Projects sharing features with Corpora

OpenChat is a conversational AI agent builder and customer service automation platform that uses large language models to power customer support chatbots across multiple channels. It provides tools for defining AI agent behavior, training on custom knowledge, managing actions, and controlling autopilot responses per channel. The platform enables deploying AI agents on web, phone, email, SMS, and WhatsApp, with a unified inbox for managing conversations across all channels. It includes CRM synchronization, automated workflows, contact segmentation, and analytics for tracking customer satisfact

This is a full-featured chatbot framework and Next.js web application designed for integrating various large language model providers into a web interface. It serves as a template for building AI chatbots that can generate text and structured data through a unified interface. The project functions as an authenticated AI application, incorporating built-in user identity verification and session management. It includes a suite for AI tool integration, allowing language models to execute tool calls and generate structured objects by connecting to external data and functions. The framework provi

This project provides a Node.js AI client and a REST API wrapper designed to expose large language model capabilities as a web service. It includes a command line interface for direct interaction with models and a conversation state manager to track and persist chat history across sessions. The system features a reverse proxy gateway specifically designed to circumvent browser and web restrictions when programmatically accessing AI interfaces. It further allows for AI personality customization by injecting prompt prefixes and custom labels to control the behavior and tone of the model. The s

This project is a serverless application that integrates OpenAI models with the LINE messaging platform. It functions as a bridge to enable real-time conversations, text generation, image creation, and speech-to-text transcription within the messaging interface. The system is designed for cloud-native deployment on Vercel, utilizing serverless functions and webhooks to handle API traffic. It features environment-driven configuration to manage bot personalities, API secrets, and access controls such as user or group limits. Beyond basic chat, the assistant includes conversational orchestratio

OpenChat is an AI chatbot management platform used for building, deploying, and managing custom agents powered by large language models. It serves as an omnichannel customer support suite that integrates language model automation with communication channels including email, SMS, social media, and voice. The platform features a retrieval-augmented generation knowledge base integrator that ingests documents, websites, and codebases to provide context-aware responses. It includes a dedicated privacy layer for the detection and removal of sensitive personal and health information to maintain regu

Zhao is a research ecosystem and collaborative repository designed for the mapping and documentation of political elite networks. It consists of structured YAML kinship datasets and a system for converting these records into visual relationship charts and kinship trees. The project transforms raw relationship data into visual network maps rendered as PDF and JPEG images. This process utilizes graph visualization tools to compile structured data into downloadable assets that illustrate family connections and power networks. The framework supports collaborative open data curation through versi

PandaWiki is an AI-powered wiki and knowledge base platform that integrates large language models to automate content creation and information retrieval. It functions as a retrieval-augmented generation system for building technical wikis, FAQs, and documentation sites that provide automated answers grounded in a private knowledge base. The system acts as an enterprise knowledge bot, allowing the deployment of AI chatbots via web widgets and messaging applications like Discord. It further extends its operational capabilities by integrating with Model Context Protocol servers to connect the AI

Fiddle is an interactive API reference tool and playground environment for the Electron platform. It serves as a project prototyper and sandbox where users can explore, draft, and test application logic without the need to manually set up a full project structure. The tool distinguishes itself by allowing users to compile prototype experiments into distributable standalone binaries for Windows, macOS, and Linux. It also provides a mechanism to export these experiments into standalone project folders for continued development in a professional integrated development environment. The environme

(aka, code for Defending Against Neural Fake News)

Grav is a flat-file content management system that eliminates the need for a traditional database by storing site content and configuration in human-readable Markdown and YAML files. Built as a modular PHP web framework, it uses a hierarchical page routing system where the physical directory structure directly determines the site's URL paths. The platform is distinguished by its event-driven plugin architecture and a command-line interface that prioritizes system administration, deployment, and maintenance tasks. It utilizes a blueprint-driven system to generate administrative forms from stru

This project is a community-maintained directory that serves as a comprehensive index of software tools, frameworks, and educational materials. It functions as an open-source knowledge base, organizing diverse engineering domains and technical resources into a structured taxonomy to assist developers in discovering high-quality content. The directory distinguishes itself through a decentralized peer-review model, where independent contributors curate, verify, and update entries to ensure accuracy and relevance. All information is stored in a version-controlled, flat-file markdown format, whic

This project is a product support database and software version metadata registry that tracks release and discontinuation timelines for software and consumer electronics hardware. It provides a programmatic software lifecycle API for retrieving end-of-life and support dates via JSON. The project maps software products to standardized identifiers, including CPE, Repology, and PURL, to ensure cross-ecosystem identification. It also includes a runtime compatibility mapper that matches software versions to their minimum required compatible runtimes and dependencies. The system transforms lifecyc

