Trending AI projects

ElevenLabs Skills is a plug‑in collection of Agent‑Skills that expose ElevenLabs’ speech‑AI APIs (text‑to‑speech, transcription, voice‑changing, music, dubbing, etc.) to any compatible AI coding assistant. Install with `npx skills add elevenlabs/skills`, set an `ELEVENLABS_API_KEY`, and use the provided Python/JS examples or run built‑in evaluations.

CCPM is an Agent‑Skill that adds a full spec‑driven, parallel project‑management layer to AI coding agents. It converts natural‑language ideas into PRDs, epics, tasks, and GitHub issues, keeps all state in markdown files, launches multiple agents to work concurrently, and provides instant status reports via bundled bash scripts. Compatible with any agentskills.io‑compatible harness (Claude Code, Factory, Cursor, etc.).

A context engineering tool that converts entire codebases into structured LLM prompts, automating the process of gathering and formatting code for AI models.

RealSense SDK 2.0 (librealsense) – open‑source C++ library for Intel RealSense depth cameras, offering cross‑platform colour‑depth streaming, calibration data, and wrappers (Python, ROS 2, C#, Unity). Provides pre‑built binaries or source builds, supports AMD GPU acceleration, and includes sample code for easy start‑up.

A lightweight, rootless Linux sandbox for isolating untrusted code using Landlock and seccomp, offering high-performance security for AI agents and scripts without the overhead of containers.

An educational book and toolkit for learning modern GPU kernel programming on Blackwell-class hardware using the TIRx Python domain-specific language.

Apache AGE is a PostgreSQL extension that adds multi-model graph database capabilities, allowing users to perform graph queries alongside standard relational SQL.

Open Cowork is a free, open‑source desktop AI‑agent app for Windows and macOS. It wraps Claude‑style models (Claude, OpenAI, Gemini, Chinese models) in a GUI, offers VM‑level sandboxing, a built‑in Skills system for Office‑document generation, MCP connectors for browsers/Notion, GUI automation, and remote control via Feishu or Slack. One‑click installers and Homebrew casks make setup trivial; developers can also build from source.

reg-factory is a local web console that automates registering and authorizing accounts across Outlook, ChatGPT, Grok, Claude, Gemini, GitHub, and more, then exports the credentials in formats like SUB2API or cookies for downstream use. It handles email pools, captchas, proxies, and phone verification, with a claimable asset API for other tools.

A Docker Compose template that bundles n8n, Ollama, and Qdrant to quickly set up a self-hosted, local AI development environment for building AI agents and workflows.

LightLLM is a Python‑based, high‑performance inference and serving framework for large language models. It combines fast kernels (FlashAttention, Triton) with lightweight, token‑level KV‑cache management, supports multi‑GPU scaling, and adds research‑grade features like constrained decoding and SLA‑aware request scheduling.

A collection of AI agent skills and SDKs that enable models to generate images, videos, search the web, and automate social media via the inference.sh CLI.

PromptCraft is a public GitHub repository that collects system prompts from ChatGPT and other AI products/custom GPTs for educational purposes. It includes a searchable table of contents, guides for getting started and security, and contribution guidelines. The project aims to help people learn prompt writing and understand prompt injection security, with the README noting that many GPT authors have improved their defenses after seeing these breakdowns.

A design engineering system for AI coding agents that provides professional design rules and verification tools to ensure AI-generated UIs are production-grade.

4DAnyone converts a single monocular video of a person into consistent multiview videos to enable high-quality 4D Gaussian Splatting reconstruction.

A tool that creates persistent, isolated Linux workspaces using Docker or Podman to provide secure environments for software development and AI coding agents.

A second-generation driver package that connects Livox LiDAR sensors to ROS and ROS2, enabling the publication of 3D point cloud data.

A free, low-maintenance online course on deep reinforcement learning, with theory and hands-on notebooks, hosted by Hugging Face.

PyHealth is an open‑source Python library that provides a modular, five‑stage pipeline for building, training, and evaluating deep‑learning models on clinical electronic health‑record datasets such as MIMIC‑III, eICU, and OMOP. It includes ready‑made data loaders, a catalog of 30+ neural architectures, a trainer with early‑stopping, and utilities for medical code lookup and tokenisation, all supported by extensive tutorials and a community Discord.

An AI-native tutoring system implemented as a Claude Code skill that provides adaptive, personalized courses on AI design and Forward Deployed Engineering.

SwitchAI is an Android app that lets you select, launch, and set a default among dozens of AI‑assistant apps (ChatGPT, Claude, Gemini, Alexa, etc.) via a Material 3 selector, home‑screen widget, and Quick Settings tile.

