Trending AI projects

A curated, regularly verified list of free AI models, APIs, and development tools that allow users to build and run AI applications without needing a credit card.

AI Story is a Docker‑based web platform that turns a short text prompt into a complete short video. It automatically rewrites the prompt into a script, creates a storyboard, generates images via multiple AI image services, plans camera motions, and renders the final video, all orchestrated with Django, Celery, Redis and a Vue front‑end.

An AI-powered mistake management system that helps students organize, analyze, and review wrong answers through automated tagging and similar-problem generation.

Local Deep Research (LDR) is an open‑source, self‑hosted AI research assistant that runs on your own hardware. It automatically searches the web, academic databases, and your personal document library, then synthesizes a citation‑rich report using any LLM you configure (e.g., a local Qwen‑3.6‑27B model). All data is stored encrypted with SQLCipher, and the system includes granular egress‑control, zero telemetry, and supply‑chain hardening. Install via Docker, Docker‑Compose, or pip, and choose from several privacy‑focused “egress scopes” to limit network traffic.

An open-source visual-first code editor for Next.js and TailwindCSS that allows users to design UIs visually in the browser and sync changes directly to the codebase using AI.

An AI-powered home intelligence agent that uses camera perception and large language models to proactively manage household tasks and learn family habits.

Dograh AI is an open‑source, self‑hostable platform for building voice AI agents with a visual workflow editor, modular LLM/STT/TTS integration, telephony connectors, and SDKs. One‑command Docker setup gets it running locally in minutes.

Physical AI Operating System that lets LLM agents control real robots (Lamp, Intern, Reachy Mini) via a Go‑based OS, HAL drivers, voice pipelines, and markdown‑defined skills.

Voxtype is an open‑source, MIT‑licensed Linux app that provides local, real‑time voice‑to‑text dictation. It runs fast CPU models (Cohere Transcribe 9‑11× realtime) and supports GPU/Intel NPU acceleration, nine interchangeable transcription engines, multilingual support, meeting‑mode transcription, and deep desktop integration (Wayland/X11, hotkey binding, auto‑pause media, waveform OSD). All processing stays on the machine unless the user opts for a remote server.

An AI-powered data visualization tool that uses agents to connect fragmented data sources and a branching "Data Thread" workspace for natural language data exploration.

HunyuanVideo is an open-source video foundation model with over 13 billion parameters that generates high-quality videos from text prompts using a hybrid Transformer architecture and a 3D VAE.

A modular workstation for 3D Gaussian Splatting that integrates training, real-time visualization, editing, and automation into a single native application.

An open-source software factory that uses autonomous agents to investigate codebases, implement changes, and manage pull requests.

A comprehensive, community-driven repository of over 23,000 concise AI paper notes categorized by conference and research field to help users quickly grasp the latest industry advancements.

A comprehensive AI content creation skill for WeChat Official Accounts that automates topic selection, evidence-based writing, editorial review, and professional layout formatting.

A Python MCP server giving AI assistants full control over Aseprite for pixel art and animation, with 123 tools across 18 categories designed for producing good pixel art (not just primitives), plus a Lua escape hatch and a recommended AI workflow. This explanation is grounded entirely in the README.

Exa MCP Server is a bridge that connects AI agents and coding assistants to Exa's search and content-fetching tools, enabling them to perform live web research and retrieve clean data.

An MCP server that connects Google Search Console to AI assistants, enabling natural language analysis of SEO data, indexing audits, and sitemap management.

A fast, CPU-based code search library for AI agents that retrieves precise code snippets using hybrid semantic and lexical search to reduce token consumption by up to 99%.

An open-source observability platform built on OpenTelemetry that unifies logs, metrics, and traces to monitor applications, infrastructure, and AI/LLM pipelines.

An open-source data labeling tool that allows users to annotate audio, text, images, and video to prepare or improve training data for machine learning models.

An open-source front-end quality system that provides 386 best-practice rules for humans and AI agents to audit and improve web development quality.

