Trending AI projects

ComfyUI‑RMBG is a set of custom nodes for the ComfyUI visual‑programming tool that bring advanced background removal and object/face/fashion segmentation using many state‑of‑the‑art vision models (RMBG‑2.0, SAM/SAM2/SAM3, Grounding‑DINO, BiRefNet, etc.). It offers prompt‑driven segmentation, VRAM‑unload toggles, real‑time background replacement, and many utility nodes, with easy installation via ComfyUI‑Manager, git clone, or comfy‑cli, and automatic model downloading.

The open-source platform for sharing and collaborating on Stable Diffusion models, featuring a community-driven repository for model discovery and development.

A GUI for dispatching multiple AI coding agents in parallel, using git worktrees to isolate each task into its own branch and directory for conflict-free development.

A local-first workbench for managing and distributing AI prompts, skills, and programming rules across multiple AI coding tools like Cursor and Claude Code.

taOS is a self-hosted AI agent platform that turns spare hardware (laptops, Pis, gaming PCs, phones) into a private distributed compute cluster. It offers a full web desktop environment, framework-agnostic agents, a self-hosted memory system (taOSmd), and large app/model catalogs—all offline-first with cloud as an opt-in. It's beta software with some rough edges and untested install manifests.

SDV (Synthetic Data Vault) is a production‑ready Python library for generating realistic tabular synthetic data. It offers a range of ML models (copulas, GANs), handles preprocessing, anonymisation, and relational constraints, and provides built‑in evaluation and visualisation tools.

A versatile model serving library that simplifies the deployment of language, speech, and multimodal models across heterogeneous hardware.

Hermes Skins is a collection of YAML-based visual themes for the Hermes CLI agent, letting users customize colors, spinner animations, branding, and ASCII art without altering the agent's behavior. It includes over a dozen curated skins and supports creating your own by dropping a YAML file into the skins directory.

This repository contains the lecture slides, lab materials, and practical code demonstrations for the University of Michigan's Applied Agentic Software Engineering course.

Tamery is an open-source AI-powered database client and MCP server for desktop and web, supporting many popular databases. It provides a fast, simple interface with an AI assistant, schema visualization, and safe agent access, while keeping your data secure and never changing anything without your approval.

A library of plugins that enables AI coding agents to perform specialized tasks across the Adobe ecosystem, including analytics reporting, AEM development, and App Builder project management.

LinguaHaru is a versatile AI translation tool that supports documents, images, video, and live speech through a unified, plugin-based engine. It features a crash-safe design, layout preservation, and portable deployment options for both desktop and web.

LeWAM is an end-to-end framework for world and action modeling using JEPAs, enabling autonomous agents to perform goal-conditioned visual planning and task completion in simulated environments.

A local chat analysis tool that uses AI to interpret emotional intent, grade your responses, and provide feedback on romantic conversations.

Claude Unlimited is a local daemon that pools multiple AI subscriptions and API keys into a single, continuous session, automatically rotating accounts when usage limits are reached to prevent interruptions.

A Python-based simulation environment for marine vehicles that provides models for AUVs, USVs, and ships to test guidance, navigation, and control systems.

Mobile Harness is a Python‑based, Markdown‑driven library that lets LLM agents control Android and iOS devices (locally via ADB/Portal or remotely via Mobilerun cloud). It offers a unified API for UI interaction, screenshots, app launch, and accessibility‑tree queries, and includes benchmarks showing near‑perfect performance on AndroidWorld and iOSWorld task suites.

A high-performance Mixture-of-Experts (MoE) implementation optimized for NVIDIA Hopper and Blackwell GPUs to reduce memory usage and increase training throughput.

A utility to synchronize provider metadata in Codex session files and SQLite indices, allowing old chat sessions to remain usable after switching AI providers.

A Windows-based input tool that provides a staging area for drafting, editing, and translating text with AI assistance before sending it to your active applications.

Gorest is a Node‑based, browser‑run editor that lets you build 2‑D game scenes, generate or import spritesheets, attach rich metadata, and preview animations—all with optional Codex‑driven prompts. It stores assets locally and includes a fake‑3D rotator for turntable‑style sprites.

A parallel programming interface that provides a partitioned global address space across NVIDIA GPU clusters for efficient GPU-initiated communication.

API Relay Audit is a zero‑dependency Python CLI that locally tests third‑party AI API relays (LLM proxies) for hidden prompt injection, context truncation, model substitution, stream anomalies, and Web3‑wallet safety, outputting a structured Markdown or JSON risk report.

Aixora Audio is a Windows‑focused, all‑in‑one desktop UI that runs open‑source speech‑synthesis, transcription, translation, dubbing, real‑time voice chat and other audio tools locally via a compiled C++ inference backend (audio.cpp). It supports CUDA, Vulkan or CPU, offers a large catalog of models, and provides a portable package plus source‑build instructions.

