Trending AI projects

A Claude Code skill that automatically turns long-form talking-head videos into short, social-ready clips with automated reframing and subtitles.

OlmoEarth is an open‑source library for building and using multimodal, spatio‑temporal foundation models on satellite and derived Earth‑observation data. It ships pretrained checkpoints (Nano‑to‑Large) trained on Sentinel‑1/2, Landsat, and six map layers, and includes scripts for pre‑training, fine‑tuning, inference, and evaluation.

A collection of official Google Model Context Protocol (MCP) servers and deployment guides that allow AI agents to interact with Google Cloud, Workspace, and other developer tools.

A browser-based first-person shooter built with Three.js and WebGL2, featuring entirely procedurally generated assets and a codebase written by AI agents.

A unified, offline history viewer for 31 AI coding assistants that allows users to browse, search, and analyze conversations and token usage across different tools.

An open-source API and RSS generator for WeChat Official Accounts that enables full-content scraping, multi-format archiving, and AI client integration via MCP.

Duckle is an open-source, local-first ETL platform that compiles visual data pipelines into high-performance SQL, allowing teams to run complex data workflows on their own infrastructure without vendor lock-in or per-row billing.

A Codex plugin that converts reference images into editable diagrams by automatically redrawing them in Microsoft PowerPoint, WPS Presentation, or draw.io.

A Rust-native, drop-in replacement for Apache Spark that provides significantly faster execution and lower infrastructure costs while maintaining full compatibility with Spark SQL and the DataFrame API.

A multi-agent framework for AI-assisted novel writing that manages everything from world-building and plot planning to style distillation and "anti-AI" refining.

TripStar is a multi‑agent AI travel planner that scrapes Xiaohongshu posts, fetches weather and hotel data, and uses an LLM to generate a complete, budget‑detailed itinerary with maps, photos, and an interactive AI Q&A window.

Pireel Studio is an open-source AI video editor that lets users create videos using a combination of manual timeline editing, chat-based descriptions, and AI agents.

Detectron2 is a high-performance computer vision library from Meta AI Research providing state-of-the-art object detection and segmentation algorithms.

A lightweight Python library providing a unified Chat Completions API and an Agents API to build AI agents across multiple LLM providers with minimal code.

k8sgpt is a CLI (and optional operator) that scans Kubernetes clusters, runs built‑in analyzers, and uses LLMs (OpenAI, Azure, Bedrock, etc.) to turn raw diagnostics into plain‑English explanations and remediation advice. It supports multiple back‑ends, anonymizes data, offers an MCP server for tool integration, and can be installed via Homebrew, RPM/DEB, or Windows binaries.

A collaboration tool for AI engineers and domain experts to build and curate high-quality datasets for NLP, LLMs, and multimodal models.

A real-time object detection framework based on the Detection Transformer (DETR) architecture that aims to outperform YOLO models in speed and accuracy.

A simulated bash environment with a virtual filesystem that allows for safe execution of bash-like commands in a sandbox.

A collection of specialized React Native knowledge bundles that can be installed into AI coding assistants to help them optimize, test, and migrate apps.

mem9 provides a persistent, shared memory layer for AI agents, allowing them to retain context across different sessions, machines, and platforms through a unified API.

OpenAI4S is a hybrid research agent that combines structured JSON orchestration with persistent Python/R kernels to automate scientific workflows, data analysis, and simulations.

A high-performance inference toolkit for deploying and serving open-source text embeddings and sequence classification models with low latency.

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.

Row‑Bot is a self‑hosted desktop AI assistant that lets you converse with LLMs to create files, run code, manage designs, and interact with services—all while keeping data locally. It offers memory via a personal knowledge graph, goal‑driven agents, approval‑gated actions, multi‑device remote access, and integrations (GitHub, Notion, Slack, etc.). Runs on Windows/macOS/Linux or Docker, using Ollama or any OpenAI‑compatible provider, and stores everything securely on your machine.

