Trending AI projects

URDF Studio is a browser-based robotics workstation that allows users to design, visualize, and export robot models without manually editing XML files, featuring AI-powered generation and multi-format support.

A set of Claude Code plugins (skills & sub‑agents) that add brainstorming, deep research, GitHub issue/PR automation, image generation, translation, and more, with ready‑made config files for many LLM providers.

AVA is an AI-native framework for visual analytics that enables users to analyze data and generate visualizations using natural language, supporting a wide range of data sources and execution engines.

LiveBench is a contamination-free benchmark for LLMs that uses monthly updated questions and objective ground-truth answers to provide reliable performance evaluations.

Ling Stack is a local-first workspace that centralizes AI model interactions, tool usage, and project artifacts into a single, organized environment to prevent workflow fragmentation.

A collection of specialized skills for AI agents to help developers build applications with Gemma models or train and fine-tune them on local hardware.

A collection of AI agent skills designed to maintain project continuity across different chat sessions, primarily through a structured project handoff system.

A collection of customizable UI components for AI applications, designed to integrate with shadcn/ui to help developers quickly build chat interfaces and AI agents.

PI Dashboard is a web/Electron UI that lets you run, monitor, and interact with multiple *pi* AI coding‑agent sessions in real time, with features like workspace organization, token‑cost tracking, integrated terminal, OpenSpec/flow support, provider management, and extensibility via plugins.

A modular platform for powergrid operation simulation, providing a Gymnasium-compatible environment for training reinforcement learning agents to manage power networks.

Reverify is a Python toolkit that lets LLMs propose facts about binaries (or source code) and then deterministically checks those claims against the actual file. It offers pure‑Python parsers/disassemblers plus optional native back‑ends (Capstone, Unicorn, LIEF, Z3, angr). Verified facts are stored in a ledger, enabling AI agents to roll over contexts without losing trustworthy state. The tool is packaged on PyPI, includes a CLI and an MCP server for agent integration, and has been benchmarked to catch 100 % of hallucinated claims on real Windows binaries.

Harness Remote is an open‑source, local‑first control plane that lets you observe, pause, resume, and hand‑off native AI coding‑agent sessions (Codex, Claude, OpenCode, etc.) across devices. It runs a small Node.js gateway on a machine with a coding‑agent CLI, then connects via desktop, web, or Android clients. All code, credentials, and session data stay on your own machines; the tool only adds a UI and coordination layer.

AMD Skills is a catalog of reusable, agent‑compatible “skills” that encode AMD‑specific AI workflow knowledge (ROCm diagnostics, Quark quantisation, LLM serving on Instinct/EPYC, etc.). Install via the `skills` CLI (`npx skills add amd/skills`) or manually, then invoke the skills through coding assistants like Cursor, Claude Code, Codex or Gemini. Each skill bundles a `SKILL.md` description, optional scripts and references, enabling agents to automatically perform setup, optimisation and debugging steps for AMD hardware.

Luvus is a cross‑platform terminal UI that lets you launch, monitor, and orchestrate AI coding agents (Claude, Codex, Grok, etc.) alongside shells, editors, and Git tools. It provides persistent workspaces, pane management, agent‑aware status panels, Git/GitHub integration, remote‑machine support, a read‑only web view, and an extensible module system. Install via a script, Homebrew, or PowerShell, then use `luvus` to start a session, `luvus doctor` to verify setup, and `luvus update` for upgrades.

Image To Slice is a Figma plugin (with a web UI) that uses AI to split a UI screenshot into editable layers and image assets, then exports the result as a Figma file or HTML/CSS bundle. It supports automatic AI slicing, manual JSON mode, background inpainting, asset classification, and configurable OpenAI‑compatible back‑ends.

RobotGo, Go Native cross-platform RPA, GUI automation, Auto test and Computer use @vcaesar

A high-performance TypeScript transformer library that compiles pure types into runtime validators, JSON schemas, and LLM function calling harnesses.

A GPU-accelerated artificial life simulator where digital organisms with neural-network-controlled bodies evolve in real-time, featuring AI agent integration for experiment control.

A multi-agent LLM system for high-frequency trading that combines technical indicators, visual pattern recognition, and trend analysis to generate trade directives.

A JavaScript library for developing Game AI, providing tools for autonomous agent design, steering, navigation, and fuzzy logic.

azooKey‑Desktop is an open‑source macOS Japanese input method that replaces the system’s Kana‑Kanji conversion with a neural model (Zenzai) and optional LLM‑based suggestions. It includes history learning, user dictionaries, and integrates with the Tuner optimizer. Users can install via a released `.pkg` or Homebrew; developers can build from source with Xcode, Git LFS, and SwiftLint, following detailed signing and submodule steps. The project is AI‑focused, community‑driven, and backed by an IPA talent‑development grant.

A fast, language-agnostic code navigator that indexes codebases into SQLite to enable millisecond-latency symbol lookups, dependency tracing, and impact analysis for humans and AI agents.

A block-based, AI-powered hardware development environment that simplifies prototyping by automating board configuration, code generation, wiring diagrams, and debugging for over 100 different microcontrollers.