Singularity is an all-in-one root app for Meta Quest headsets (2, Pro, 3, 3s) that uses the fugu exploit to grant root in seconds, then gives you Magisk, privacy blockers, and a wide range of system tweaks.

ml-engineering is an open, practical guide for training and running large language and multi-modal models, compiled from the author's real-world experience. It covers hardware, orchestration, training, inference, and debugging, with ready-to-use scripts, comparison tables, and downloadable ebook formats.

A data preparation layer that converts documentation, codebases, and videos from 18 sources into structured knowledge assets for AI skills, RAG pipelines, and AI coding assistants.

A portable catalog of 17 AI research skills that guides users from literature discovery to manuscript release through an eight-stage pipeline with evidence-aware handoffs and explicit human approval gates. It solves context re-explaining, hallucinated citations, weak gap analysis, AI-smelling prose, and state loss when switching AI tools — installable as plugins for Claude Code and other hosts.

A local-first search layer that unifies ripgrep, BM25, and vector search to provide high-relevance retrieval for humans and AI agents.

A voice timbre conversion framework that uses retrieval-based features to transform voices with high fidelity and low latency.

An open-source desktop application for building and deploying a multi-agent AI workforce to automate complex digital workflows.

A stealth browser automation server for MCP-compatible AI agents that bypasses anti-bot protections like Cloudflare while providing deep browser control and network inspection.

A video editing platform that treats projects as code, allowing AI agents to programmatically edit, transcribe, and render videos while providing a visual interface for manual refinement.

A schema-based environment variable manager that allows AI agents to read configuration schemas without exposing sensitive secrets.

JobSpy is a Python library that scrapes job postings from LinkedIn, Indeed, Glassdoor, ZipRecruiter, and other boards concurrently, then aggregates them into a pandas dataframe for analysis or export.

A multi-platform IM agent that routes messages from WeChat, Lark, Telegram, and WhatsApp to various LLMs for automated replies and chat history analysis.

A desktop studio for ACE-Step 1.5 that enables local generation of full songs with vocals, featuring integrated LoRA training, stem separation, and MIDI tools.

A GPU-accelerated physics simulation engine built on NVIDIA Warp and MuJoCo Warp, designed for scalable and differentiable robotics simulation.

An open-source tool that lets you describe UI components in plain language and see them rendered live, with the ability to convert them to React, Svelte, or Web Components.

A portable agent skill that provides AI coding tools with expert SwiftUI best practices and a toolchain for analyzing performance traces.

Anomalib is a deep learning library that provides a modular framework for training, benchmarking, and deploying state-of-the-art visual anomaly detection models across various hardware platforms.

A cross-platform desktop management tool for OpenAI Codex that provides a visual interface for managing prompt templates, API providers, sessions, and Skills/MCP extensions.

A project that calculates the true per-token cost of AI coding subscriptions and compares them against model performance benchmarks to help users find the best value.

A local-first, self-evolving personal knowledge base that stores AI agent memory as editable Markdown files, enabling long-term knowledge retention and cross-agent sharing.

Photoshop MCP is a Node‑based AI assistant that lets you describe Photoshop edits in plain language. It translates prompts into Photoshop commands (via an LLM or the optional Jev router) and runs them as single undo‑able steps, supporting tasks like background removal, portrait retouch, batch watermarking, and carousel creation. Use it through a browser chat UI (`npx -p @alisaitteke/photoshop-mcp ui`) or via plugins for Cursor, Claude, and VS Code. Beta, community‑maintained, works on Windows/macOS with Photoshop 2012+ and Node 18+.

A local desktop application for reading academic papers that provides AI-powered translation, interactive Q&A, and structured note-taking while preserving original document formatting.

Omi is an open‑source “second‑brain” platform that records screen and audio, transcribes it live, and feeds the text to LLMs for summarisation and a persistent AI chat. It includes firmware for wearables, macOS/Windows/Flutter apps, a Python FastAPI backend, and multi‑language SDKs, all under an MIT license.

Scope Recall is a persistent, shared memory system for AI agents that uses SQLite to store verified facts and provides a unified knowledge base across multiple AI assistants like Hermes, Codex, and Claude Code.

A comprehensive collection of Python code and a textbook implementing essential robotics algorithms for localization, mapping, SLAM, and path planning.

A compact, 3D-printable open-source humanoid robot designed as an affordable platform for learning and experimentation in robotics.