Open-source alternatives to Paper2Slides

Presenton is an AI-powered presentation engine and API designed to transform natural language prompts, uploaded documents, and structured data into professional slide decks. It functions as a generation service that leverages large language models to automate the creation of outlines, slide content, and visual assets. The system is distinguished by its support for both cloud-based and self-hosted infrastructure, allowing for the integration of local language models and image generators to ensure data privacy. It implements a Model Context Protocol server, enabling external AI agents to trigge

Swirl Search is an AI-powered middleware engine designed for federated enterprise search and retrieval-augmented generation. It functions as a unified platform that aggregates search results from multiple internal data sources and applications simultaneously, allowing users to query disparate knowledge bases without requiring data migration or indexing. The platform distinguishes itself by using a modular pipeline architecture to transform queries and synthesize information into grounded natural language answers. It employs semantic re-ranking and vector similarity to normalize results across

This project is a machine learning research automation system designed to manage the full research lifecycle, from idea discovery to final paper submission. It utilizes markdown-based skill templates to execute autonomous research tasks and manage iterative loops of deep review and experimentation. The system distinguishes itself through integrated capabilities for academic communication and integrity auditing. It can automate the generation of LaTeX papers, conference slide decks, and evidence-grounded peer review rebuttals. To ensure rigor, it employs cross-model review routing and adversar

Vizro is a low-code Python framework for building production-ready data visualization applications. It functions as a UI orchestrator that allows users to define multi-page analytical dashboards through structured configurations in Python, YAML, or JSON, reducing the need for extensive frontend engineering. The project distinguishes itself through generative AI integration, utilizing a model context protocol server to translate natural language descriptions into validated dashboard configurations, charts, and layouts. It also features a decoupled data cataloging system that separates data sou

Blinko is a personal knowledge management system and an LLM-powered knowledge base that enables users to capture and organize thoughts through a bi-directional knowledge graph. It functions as a RAG-enabled note-taking application and a self-hosted Markdown editor, allowing for the creation of permanent documentation and fleeting notes. The project distinguishes itself by integrating retrieval-augmented generation to provide conversational querying and AI-powered analysis of private document libraries. It supports both cloud-based and local AI model integration, enabling users to perform sema

Open Design is an AI design orchestration platform and LLM agent workspace designed for generating prototypes, presentations, and motion graphics. It functions as a local-first environment that integrates various command-line AI agents and coding tools into a unified design workflow, allowing users to migrate design specifications into brand-compliant source code. The project is distinguished by its ability to enforce visual consistency through a design system manager that defines brand contracts and tokens using Markdown. It features a specialized motion graphics generator that converts HTML

Flowise is a low-code platform designed for building and deploying complex language model workflows through a visual, node-based interface. It functions as an orchestrator for autonomous multi-agent systems, allowing users to construct conversational pipelines by connecting language models, memory stores, and external tools on a drag-and-drop canvas. The platform distinguishes itself through its support for sophisticated agentic patterns, including supervisor-worker delegation and iterative reasoning strategies. Users can design directed acyclic graphs to manage conditional branching, state p

Baserow is a no-code relational database and application builder that allows users to create structured data tables and business tools through a visual interface. It functions as a headless REST API data backend and a self-hosted data workspace, providing a platform for managing collaborative databases while maintaining full control over data residency. The platform integrates large language models to serve as an LLM-powered data platform, capable of generating database structures, record content, and technical workflows from natural language. It also acts as a Model Context Protocol server,

Webstudio is a visual CMS and website builder that provides a visual development environment for designing and publishing websites. It functions as an AI-powered design tool, a REST and GraphQL API client, and an atomic CSS compiler. The platform distinguishes itself through generative AI capabilities for creating layout variants and refining visual styles from text prompts. It integrates a headless CMS workflow that maps external data sources to visual components and utilizes a specialized compiler to convert design tokens into deduplicated atomic CSS for optimized page load speeds. The sys

Viewers is a zero-footprint DICOMweb medical imaging viewer and a modular plugin framework. It serves as a diagnostic interface for rendering 2D and 3D medical images, providing a web-based clinical workflow engine to automate image layouts and toolsets. The project distinguishes itself through a highly extensible architecture that allows for the development of custom clinical workflows, specialized viewing modes, and the integration of external functional extensions. It includes a dedicated command line interface for managing these plugins and supports white-labeling through a comprehensive

This project provides a comprehensive architectural framework and set of standardized patterns for building, securing, and scaling production-ready Node.js applications. It serves as a foundational guide for establishing consistent development workflows, operational observability, and reliable service integration across distributed software systems. The framework distinguishes itself by emphasizing a schema-first approach to API development, ensuring that interface definitions drive the creation of server stubs, client libraries, and type definitions. It promotes a cloud-native posture by int

Pdfcraft is a containerized service for self-managed PDF processing, editing, and conversion. It provides a toolkit for document manipulation, a multi-format converter, and OCR software to transform scanned documents into searchable and editable text. The project features a visual, node-based workflow editor that allows users to build automated pipelines by chaining together various PDF conversion and optimization operations. The service covers a broad range of capabilities, including document management for merging and splitting files, format conversion between PDFs and office documents or

Query Server is a federated search gateway and multi-engine aggregator that dispatches search requests across multiple external web platforms simultaneously. It collects comprehensive results through a unified endpoint, consolidating information from diverse search engines into a single response. Beyond aggregation, the service transforms retrieved search data dynamically into multiple structured output formats including JavaScript Object Notation, Extensible Markup Language, and comma-separated values based on incoming client request parameters. It also automatically records executed search