An end-to-end solution for creating digital avatars by fine-tuning LLMs on exported chat history, featuring data preprocessing, privacy filtering, and multimodal support.

An intelligent customer service agent for robot vacuum users that combines Agentic RAG and device data analysis to provide technical support and personalized usage reports.

IFClite is an open‑source, Rust‑powered toolkit (exposed via npm packages, a CLI and a WebGPU viewer) for parsing, querying, editing, validating, rendering and exporting IFC building‑information models. It supports IFC2X3, IFC4/4X3 and IFC5, offers exact‑arithmetic geometry, streaming first‑render, and integrations for Three.js, Babylon.js, Python, and AI agents.

RemCTL is a macOS‑only tool that lets you manage Apple Reminders from the terminal, scripts, and AI assistants (Claude Code, Codex, etc.) via a signed background host and an MCP server. It supports full reminder features—including private Apple APIs—offers CLI commands, AI‑ready tools, and plugins that embed a Reminders workspace inside Claude Code and Codex.

A research-oriented, differentiable rendering system for forward and inverse light transport simulation with deep Python integration.

OmicVerse is a Python library that unifies bulk RNA‑seq, single‑cell, and spatial transcriptomics analysis. It bundles dozens of established bio‑informatics tools, standardises on the anndata/mudata data structures, and adds AI‑assisted agents (J.A.R.V.I.S.) and an MCP server so you can run pipelines via natural‑language commands or LLM integration. Optional extensions provide synthetic‑biology modelling and GPU‑accelerated molecular‑dynamics workflows.

A learning system plugin for AI agents that turns your assistant into a tutor and examiner to ensure you actually retain the information it explains.

Keeper.sh is an open‑source calendar‑sync platform with API and MCP server support, enabling AI agents to manage multiple calendars. It syncs Google, Outlook, iCloud, Fastmail, CalDAV and public iCal/ICS sources, offers privacy filters, and can be self‑hosted or used as a SaaS.

A transport proxy for the Model Context Protocol (MCP) that enables communication between clients and servers by converting between stdio and SSE/StreamableHTTP transports.

A versatile framework for scaling the pre-training and post-training of single- and multi-modal models across various hardware accelerators.

An AI-powered visual asset generator for e-commerce that uses 39 scene templates and technical pre-checks to create professional, platform-compliant product images.

A personalized diet management platform that uses LLMs, RAG, and multimodal AI to provide intelligent meal planning, nutritional tracking, and recipe recommendations.

A world model that generates real-time, photorealistic multi-camera video for autonomous driving simulation using HD maps and trajectory poses.

A set of AI-optimized skills and an MCP server that provides AI coding assistants with version-aware PostgreSQL documentation and best practices to improve generated SQL code.

AI Factory is an npm CLI that instantly equips a codebase with AI coding agents and pre‑built prompt “skills”. After `ai-factory init` it configures agents (Claude, Codex, Gemini, etc.), installs community‑sourced skills, and provides slash‑command workflows (/aif‑plan, /aif‑implement, /aif‑fix, …) to research, plan, implement, and document features with AI‑generated commits and quality‑gate reports.

WorldSculpt is a research codebase that converts multi‑view RGB video (with instance masks and 3D boxes) into a single compositional mesh for scenes containing hundreds of objects. It fine‑tunes the Pixal3D single‑object prior, provides a new UE‑MeshyScene benchmark, releases checkpoints and data on Hugging Face, and includes a community ComfyUI integration.

Foam-Agent is an AI-driven framework that automates OpenFOAM CFD simulations from natural language prompts or existing cases, using multiple agents, RAG, and error correction. It offers Docker setup, MCP integration, and configurable models, with reported benchmark success but no guarantees.

A Python and TypeScript library for creating evaluations for LLM applications, featuring LLM-as-judge capabilities and prebuilt prompts for quality, safety, and RAG.

vLLM Router is a high-performance, lightweight request-forwarding system for vLLM large-scale deployments. It provides advanced load balancing methods and prefill/decode disaggregation to keep LLM inference fast and efficient.

A Model Context Protocol (MCP) server that provides a universal memory layer, allowing users to carry their personal memories and context across different LLMs and AI clients.

An open-source website data extraction platform that converts public pages into cleaned markdown and hierarchical link trees for AI agents.

A solution accelerator for Databricks that ingests, indexes, and analyzes medical DICOM images, enabling AI-powered segmentation and secure, SQL-based research workflows.

An iOS and macOS Markdown renderer optimized for LLM streaming, providing smooth transitions, LaTeX support, and inline citation UI.

An interactive browser UI for AI brainstorming that replaces terminal typing with visual inputs and parallel exploration branches.