AI applications

Application performing real-time face swapping and one-click video deepfakes from a single image, supporting live streaming and video processing workflows.

Real-time global intelligence dashboard that aggregates news with geopolitical and infrastructure signals, providing a unified situational awareness interface across multiple devices.

Transforms complex PDFs and Office documents into large-language-model-ready Markdown or JSON, preserving structure for downstream retrieval and agentic workflow processing.

Swarm-intelligence prediction engine using parallel multi-agent simulations to extrapolate future trajectories and generate forecast reports for analysts exploring complex scenarios.

An AI-powered document processing app that converts PDFs, Office files, images and audio into structured Markdown and JSON for generative AI workflows.

Combines multi-source market data and real-time news into an LLM-driven multi-market stock analysis system that generates decision dashboards and automated alerts, designed to run on free scheduled jobs.

Implements a few-shot voice cloning and text-to-speech web application that trains personalized, high-fidelity synthetic voices from as little as one minute of recorded audio.

Deep-learning face-swapping software for images and video, covering face extraction, training, and conversion workflows for researchers and hobbyists experimenting with synthetic media.

AI application converting documents or topics into native editable PowerPoint decks with shapes, animations, data-driven charts, tables, templates, and narration from speaker notes.

Open-source AI voice studio that runs locally for voice cloning, multi-engine text-to-speech synthesis, dictation, and audio creation without cloud dependence.

Free open-source desktop software for AI image upscaling on Linux, macOS, and Windows, enhancing resolution and quality locally with selectable models for designers and photographers.

Open-source desktop application for running local large language models, supporting text and vision chat, tool calling, and an OpenAI-compatible API while keeping data private.

Personalized AI tutoring application for lifelong learning, offering course support, study guidance, and continuous assistance to learners outside traditional classrooms.

Open multi-agent interactive classroom that generates complete courses in one click, combining lecture materials, question answering, quizzes, and audio-video assets for teachers and learners.

AI-powered tool translating full PDF scientific papers bilingually while preserving original layout, formulas, and formatting. Supports Google, DeepL, OpenAI, Ollama, and other services with CLI, GUI, Docker, MCP, and Zotero interfaces.

Privacy-focused AI search engine that combines multi-source retrieval with cited, conversational answers. Offers users an open-source, self-hostable alternative to Perplexity for question-driven research.

A local NVR that performs real-time AI object detection on IP cameras with recording, live view, and Home Assistant integration.

A Next.js app that creates and edits draw.io diagrams from natural language chat, uploads, and MCP-powered agents.

Helps users rewrite, compare and iterate prompts to improve AI outputs, providing testing and asset management features for prompt engineers and regular users.

Local-first open-source desktop voice studio for creators, supporting voice cloning, voice design, video dubbing, dictation, and long-form audiobook production entirely on-device.

Fully local open-source alternative to ElevenLabs that integrates voice cloning, voice design, dubbing, transcription, dictation, and audiobook creation across hundreds of supported languages.

An automation app that generates and publishes Twitter content and YouTube Shorts to earn money online.

Local-first open-source AI meeting assistant written in Rust. Provides realtime transcription, speaker diarization, and on-device summarization for macOS and Windows users preferring self-hosting.

Implements an autonomous research agent that plans web and local searches, gathers sources and synthesizes comprehensive reports, serving analysts and developers needing structured in-depth research.

An open-source PDF parser turning documents into AI-ready Markdown, JSON and tagged accessible PDFs.

Free open-source studio for AI image and video generation, integrating more than 200 generation models with self-hosting, desktop, and browser-ready options for creators and developers.

Electron desktop chat client built on the official DeepSeek Harness with tuned support for macOS and Windows. It provides Chinese-speaking users an out-of-the-box conversational experience without manual setup.

Automates short-video production with an AI engine that handles scripting, voiceover cloning, and digital humans, enabling creators to batch-generate ready-to-publish short videos with one-click workflows.

An open-source creative engine for Stable Diffusion and Flux models with a web UI, unified canvas, node workflows and gallery management for visual creation.

A browser automation platform combining large language models with computer vision to execute workflows on arbitrary websites, offering an SDK and no-code builder for operations teams.

A leading open-source creative engine for Stable Diffusion and Flux models with a polished web UI, canvas, and workflows.

Deep research assistant combining search engines, web scraping, and large language models to iteratively investigate any topic and generate sourced reports for knowledge workers.

Document parsing toolkit built on a 7B vision-language model that linearizes PDFs and images into clean Markdown for LLM dataset preparation.

Efficient portrait animation application that drives static portraits into expressive videos for humans, cats, and dogs, providing a Gradio interface and one-click installation packages.

