Trending AI projects

CyberVerse is an open-source framework for building real-time digital-human agents that can see, hear, and talk via WebRTC. It combines persona memory, RAG, tool calling, and optional avatar video (from a single photo) to create voice-centered AI characters, with full-duplex interaction and multi-agent task delegation.

AvatarAI is an open‑source, production‑grade system that turns any portrait photo and a short voice sample into a real‑time, lip‑synced talking avatar. It streams Whisper‑transcribed speech to a selectable LLM (Claude, GPT‑4o, or local Ollama/vLLM), feeds the generated text to a multilingual TTS (Chatterbox/XTTS), and renders video frames with MuseTalk V1.5. The stack includes Next.js front‑end, FastAPI back‑end, PostgreSQL, Redis, Celery, Prometheus, and Docker‑Compose, with optional one‑click AWS GPU deployment. Features include zero‑shot voice cloning, barge‑in interruption, multi‑LLM support, JWT auth, conversation memory summarisation, and optional face‑restoration via GFPGAN.

A unified memory stack for LLM agents that provides semantically lossless compression for text and multimodal data, featuring a self-evolving retrieval system to maximize recall while minimizing token usage.

A self-hosted server with a Web UI and OpenAI-compatible API for Resemble AI's Chatterbox TTS family, featuring voice cloning, multilingual support, and audiobook generation.

A DSH plugin that allows AI models to generate interactive, sandboxed UI components like charts, simulators, and dashboards directly within the chat interface.

A collection of modular skills for AI coding agents that automate tasks like video production, competitive content analysis, macOS system management, and college application planning.

Neuron AI is a Composer‑installable PHP framework that lets developers build full‑featured AI agents, RAG pipelines, tool‑calling, structured output and multi‑agent workflows. It abstracts dozens of LLM providers, offers ready‑made toolkits (e.g., MySQL), an MCP connector for remote tools, and a low‑level Workflow engine for custom pipelines. Installation is a single `composer require` plus optional skill integration for Laravel/Symfony. The library targets PHP teams that want the AI agent to be the core architecture of their application.

AI Playground is an open-source generative AI application suite for Intel AI PCs, offering offline chat, image generation, video generation, code assistance, and document search. It supports local models via Llama.cpp and OpenVINO, with an optional Hybrid Cloud mode for frontier models.

A high-throughput REST API for serving text-embeddings, reranking, and multi-modal models from HuggingFace with low latency and hardware flexibility.

Home LLM is a Home Assistant integration that runs a small, locally hosted LLM (or connects to an external LLM server) to let you control smart‑home devices via voice or chat, with multilingual support and low‑power hardware compatibility.

An agent testing framework that uses simulations, user simulators, and judge agents to evaluate the behavior and robustness of AI agents in multi-turn conversations.

A curated, timeline-ordered list of open-source AI web search tools that combine large language models with web capabilities, covering summarization, function calling, and agent-driven research.

noScribe is a free, open‑source desktop app that locally transcribes interview audio, detects speakers, and supports many languages using Whisper and pyannote‑audio. It’s aimed at researchers and journalists who need confidential, high‑quality transcripts.

AlphaGenome is a unified DNA sequence model that predicts the effects of regulatory genetic variants on gene expression, splicing, and chromatin features at single base-pair resolution.

MoE4All is a high-performance inference engine that enables running large Mixture-of-Experts models on consumer hardware by intelligently offloading weights between SSD, RAM, and GPU VRAM.

Molio is a local-first knowledge management tool that transforms personal documents and files into an AI-ready knowledge base, allowing AI agents to research and analyze your data while keeping everything private on your own machine.

A Home Assistant integration that transforms any web browser or Android tablet into a private, hands-free voice assistant satellite with on-device wake word detection.

A real-time AI assistant for Meta Ray-Ban smart glasses that uses Gemini Live to see, hear, and take actions via OpenClaw integration.

A lightweight, YAML-driven Python robot simulator for rapid prototyping of navigation, control, and learning algorithms in 2D environments.

A CUDA-accelerated library for robot motion generation that provides GPU-parallel algorithms for kinematics, collision checking, and trajectory optimization for high-DoF robots.

py-xiaozhi is a cross-platform, asynchronous Python framework that enables real-time voice and vision AI interactions on desktop and embedded hardware.

