation tool for AI painting that turns complex prompts into a visual fill-in-the-blank interaction for easier management and iteration.

A unified control plane and gateway for AI assets, providing centralized discovery, governance, and secure access to MCP servers, agents, and model inference endpoints.

A Go SDK and model server for hardware-accelerated local inference of text, vision, audio, and image models without requiring Python.

An AI-enhanced RSS reader that provides automatic translation, summarization, and recommendations to streamline information consumption.

An MCP server that connects AI assistants to official Korean law APIs to provide real-time citation verification, precedent tracking, and legislative analysis while preventing LLM hallucinations.

Aether is a highly extensible, localized AI agent application for Android, iOS, and macOS that combines a polished UI with a powerful agent execution engine.

A local proxy server that transforms the Google Gemini web interface into a standardized REST API using browser cookies instead of API keys.

A synchronized, multi-client state protocol that allows multiple clients to maintain a consistent view of AI agent sessions via a standalone sessions server.

A self-hosted, open-source project management platform where AI agents and humans collaborate as equal teammates on a shared Scrumban board.

k7 is an open‑source platform that lets you run isolated VM sandboxes (via Kata, Firecracker, QEMU, or Katakate’s own k7d runtime) on Kubernetes. It targets AI agents needing to execute untrusted code at scale, offering fast warm‑forks, Docker‑in‑VM support, snapshotting, and optional Cilium network policies. Install via APT, manage sandboxes with the `k7` CLI or Python SDK, and control everything through an automatically deployed HTTPS API.

An AI-powered Rust development assistant that uses a meta-cognition framework to provide architecturally sound solutions instead of surface-level syntax fixes.

A collection of PyTorch-based tools for image super-resolution, 2D-to-3D video conversion for VR, and image quality assessment for dataset filtering.

A macOS voice input and translation app that provides live transcription, AI translation, and voice-prompted text rewriting across all applications.

Deltafin is a Rust‑based native binary that runs the full 2.8 T‑parameter Kimi K3 Mixture‑of‑Experts model on consumer hardware (macOS arm64 or Linux x86‑64/aarch64). It keeps all 16 experts, offers both full‑download and on‑demand streaming installations, optional Qwen draft‑model acceleration, a CLI for chat/completion, and an OpenAI‑compatible server. The project is MIT‑licensed, with model weights under their original terms.

UModel (Unified Model) is an open‑source, vendor‑neutral semantic runtime that unifies enterprise schemas, entities, and topology into a single graph. It offers a local service with a web UI, CLI, REST/OpenAPI, and generated Go/Python/Java SDKs. Agents can discover services, traverse relationships, and perform model‑guided root‑cause analysis via built‑in AgentGateway/MCP skills. Quick‑start uses `make quickstart` to launch a demo workspace; the system supports multiple GraphStore back‑ends and is licensed under Apache‑2.0.

An open-source PyTorch framework for physics and scientific machine learning that provides reusable components and training recipes for AI in science and engineering.

A real-time AI coding agent status panel for the macOS Dynamic Island that tracks sessions, tool calls, and permissions across 15 different AI tools.

A lightweight library for easy one-line loading and efficient pre-processing of massive multi-modal datasets for machine learning training and evaluation.

A high-performance, resource-efficient IDE that implements the Jupyter wire protocol to run notebooks with significantly lower CPU and RAM overhead than JupyterLab.

A professional data analysis skill for AI agents that prevents silent calculation errors in Excel by implementing a rigorous 8-step audit and reconciliation workflow.

TE MAN is a ComfyUI plugin that adds an infinite‑canvas workflow, asset library, audio/video/image nodes, 3‑D director, batch prompt tools, and an AI‑assistant chat panel, enabling both local model inference and remote API usage for image, video, and multimodal generation.

An end-to-end framework for training and serving omnimodal world models, including the Cosmos 3 family, designed to unify language, vision, audio, and action for Physical AI.

A reverse-engineering project that detects and removes Google's invisible SynthID watermarks from Gemini-generated images using spectral analysis and a multi-stage adversarial pipeline.

A GPU-accelerated suite of robot learning environments built with MuJoCo MJX, designed for efficient reinforcement learning and sim-to-real research.

A multi-modal world model framework that generates and reconstructs editable 3D assets (meshes and Gaussian Splattings) from text, images, or video for use in game engines.

AIWriteX is a Python‑based, multi‑agent AI writing suite for Chinese social‑media (WeChat, XiaoHongShu, etc.). It combines CrewAI agents, AIForge search, template‑driven visual design, AI‑generated images, anti‑detector polishing, and one‑click publishing. Available as a downloadable desktop app or a pip‑installable source tree, it’s licensed under Apache 2.0 with a non‑commercial add‑on.

A full-stack US and HK market data toolkit designed as a skill for AI coding assistants to fetch quotes, options Greeks, SEC filings, and macro data without API keys.

A Python library that converts scanned PDFs into editable Markdown or EPUB files using OCR and LLM-powered translation.

A Chromium side‑panel extension that connects your browser to a Hermes Agent (local, cloud, or remote). It streams active‑tab context, supports multi‑agent switching, smart tab scoping, site‑aware drafting (Hermes Assist), page comments, and optional live tab control, all with transparent diagnostics and nine visual themes.

A centralized registry and API for Model Context Protocol (MCP) servers, functioning as an app store for discovery and integration.

A Windows desktop assistant for League of Legends ARAM that provides champion selection advice and uses OCR to recommend builds based on in-game Hextech Augments.

A secure agent that connects private or localhost MCP servers to OpenAI-hosted products like ChatGPT and Codex without exposing them to the public internet.

HERO‑Anti‑OverDefense is a tiny copy‑and‑paste prompt block (with docs and real‑world examples) that you add to the config file of AI coding assistants (Claude Code, Copilot, Cursor, Gemini CLI, etc.). Its nine rules stop the model from over‑defending—adding unused hashes, guarding irrelevant edge cases, building exhaustive rubrics, or creating unnecessary scaffolding—so the assistant delivers the requested feature instead of a defensive fortress.

A desktop workspace that provides a unified GUI for Pi, OMP, and Prime Agent coding agents, integrating coding tools, a browser, and session management.

An open-source API and RSS generator for WeChat Official Accounts that enables full-content scraping, multi-format archiving, and AI client integration via MCP.

A collection of agent skills for financial analysis and trading that enables AI agents to perform valuations, market research, and data retrieval from professional financial sources.

A prompt library and agentic SDLC framework for GitHub Copilot that provides specialized agents, reusable prompts, and coding instructions to make AI-assisted development repeatable and scalable.

A one-stop AI digital human desktop application that integrates lip-syncing, voice cloning, and audio-visual tools for easy content creation.

A desktop application that translates books, subtitles, and documents using local or cloud LLMs while preserving original formatting and stylistic consistency.