Deep-learning file-type detection tool delivering millisecond identification of over 200 formats, providing CLI and multi-language APIs for security routing and content handling.

A locally deployable AI platform for quantitative research and trading, covering data ingestion, factor mining, backtesting, and live trading across stocks, funds, futures, and crypto assets.

End-to-end solution for creating personal digital avatars by fine-tuning large models on chat history, covering data export, training, and multi-platform chat deployment.

AI-driven interactive wiki generator that analyzes code repositories from GitHub and similar sources, producing documentation and visualizations for easier codebase understanding.

Open-source no-code platform for web data extraction, letting analysts turn any website into structured APIs through scraping, crawling, search, and AI-powered extraction.

Generates and maintains visual wiki documentation for codebases via CLI, producing agent-readable memory and explorable node graphs intended for both developers and coding agents navigating large projects.

Token-efficient image-to-3D tool that rebuilds objects from reference images as code-only, procedural, quality-gated Three.js models ready for animation for web developers and artists.

Gradio-based interactive interface for browser-use agents, supporting multiple LLMs and proprietary browsers to let users conveniently direct AI webpage tasks.

LLM-powered subtitling tool for video creators that handles transcription, sentence segmentation, correction, translation, and dubbing through both CLI and graphical interfaces.

An open-source cross-platform desktop tool that converts novels and scripts into animated short dramas, integrating AI scriptwriting, storyboarding, character creation, and video generation.

Collection of Google Colab notebooks for one-click deployment of Stable Diffusion WebUI, enabling hobbyists and researchers to generate images with text prompts, use ControlNet, and train LoRA models.

An offline-first, privacy-preserving English grammar checker written in Rust, offering millisecond-level checking across documents with integrations for multiple popular editors.

AI-native slide generation app built on Nano Banana Pro, letting presenters create decks from a single prompt with templates, conversational editing, and editable PPT export.

An AI-powered short-drama studio that automates the whole pipeline from one sentence to script, characters, storyboards, and final video.

Self-organizing AI knowledge base for Obsidian and Claude Code that ingests sources, links notes, and builds a Markdown-based graph for research, retrieval, and visual exploration.

Application for building datasets for LLM fine-tuning, RAG, and evaluation, offering document parsing, chunking, QA generation, cleaning, augmentation, assessment, and multi-format export in one workflow.

Neural-network-based green-screen keying tool that separates foregrounds while reconstructing true colors and linear alpha channels, exporting EXR for film compositing workflows.

Automated research assistant that turns research ideas into conference-level papers, integrating literature retrieval, experiment execution, and multi-agent review for researchers.

macOS-native video editor built for AI workflows, combining built-in AI video and image generation with MCP support so agents can operate the timeline directly.

Open-source autonomous driving simulator built on Unreal Engine, offering urban traffic assets and sensor simulation to support algorithm development, training, and validation.

Industrial-grade workspace for end-to-end AI film and video production. Lets creators generate, organize, and refine images and videos on a canvas using multiple controllable models.

Locally run voice-interactive AI companion supporting arbitrary LLMs, interruptible speech, and Live2D avatars, offering web and desktop modes for personal users and hobbyists.

Open-source Chrome extension using a personal LLM key to run multi-agent workflows. Automates webpage interactions for users seeking browser-based task automation without separate infrastructure.

A text-to-speech model and application suite that provides high-quality zero-shot voice cloning and voice design across more than six hundred supported languages.

An AI-powered app removing hard-coded subtitles and watermarks from videos and images locally.

A Gradio-based web UI for creators and developers combining speech recognition, translation, text-to-speech, and zero-shot voice cloning, plus YouTube downloading, vocal isolation, and audio processing tools.

Command-line tool and Python library for interacting with multiple LLMs, supporting prompts, chat sessions, embeddings, structured data extraction, and tool calls for developers and researchers.

Command-line AI assistant powered by GPT and other LLMs, helping terminal users generate shell commands, code snippets, and documentation while analyzing logs to improve productivity.

End-to-end AI video translation and dubbing application covering downloading, transcription, translation, voiceover, re-timing, and covers, supporting 100+ languages for creators and AI agents.

Single-file local inference suite for GGUF models with a KoboldAI interface supporting text generation, image handling, speech, and role-play scenarios without installation overhead.

On-device dictation app for macOS users prioritizing privacy, providing fast local speech-to-text transcription plus a custom-trained AI enhancement model as a local alternative to cloud services.

Open-source toolkit for computer vision engineers to visualize, curate, annotate, and evaluate datasets and models. Helps teams find data quality issues and improve model performance efficiently.

Self-hosted AI-assisted card note tool for quickly capturing and organizing ideas in Markdown, offering natural-language RAG search across devices for individual knowledge management users.