A community-powered distributed inference cluster that lets volunteers share their GPU power to provide free AI image and text generation for everyone.

A library and agent skill for creating and managing "loops"—iterative, feedback-driven prompts that allow AI agents to repeat and verify tasks until they succeed.

A collection of modular tools, function pipes, and filters that extend Open WebUI with capabilities like academic research, media generation, autonomous agents, and web search.

Gladys Assistant is a privacy-focused, open-source smart home platform that allows users to manage and automate their connected devices locally on their own hardware.

Audire is an open-source Android app that identifies music playing around you. It is available on GitHub, Google Play, and IzzySoft.

Birdview is a skill for AI coding agents that visualizes a project's architecture, constraints, and planned changes in a standalone HTML page. Developers confirm the AI's plan before any code is edited, helping catch scope mistakes early. It offers architecture reviews, constraint audits, and impact tracing, with bilingual UI and optional auto‑mode.

A high-fidelity digital twin project for Unitree Go2 and G1 robots in Nvidia Isaac Sim, enabling real-time synchronization between physical robots and their virtual counterparts.

Pro Workflow is a plugin toolkit that adds persistent self‑correcting memory, searchable research wikis, and automated research loops to LLM coding assistants (Claude Code, Cursor, Gemini‑CLI, etc.). It stores rules and wiki data in a single SQLite database, provides 41 skills, 8 agents, and 23 slash commands, and works across 30+ agents via a `skills add` installer.

OnlySwitch is a customizable macOS menu-bar utility that consolidates system controls, shortcuts, and hardware monitoring into one interface, featuring an AI-powered agent for executing system tasks via natural language.

Riko is an open-source anime AI companion that runs on your PC. Using push-to-talk, you speak, she replies with a personality you define via OpenAI GPT, speaks with a cloned voice (local or online), and shows a lip-syncing 3D avatar.

Search Console MCP is a tool that connects your AI agent to Google Search Console, Bing Webmaster Tools, GA4, and AdSense, allowing you to perform SEO and revenue analysis without manual data exports.

TrackEverything is a system for dense 3D point tracking in long videos. It builds a persistent, de-duplicated 3D scene representation using RGB, depth, and camera poses (or estimates them) and outputs per-point trajectories labeled static or dynamic.

A powerful search engine plugin for Obsidian that uses the BM25 algorithm to provide instant, relevance-ranked search across notes, PDFs, and images.

A language-agnostic tool that automatically synchronizes subtitles with video or audio files using voice activity detection and FFT-based alignment.

A pure C implementation of an AI assistant for the ESP32-S3 chip, providing a low-power, always-on agent with local memory and tool-calling capabilities via Telegram.

An MCP server that enables AI assistants to execute trades and access market data for stocks, options, and crypto via the Alpaca Trading API.

Lichtblick is an integrated visualization and diagnosis tool for robotics that allows developers to inspect and visualize robotic data via a browser or desktop app.

A comprehensive, offline-first personal web application that provides a persistent, multi-modal environment for long-term emotional interaction with AI models.

A mobile companion for the Codex CLI that lets you monitor and steer AI coding sessions from your phone while keeping all work on your local computer.

A reference implementation for deploying and scaling vLLM inference services on Kubernetes, featuring request routing, observability, and automated infrastructure management.

A local AI quota aggregator and proxy that lets you use AI subscriptions from various providers (like Claude Pro or Cursor) across any AI tool or IDE.

A curated library of 869 AI agent skills for OpenClaw and NanoClaw that provides specialized capabilities for biomedical research, clinical workflows, and bioinformatics.

An AI-powered image annotation tool that integrates YOLOv8 and Segment Anything to provide automatic labeling for computer vision datasets.

Hercules is an open-source AI testing agent that turns simple Gherkin feature files into fully automated end-to-end tests using natural language, no coding required. It supports browser, API, security, and Python sandbox testing and generates detailed reports and proofs.

HermesClaw is a lightweight Python proxy that lets a single WeChat account use Hermes Agent, OpenClaw, and OpenCode simultaneously, providing slash commands to switch or combine them.

Quotio is a management tool for AI coding agents that tracks provider usage quotas, manages API credentials, and configures local proxies from a native macOS app or a terminal CLI.

A gateway that enables free access to multiple premium LLMs by automating browser logins and driving official web UIs instead of using paid API tokens.