A tool that runs local processes inside a live Kubernetes cluster by mirroring traffic, files, and environment variables from a target pod.

A Model Context Protocol (MCP) server that allows AI assistants to manage Discord servers, including channel, member, and moderation tasks.

DocsGPT is an open‑source, self‑hosted platform that turns your documents, sites and connected apps into AI agents. It supports any OpenAI‑compatible model, provides cited answers, visual workflow building, extensive data connectors, team‑level SSO/quotas, and can be accessed via a web UI, widget, API or chat‑bot integrations.

A remote development workstation tool that provides a low-latency remote IDE, screen streaming, and a unified UI for running multiple AI coding agents across all devices.

A local-first macOS coding workspace that unifies multiple AI coding agents and provides intelligent task routing and a visual agent graph.

aislop is a deterministic CLI that scans code for AI‑generated “slop” (unused imports, narrative comments, dead code, etc.) across 10 languages, scores the repo 0‑100, can auto‑fix safe issues, and integrates with AI agents, git hooks, and CI.

A notification system for AI coding agents that provides voice-line audio alerts and visual banners when tasks finish or require user input.

A lightweight, Kubernetes-native LLM inference platform that provides modular control and data planes for scalable, cost-efficient model serving.

WordPress AI is an official experimental plugin that integrates AI capabilities (text generation, image generation, moderation, translation, etc.) into the Gutenberg editor via a modular “experiment” framework. It relies on separate AI Connector plugins for provider access, offers logging, key encryption, and a permissions‑style Abilities API, and serves as a reference implementation for developers and a test‑bed for potential core features.

Uni‑Agent is an open‑source framework for plugging any LLM‑based agent harness into a scalable, sandboxed pipeline that can run thousands of long‑horizon sessions in parallel, collect traceable trajectories, and train agents via reinforcement learning. It offers modular abstractions, reproducible example recipes, and supports serverless back‑ends like veFaaS and Modal.

A framework for deploying real-time voice AI on ESP32 devices, connecting low-power hardware to frontier speech-to-speech models via edge functions.

A curated, weekly-updated list of 2026 AI agent research papers from arXiv, covering multi-agent coordination, memory/RAG, tooling, evaluation, and security.

Codex Router is a client‑side tool that lets the Codex app use many LLM providers (Anthropic, Kimi, DeepSeek, Grok, Claude, Gemini, etc.) via a secure background service, Electron control center, and optional macOS widget. It manages credentials locally, offers experimental bridges to existing Claude/Cursor/Gemini agents, and provides a Homebrew tap for CLI‑only installs.

A fully local, private, and uncensored AI companion framework that integrates LLMs, voice synthesis, image generation, and Live2D animations to create interactive, persistent characters.

A collection of optimized recommender models and GPU libraries for large-scale ranking, retrieval, and generative recommendation, featuring agent-driven PyTorch optimization.

A terminal-based interface for the Kraken exchange that enables manual trading, automated AI-driven trading via MCP, and paper trading with live market data.

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.

Docker Sandboxes (sbx) is a Docker‑based tool that creates isolated containers for AI agents, giving them controlled file‑system and network access so they can run autonomously without endangering the host. It ships as a native installer (Homebrew, WinGet, APT, etc.), supports pre‑release (RC/nightly) builds, and works with popular LLM CLIs like Claude Code, Codex, and Gemini.

A unified collection of core CUDA C++ libraries (Thrust, CUB, and libcudacxx) providing high-performance parallel algorithms and standard library abstractions for GPU development.

Open‑WebSearch is a Node‑JS service that lets AI agents perform live web searches and fetch article content without any API keys. It offers an MCP‑compatible server, a CLI, and a long‑running HTTP daemon, aggregates results from many public search engines, supports proxy use, and can optionally use Playwright‑driven headless browsers for sites that need JavaScript rendering.

An optimized inference engine for Qwen3-TTS that provides real-time streaming and high-speed generation across NVIDIA, AMD, and Apple Silicon hardware.

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.

An information processor for quantitative finance that transforms raw papers and news into structured, cited, and timestamped financial knowledge for RAG and agentic reasoning.

A serverless platform for building and deploying AI agents as code, providing a managed cloud environment and CLI tools for rapid development.

A practical node suite for ComfyUI that simplifies MiniMax H3 video generation, offering unified media management and tools for creating long, continuous videos via connected segments.

An MCP plugin that adds semantic code search to AI coding agents, allowing them to efficiently retrieve relevant snippets from large codebases using a vector database.

A low-code website builder with a visual editor and an AI agent that creates and edits pages based on the site's existing design language and data.