CLI and TypeScript SDK from OpenAI for finding, validating and fixing code security vulnerabilities, supporting policy generation plus batch scanning and remediation.

An open-source, agentic-first CRM built for AI agents to autonomously research leads, follow up, and write back records, while human operators review and manage customers through the interface.

Provides an open-source AI presentation generator and API that creates presentations from prompts or documents, allowing users to edit content and export editable PPTX and PDF slide decks.

AI image translation application that translates text inside manga and other images, supporting multiple languages with text removal, restoration, and automatic typesetting for comic readers.

Open-source AI-driven knowledge base system for building product docs, technical documentation, FAQs, and blogs, providing AI-assisted authoring, Q&A, and search for support and content teams.

Story creation workbench for novel, screenplay translation and interactive games, unifying Studio, TUI and CLI tools to manage settings, drafting, review, revision and multilingual delivery.

Open-source recommendation engine written in Go, supporting classic ranking, LLM reranking, and multimodal embeddings for developers adding personalization to online services.

Lightweight text-to-speech application that runs in real time on CPUs, supporting multiple languages, voice cloning and browser-based trials for accessible speech synthesis.

A Rust-centered multilingual document-parsing framework supporting conversion of 97+ formats into text, tables, and metadata, accessible through SDKs, CLI, REST, and MCP interfaces.

A locally run AI deep-research assistant integrating multi-source search across arXiv and PubMed with PDF parsing to generate cited reports with encrypted local storage.

An AI-focused browsing workspace with multi-window sessions, prompt management, and a built-in local terminal.

Runs GPT-2 live in the browser as an interactive educational visualization, letting users enter text and observe how Transformer components collaborate to predict subsequent tokens step by step.

Offers a desktop application for creators and hobbyists that converts images or text prompts into 3D models using local AI inference entirely on the user's GPU.

Turns LLM coding capabilities into image composition through a fine-tuned model and virtual canvas. Developers describe layouts in code, which the system then renders into generated images.

Command-line tool that generates commit messages from staged changes using large language models, supporting multiple model providers and local deployment options for developers.

Delivers an open-source office suite for editing real .docx, .xlsx, and .pptx files locally with a built-in AI agent, plus a CLI and agent skill for Claude Code, Codex, and Cursor.

Local-first desktop application that parses chat histories from multiple platforms and combines a SQL engine with AI agents for searchable statistics and visual insights.

LLM-based platform for extracting structured data from unstructured documents, letting users define schemas in natural language and deploy extraction as APIs or ETL pipelines producing JSON for downstream systems.

Scores job candidates by parsing PDF resumes and combining them with GitHub signals, producing explainable evaluations to assist human reviewers in early screening.

A private automatic work journal for Mac that uses AI to turn screen activity into timelines, standups, and searchable answers.

Voice assistant application bridging Xiaomi smart speakers with ChatGPT and other LLMs, supporting multi-model switching and TTS playback for voice Q&A and control.

Conversational text-to-SQL system based on LLMs and RAG that turns natural-language questions into SQL queries and charts, supporting multiple data sources and models for data analysts.

Self-hosted AI bookkeeping app that extracts and categorizes data from uploaded receipts and invoices using LLMs, supporting multi-currency and multi-project management for freelancers simplifying accounting and taxes.

Provides a full-stack AI red-teaming platform for security teams, scanning agents, skills, MCP servers, AI infrastructure, and evaluating LLM jailbreak resistance to secure AI ecosystems.

A native macOS open-source voice-to-text application providing offline AI dictation, global shortcuts, and context-aware transcription without subscription fees for fast hands-free writing across everyday workflows.

End-to-end production workspace for AI-generated short dramas, supporting script input, structured storyboarding, character consistency management, shot preparation, video generation, and final export.

Free CLI, OpenAI-compatible server, and interactive chat that run entirely on-device through Apple Intelligence on Mac, requiring no API keys, cloud access, or extra downloads.

Provides a general-purpose AIGC video pipeline from script to storyboard to finished film, aimed at creators producing dramas, advertisements, e-commerce videos, and otome games.

A live transcription app powered by Whisper that captions microphone and speaker audio in real time.

An AI-powered desktop studio that auto-generates marketing short videos with copywriting, voiceover, editing, and captions.

Provides an open-source AI video workspace that moves from fiction and character design through scripts and storyboards to finished video while preserving cross-shot character consistency.

Automates evaluation and optimization of retrieval-augmented generation pipelines in AutoML style, helping developers tune document QA systems for actionable, grounded answers.

Offers an agentic framework for users generating PowerPoint presentations, using reflective mechanisms to produce high-quality slides automatically from input content.