LLM Vision is a Home Assistant integration that uses multimodal large‑language models (OpenAI, Anthropic, Gemini, Ollama, etc.) to analyze images, video clips, live camera feeds and Frigate events. It returns natural‑language descriptions, remembers identified people/pets/objects, and stores each analysis in a timeline that can be shown on the dashboard or queried via Assist. Install via HACS, configure an LLM provider, and optionally add the supplied Blueprint for AI‑summarized camera notifications.

A collection of 11 autonomous SEO skills for Claude and other AI agents that perform live research, competitor analysis, and content auditing without requiring manual data exports.

Claurst is a Rust‑based terminal coding assistant that talks to multiple LLM providers, offers a rich TUI, supports the open Agent Client Protocol for editor integration, and includes experimental features like multi‑turn goals and an ultra‑think mode.

A high-performance inference optimizer and runtime from NVIDIA that accelerates AI model deployment and throughput on NVIDIA GPUs.

A PyTorch library providing a high-level API for image semantic segmentation, featuring 12 architectures and over 800 pretrained encoders.

Labelme is a graphical image and video annotation tool that helps users create labeled datasets for computer vision tasks like segmentation and object detection, featuring AI-assisted labeling capabilities.

A desktop application that uses the RMBG-1.4 model to provide local AI-powered background removal, batch processing, and image editing tools.

An AI-powered academic workstation for researchers that provides high-speed translation, OCR, and agentic analysis of academic papers while preserving original formatting.

dsh‑pentest is a DeepSeek Harness plugin that adds a structured penetration‑testing mode. It provides tools for agents to record goals, intents, facts, findings and assets, stores them in a SQLite DB, and shows the data in a dedicated web UI (graph, vulnerability list, asset view, markdown report). Intended for authorized security work, it works with DSH ≥ 0.1.6 and Node ≥ 22.5.

A privacy-focused collection of 152 browser-based utility tools, featuring on-device AI for transcription, translation, and image processing via Transformers.js.

A high-performance, unofficial Rust reimplementation of Apache RocketMQ that provides a distributed message queue system with full protocol compatibility.

A Python library for differential inverse kinematics based on the MuJoCo physics engine, enabling robots to reach targets while avoiding collisions and respecting joint limits.

An anime scene search engine that identifies the specific anime, episode, and timestamp of a screenshot using image vector search.

A collection of modular AI-assisted skills for auditing, formatting, and polishing academic LaTeX and Typst manuscripts.

A ComfyUI implementation of the Spectrum method to accelerate MiniMax H3 audio-video generation by forecasting hidden states to skip expensive transformer evaluations.

A GUI application and toolkit for Claude Code that provides visual session management, custom agent creation, and usage analytics.

An open-source, local-first AI journal that uses a multi-agent system to automatically organize life fragments into a structured, private knowledge base.

LMDeploy is a comprehensive toolkit for compressing, deploying, and serving large language and vision models, designed to maximize inference speed and hardware efficiency.

CUGA is a framework for building custom AI agents for the enterprise. Instead of writing agent orchestration, tool wiring, and safety logic from scratch, you configure your domain's tools, policies, and workflow on top of a high-performing generalist core. It integrates many tool types (MCP, OpenAPI, LangChain), supports RAG over your documents, multi-agent supervision, and event-driven triggers, and lets you govern behavior with policies including human approval gates.

A high-performance GPU document parser that converts images and PDFs into structured Markdown, tables, and formulas at extreme speeds using C++ and TensorRT.

An interactive 3D insect encyclopedia that generates all models programmatically using TypeScript and Three.js, offering detailed anatomy, life cycles, and educational quizzes for 63 species.

A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

An extension for the pi CLI that manages multiple AI service subscriptions, providing automatic rate-limit rotation and intelligent failover across different accounts and providers.

DepthFlow is an open-source image-to-video converter that transforms static pictures into 3D parallax animations using depth estimation and optimized shaders.