Trending AI projects

A Java SDK for the Model Context Protocol that enables Java applications to interact with AI models and tools through a standardized, interoperable interface.

A comprehensive, tutorial-driven project that demonstrates how to build an AI-powered data analysis agent using LangGraph, FastAPI, and hybrid search to translate natural language into accurate SQL queries.

An AI-driven cultivation world simulator where every NPC is an independent LLM agent, creating an emergent narrative based on a rigorous set of cultivation rules.

UnitySkills is an open‑source Unity plug‑in that exposes 839 REST‑based “Skills” for AI assistants to read and modify Unity projects. It offers a three‑tier permission system, dry‑run previews, transactional batch calls, audit logs, and per‑skill rollback snapshots. The plug‑in integrates with major AI coding terminals (Claude Code, Antigravity, Codex, Cursor, Kimi Code, OpenCode) via one‑click installers, enabling safe, automated editor workflows.

GPTaku Plugins is a collection of 19 open‑source extensions for Anthropic’s Claude Code IDE. They let you bypass blocked web pages, extract design tokens, get code reviews from a stronger model, generate full product specs, and more—all without leaving the Claude Code session. Installation is done via Claude Code’s `/plugin marketplace add …` command, and most plugins need no extra API keys; a few (Google Workspace, ChatGPT‑Pro review, Codex CLI) require a one‑time credential setup. The suite is MIT‑licensed and aimed at removing the practical “walls” developers hit when building with AI.

A Markdown‑based “skill” that plugs into AI coding assistants (Claude Code, Copilot, Gemini, etc.) to teach them Home Assistant best‑practice patterns for automations, dashboards, backups, AppDaemon, and more. Install via `npx skills add …` or Claude Code’s plugin marketplace; the assistant then automatically applies the guidance when generating Home Assistant configuration.

Toolcraft is a free, MIT‑licensed starter kit that combines React, Tailwind, and a ready‑made canvas/UI library to let AI coding agents (Codex, Claude, Cursor, etc.) generate custom web‑based design tools in minutes.

A native mobile frontend for LLMs that allows users to run models locally on-device or connect to various commercial and open-source APIs.

An 8B-scale vision-language interaction model and system that enables AI to proactively respond to real-time video streams in under a second without waiting for user prompts.

A network traffic capture and analysis tool that uses AI to automate protocol reverse engineering and API documentation from browsers, apps, and devices.

A cross-platform C/C++ SDK and framework for building AI-agent hardware that integrates embedded devices with multimodal AI and leading LLMs via Tuya Cloud.

TypeTale (字字动画) is a Windows‑only AIGC creation tool that lets creators generate novels, short dramas, and AI movies end‑to‑end. It integrates LLMs, image generators (Stable Diffusion, Midjourney, etc.), video models (ComfyUI‑based), and TTS engines, offers a visual workflow editor, a conversational AI assistant, and a plugin system for Python/ComfyUI extensions. The core features are free forever, and the app can run locally or connect to cloud AI services.

A cycle-level simulator for LLM inference infrastructure that models heterogeneous hardware, disaggregated memory, and advanced serving techniques to predict performance before deployment.

An MCP server that allows AI assistants to control SideFX Houdini via its Python API to build networks, run simulations, and manage renders.

A model-agnostic agent-skills platform that provides a marketplace of thousands of plugins and skills to extend the capabilities of AI agents.

A PostgreSQL extension that lets you filter, rank, and classify table rows using plain-language conditions, judged by an AI model that returns calibrated probabilities — no embeddings or vector columns needed.

AIOMetadata is a Stremio metadata addon that aggregates and enriches movie, series, and anime metadata from multiple sources, giving users full control over catalogs, artwork, and search. It solves the problem of limited default metadata by providing deep customization, anime power, and self-hosting options.

GSM is a tool that automates the creation of language-learning flashcards by capturing game audio, screenshots, and text directly while you play.

LLM-RL-Visualized is a bilingual, diagram-heavy educational repository with 100+ original architecture diagrams explaining large language models, reinforcement learning, and related training techniques — organized into 11 topic sections with high-res SVG/PNG images and bonus PDFs.

A large-scale evaluation framework for assessing AI agents' ability to perform real-world vulnerability analysis and Proof-of-Concept exploit generation.

A remote access gateway and visualization interface that lets you manage local AI agent CLIs and workstation data from any device via a web browser.

Pi MCP Adapter is a Pi‑agent plugin that replaces Pi’s built‑in MCP support with a lightweight proxy. It launches MCP servers only when needed, caches tool metadata, reduces token and memory usage, stores OAuth tokens securely, and adds semantic tool search and UI features.

A research codebase that implements Context Language Models—LLMs that treat their context as a mutable file, allowing dynamic read/write updates. Built on the Harbor framework, it includes zero‑shot, in‑context learning, and RL pipelines, plus tools for efficient serving and integration with benchmarks like ContextBench.

A high-performance gradient boosting library for decision trees that provides native support for categorical features and fast prediction speeds.

Docker Agent is a Docker CLI plugin that lets you declaratively define, run, and share AI agents (single or multi‑agent) via YAML. It supports many LLM providers, a plug‑in tool ecosystem (including MCP services), RAG retrieval, and can be packaged as OCI images for easy distribution.