A system for building a structured, interconnected knowledge base from fragmented data, featuring an interactive knowledge graph and integration with AI CLI agents.

FaceWinUnlock‑Tauri is a Windows‑only tool that adds webcam‑based face unlock by injecting a custom Credential Provider DLL. It combines a Tauri‑Rust back‑end (registry edits, SQLite storage) with a Vue 3 front‑end and OpenCV face matching, offering multi‑account support, optional liveness detection, and logging. The core code is now closed‑source; use only on non‑critical PCs and test in a VM because registry changes can lock you out.

A Model Context Protocol server that enables AI models to perform automated Windows crash dump analysis and live debugging by wrapping the standard WinDbg command-line tools.

Kernel Images supplies sandboxed Chrome containers (Docker or Unikraft unikernel) that expose a CDP endpoint for Playwright/Puppeteer, offer remote GUI streaming (VNC/WebRTC), fast standby/restart, and screen‑recording – enabling AI agents and automation scripts to run persistent, low‑latency browser sessions in isolation.

LLM‑PID‑Tuner is a desktop utility that uses a large language model to suggest and apply PID controller gains for hardware (Arduino/ESP32) or simulated systems, with safety limits and rollback.

RSTGameTranslation is a Windows‑only tool that captures a game’s screen region, runs OCR, sends the text to an AI translator (Google, Gemini, Ollama, etc.), and draws the translation back onto the game. It also supports voice‑to‑text (Whisper/FunASR) and offline text‑to‑speech (Supertonic). Users select a window or rectangle, configure language and translator, and control everything via hotkeys. The app is useful for playing untranslated games, reading manga, or streaming with live subtitles.

Gorse is an open‑source, Go‑based recommender‑system server that automatically trains models from user‑item interaction data and serves personalized suggestions via REST APIs or a web dashboard. It supports multiple recommendation algorithms, multimodal item embeddings, and can run on a single node or a distributed cluster.

A PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) for generating high-quality images and 1D sequences.

An open-source framework for training language agents with reinforcement learning, allowing the same agent code to be used across different backends, sandboxes, and benchmarks.

An observability and automated fixing platform that helps developers make AI agents self-healing by capturing traces, grouping failures, and dispatching coding agents to implement fixes.

A gradient-free optimization platform for minimizing functions, particularly useful for hyperparameter tuning in machine learning.

IREE is an MLIR-based compiler and runtime that lowers machine learning models to a unified IR for efficient deployment across data centers, mobile, and edge devices.

The official Google Gen AI Python SDK provides a streamlined interface for developers to integrate Gemini models and the Gemini Enterprise Agent Platform into their applications.

VOICEVOX is an open‑source Electron‑based desktop editor for the VOICEVOX neural text‑to‑speech engine. It lets users pick a voice, type text, and generate Japanese speech, while providing full development tooling (Storybook, Playwright tests, linting, CI). The editor talks to a native engine binary via a local API, and can also connect to a separate engine server. The repo includes scripts for building, testing, and contributing, and is dual‑licensed (LGPL v3 + commercial).

Inspect Petri is an auditing agent that automates the monitoring and interaction with language models to detect alignment issues and reward hacking.

SCAIL-2 is an open-source model for end-to-end character animation and replacement, removing the need for intermediate pose representations to support complex motions and diverse identities.

Agent SOPs are markdown-based instructions that let you define complex workflows for AI agents using natural language, parameters, and RFC 2119 constraints. They can be distributed as MCP prompts, Agent Skills, or Python modules, enabling consistent task execution across different AI systems.

Aholo Viewer is a TypeScript‑based web renderer for large 3D Gaussian Splatting (3DGS) and mesh data, using a Chunked Streaming LOD format. It includes a conversion CLI, native C++ engine, an Astro documentation site with a live playground, and AI‑assisted integration guides. The project is packaged as `@manycore/aholo-viewer` on npm and is MIT‑licensed.

A design-enforcement engine that installs into AI coding agents (Claude Code, Codex, Cursor) to make their UI output look professionally designed rather than AI-generated, using a scored quality gate that automatically fixes problems before you see the result.

ProgramBench is a benchmark that tests if AI agents can rebuild a complete codebase from scratch given only a compiled binary and its documentation.

A modern, open-source interface for the NVIDIA cuDNN library that provides a simplified C++ and Python API for building high-performance deep learning kernels and computational graphs.

ChattyPlay-Agent is a multi-functional web platform that integrates AI services, media parsing, productivity tools, and financial data into a single, unified interface.

A Python library from Neo4j that lets you build Graph Retrieval‑Augmented Generation (GraphRAG) apps. It provides pipelines to turn text/PDFs into a Neo4j knowledge graph, utilities for vector indexing, hybrid retrievers that blend vector search with graph traversal, and a simple RAG API that plugs any supported LLM (OpenAI, Anthropic, Ollama, etc.). Install via `pip install neo4j-graphrag` (optional extras for your LLM), create a KG, index embeddings, then query with natural language.

A real-time, browser-based motion capture tool that uses a webcam to drive MMD characters and export animations as .vmd files.

An AI agent framework for Claude Code that guides developers through a structured seven-wave process from idea to code, enforcing TDD and human review at every step.