This project is a comprehensive collection of tutorials and guided laboratories designed to teach containerization, networking, and security using Docker. It serves as a learning path for building portable images and executing isolated processes. The materials provide specific guides for managing container clusters and scaling services through Docker Swarm and overlay networks. It includes a security handbook for implementing image scanning and secret management, as well as laboratories dedicated to modernizing legacy applications by wrapping older software installers into containers. The co

Relax is a headless content management system and visual website builder. It allows for the creation and organization of digital content delivered via a GraphQL API to a React frontend, utilizing a component-based visual editor to construct web pages and layouts without writing manual code. The platform integrates a dockerized content manager for simplified deployment and uses a schema-driven approach to structure data architecture and entry types. It features a dynamic administrative experience built with React and Redux to manage site states and user interfaces. The system provides broad c

Bustag is a containerized media library manager and automated metadata aggregator. It serves as a centralized database for tracking digital assets, utilizing machine learning models to act as a predictive content filter that identifies and recommends media based on user preferences. The system distinguishes itself through a supervised preference modeling workflow, where users manually label assets as liked or disliked to train predictive models. These models then automate content curation and personalized recommendations by analyzing labeled datasets. The platform integrates web data aggrega

AzurLaneAutoScript is a mobile game automation system designed to perform repetitive gameplay tasks unattended. It functions as a screenshot-driven bot that controls Android devices, emulators, and cloud phones via ADB and uiautomator2, using computer vision to make interaction decisions instead of fixed timers. The project distinguishes itself through an advanced computer vision suite that includes local optical character recognition and perspective-aware grid detection. These tools allow the bot to parse 3D game maps, compute vanishing points, and normalize grid-centered objects for precise

This project is a retrieval-augmented generation pipeline designed for building custom ChatGPT plugins that allow language models to query private or professional documents. It implements a full retrieval workflow, from processing and indexing document chunks to retrieving relevant context for natural language queries. The system distinguishes itself through a hybrid retrieval approach that combines dense vector embeddings with sparse keyword matching, further refined by a two-stage semantic re-ranking process. It includes specialized data privacy tools for screening personally identifiable i

eShopOnWeb is a reference application for ASP.NET Core that demonstrates a sample e-commerce site. It serves as a template for building scalable services using domain-driven design to separate business logic from infrastructure and data access. The project implements a decoupled messaging pattern through a request pipeline to separate web controllers from application logic. It utilizes a repository pattern to abstract data persistence and isolate the core application logic from the specific database storage mechanism. The application covers a broad surface of web capabilities, including user

Gekko is a Node.js trading platform and automated Bitcoin trading bot designed to execute buy and sell orders across multiple cryptocurrency exchanges. It functions as an algorithmic trading system that uses a standardized exchange integration gateway to connect with various external trading platforms. The system includes a backtesting engine that simulates trading strategies against historical market data to evaluate performance before live deployment. It employs an adapter-based integration model to normalize diverse exchange API responses into a consistent internal format. The platform pr

This project is a wireless hotspot management interface for Debian devices. It provides a web-based controller for managing wireless access points, wireless repeaters, VPN gateways, and DNS ad-blocking filters. The system includes a captive portal framework to intercept network traffic via customizable splash pages and a VPN controller that supports WireGuard and OpenVPN with kill-switch functionality. It further differentiates itself with a DNS ad-blocking filter using curated blacklists and the ability to operate in multiple network modes, including bridged access point and wireless repeate

Knowledge Repo is a technical content management system designed for organizing and sharing research, professional guides, and technical documentation. It functions as a collaborative technical wiki and knowledge base that supports the curation of insights using notebooks and markdown files. The platform synchronizes with version control to automate content publishing by detecting commits and changes pushed to a connected Git repository. This integration allows the system to manage markdown content and technical posts through a version-control-integrated workflow. The system includes tools f

This project is a diffusion-based AI art generator and animation framework used to create digital images and motion graphics from text prompts. It functions as a system for producing stylized videos and AI art through iterative diffusion sampling and neural network models. The framework distinguishes itself through specialized tools for 3D depth animation, using depth-map transformations to create spatial movement. It also includes neural style transfer capabilities to apply specific artistic looks, such as watercolor or pixel art, and utilizes optical flow frame blending to reduce flickering

This project is a conversational AI bot that integrates large language models into WeChat accounts to provide automated responses in private and group chats. Built on the WeChaty bot framework, it functions as a bridge that enables real-time conversational interactions between a messaging account and an AI model. The system acts as an AI multimedia gateway and context manager, supporting the generation of images from text and the transcription of audio files within the chat interface. It tracks interaction histories to manage token limits and maintains coherent conversations through custom sy

acme-dns is a DNS server and protocol manager designed to proxy TXT records for ACME DNS-01 challenges. It enables the validation of domain ownership for automated certificate issuance without exposing primary DNS zone files or credentials to external clients. The project utilizes CNAME-based delegation to offload verification from a primary zone to a specialized server. It provides a REST API for programmatically updating short-lived validation tokens, which is secured through CIDR-based network restrictions and automated TLS provisioning for the API interface. The system supports stateless

This project is a Telegram bot that integrates large language models, such as OpenAI and Claude, to provide an AI chat interface within the messaging app. It functions as a multi-model AI gateway that routes prompts to various providers via API keys and YAML configurations. The implementation includes a provider-agnostic routing system and response streaming to deliver text word-by-word. It distinguishes itself with a token-based cost tracker that calculates the monetary expenditure of API requests and a whitelist-based access control system to restrict usage to authorized users. The bot sup

Log Lottery is a 3D lottery draw application used for virtual giveaway management and selecting winners from participant lists. It functions as a web-based prize manager that allows users to define prize rules, eligibility criteria, and winner counts. The tool features three-dimensional animations to announce winners, complemented by a customization suite for updating background images and audio tracks. It is provided as a containerized application to ensure consistent installation and operation across different hardware environments. The system includes utilities for participant administrat