PulseLoop is an open‑source iOS health app that connects via BLE to cheap smart rings, stores raw metrics locally, and adds an optional LLM‑powered “AI Coach” that can analyse the data, generate charts, answer questions, and even accept images. It aims to replace expensive subscription wearables with a $20 ring + on‑device intelligence.

Thunderbird MCP is a Thunderbird add‑on plus a Node.js bridge that exposes about 40 mail‑related tools (search, read, compose, filter, contacts, calendar) over the Model‑Context‑Protocol, enabling local AI assistants to work with your mailbox while staying on‑device and safe.

An iterative video editor for macOS that uses AI agents to write and load custom panels, effects, and workflows into the running application in real-time.

NeMo RL is an open-source post-training library for scalable reinforcement learning of large multimodal models (LLMs, VLMs). It provides algorithms like GRPO, DAPO, and SFT, with flexible backends for distributed training and generation.

ZML is an open‑source inference framework written in Zig that compiles AI models (including LLMs) to run at native speed on NVIDIA, AMD, Intel, TPU, and AWS Trainium hardware. It uses Bazel/MLIR for builds, offers a unified model‑loading VFS, and provides ready‑to‑run examples (MNIST, LLMs) with simple platform flags.

A collection of 31 verified AI agent skills for Unreal Engine 5.8 C++ development, ensuring AI coding agents produce production-quality, up-to-date code.

A curated directory of AI tools, frameworks, and datasets designed to accelerate scientific research, covering everything from literature management and document parsing to autonomous research agents.

A comprehensive software stack for Tenstorrent AI hardware, providing both high-level neural network libraries and low-level kernel programming tools to optimize and run large-scale models.

Spice.ai is an open‑source Rust runtime that federates >30 data sources, optionally materialises them for sub‑millisecond SQL queries, adds built‑in vector/full‑text search, and provides OpenAI‑compatible LLM endpoints—all via standard APIs (HTTP, Arrow Flight, JDBC/ODBC). It offers real‑time CDC replicas for PostgreSQL/MySQL/MongoDB, a distributed query engine (Ballista), and a Vortex‑based acceleration engine (Cayenne). Ideal for building data‑grounded AI apps, agents, and analytics without custom pipelines.

An AI Agent Skill that organizes Ni Haisha's TCM courses into a searchable, traceable knowledge base with screenshot and PDF evidence for learning and theory organization.

An invisible AI desktop overlay that provides real-time transcription and grounded answers during live calls and tasks, remaining hidden from screen shares.

An AI agent harness designed for authorized penetration testing and bug bounty research, featuring a multi-provider LLM engine and a built-in security toolset.

Project AirSim is an open‑source simulation platform for autonomous drones, aircraft, and ground vehicles. It can run headlessly (no Unreal) or inside Unreal Engine 5 for full 3D worlds and rendered sensors. Features include multiple physics back‑ends (Fast, JSBSim, Simulink), support for PX4/ArduPilot SITL/HITL, a rich sensor suite (cameras, LiDAR, radar, IMU, GPS, etc.), Python/C++/ROS 2 APIs, and multi‑vehicle/swarm capabilities. The project is maintained by IAMAI Consulting, builds on Microsoft’s AirSim code, and is MIT‑licensed.

hcom is a CLI/TUI tool that lets multiple AI coding assistants (Claude, Gemini, Codex, etc.) run in separate terminals, exchange messages, observe each other's activity, and be orchestrated (spawn, fork, kill) across local or remote machines via an MQTT relay.

A Python framework and Rust-based engine for stateful event and stream processing, enabling real-time data pipelines and online machine learning.

A private network for AI agents that enables secure discovery and calling of tools and models across distributed devices and environments.

Pulse is a free, open-source macOS app that monitors usage limits for 77 AI coding tools (Claude Code, Codex, Cursor, etc.), showing live quota status as colored rings on a floating screen-edge rail, with optional forecasting, token-spend analytics, and menu bar integration.

A plugin for Claude Code and Codex that implements a rigorous engineering framework for coding agents, emphasizing verification, multi-model review, and structured workflows.

An AI teammate for Slack that captures organizational knowledge from conversations and tools to answer questions, perform tasks, and proactively assist teams.

An MCP server that enables AI models to automate SolidWorks CAD tasks by translating high-level design intent into a deterministic compiler for 3D modeling and 2D drawing reconstruction.

AuK is a 1.5 B‑parameter open‑source foundation model for speech generation, editing, enhancement, and separation. It works via natural‑language prompts, offers a high‑quality base checkpoint and a fast 4‑step distilled variant (AuK‑Flash), and provides CLI, Python API, Gradio UI, and ComfyUI integration.

A reproducible training and evaluation pipeline for long-horizon shopping agents using SFT and GRPO within the ShopSimulator environment.

Loghub is a free collection of real system log datasets for AI-driven log analytics research. It includes 20 datasets across six categories (distributed systems, supercomputers, OSes, mobile, server apps, standalone software), with metadata like line counts, sizes, and labeling status. Logs are intentionally unsanitized. Usage requires citing the Loghub paper and referencing the repo URL.