PyWebIO is a Python web application framework and script-based UI library that allows the construction of interactive web interfaces without writing HTML, CSS, or JavaScript. It treats the web browser as a rich terminal, translating Python function calls into UI elements and capturing user input through a synchronous request-response loop. The framework functions as an asynchronous web app server that executes user sessions as coroutines to handle multiple concurrent interactions on a single thread. It also serves as a data visualization interface, enabling the direct rendering of interactive

This project is a public health dataset providing historical and real-time COVID-19 case and death counts across the United States. It consists of a collection of CSV files containing time-series pandemic data organized by date, state, and county. The dataset includes specialized records for institutional outbreaks, tracking infection and death rates within correctional facilities, colleges, and universities. It also provides statistics on excess mortality to estimate total pandemic impact and survey-based data on mask usage prevalence across different counties. To facilitate geographic anal

Helpy is a customer support platform and omnichannel help desk designed to manage support tickets, knowledgebases, and community forums. It functions as a centralized hub that converts emails into trackable tickets and provides a web interface for support agents. The system includes an embeddable support widget for external websites that connects users to agents or AI chatbots. It also serves as a self-service knowledge base for hosting searchable help articles and as an identity integrator for connecting users to external providers via single sign-on protocols. The platform covers a broad r

Data on COVID-19 (coronavirus) cases, deaths, hospitalizations, tests • All countries • Updated daily by Our World in Data

SecurityAdvisories is a software composition analysis tool and PHP security advisory database used to audit project dependencies against known security flaws and CVEs. It functions as a vulnerability scanner for PHP projects to identify and manage risky third-party libraries. The project implements a system for detecting and blocking vulnerable dependencies during the software development lifecycle. It prevents the installation of software packages with known security flaws by maintaining an exclusion list of forbidden versions. The tool integrates with the PHP package manager to intercept d

This project is a curated repository of technical learning materials and a personal knowledge base. It consists of version-controlled Markdown summaries covering software architecture, engineering literature, research papers, and professional talks. The collection functions as a digital garden, using bidirectional linking and cross-references to map relationships between technical concepts. Content is distilled from various sources, including technical books, conference talks, and foundational computer science papers, into concise summaries to facilitate recall and study. The system is organ

This project is a themed technical art collection and visual archive of stylized illustrations depicting computer science literature. It serves as a technical book illustration gallery that pairs anime-style characters with specific programming and technical textbooks. The repository functions as a static technical asset library, utilizing a JSON-driven image gallery to map visual assets to their corresponding metadata. This structured approach allows for the sourcing of theme-consistent artwork for use in developer blogs, presentations, and technical documentation. The system employs a resp

Novel-Plus is a content management system and online reading platform designed for hosting, managing, and distributing web novels across PC and mobile web interfaces. It provides a comprehensive environment for web novel publishing, featuring a multi-platform reader with bookshelves, customizable themes, and community commenting systems. The platform integrates an automated content crawler to gather and update literary data from external remote sources and employs a scalable text storage system using database sharding and flat files to handle large volumes of content. It also includes an inte

This project is a developer onboarding tool and GitHub issue discovery portal. It serves as a curated directory and contribution guide designed to match new programmers with beginner-friendly open source tasks based on their technical skills and experience level. The platform operates as a static project directory, using a serverless catalog of repositories stored in JSON files. It provides the ability to filter tasks by programming language and difficulty, enabling users to identify approachable starting points in active software projects. The system includes capabilities for repository cur

This project is a framework for building custom AI chatbots capable of PDF document analysis. It implements Retrieval Augmented Generation to connect a large language model to private document data. The system utilizes graph-based agent orchestration to control conversation flow and decision logic. It maintains context across interactions through thread-based state management and delivers AI responses to the user interface via real-time streaming. The project covers PDF document ingestion through chunk-based processing and vector-store retrieval. It includes mechanisms for query-based data r

EasyImages2.0 is a self-hosted, database-less image hosting platform. It stores files directly on the server and generates shareable links without requiring a relational database, utilizing flat-file metadata storage and filesystem-based content mapping. The platform includes a centralized web management interface for organizing uploaded media and monitoring site statistics. It features an integrated image processing gateway that automatically resizes, compresses, and converts image formats during the upload process, and can apply custom watermarks to protect ownership. Additional capabiliti

This project is a public health data repository and open government data archive. It provides structured historical records, daily updates on infection trends, and official epidemiological statistics for pandemic monitoring. The resource includes geospatial health data, such as standardized mapping files and administrative boundary data used to visualize regional health restrictions and emergency measures. It also serves as a monitor for public health spending by publishing records of government supply contracts related to emergency health responses. The system utilizes a decoupled data dist

This project is a self-hosted project management platform and collaboration tool designed for private deployment on owned servers. It provides a workspace for tracking tasks and issues, utilizing a container-based application stack to orchestrate the deployment of backend services and databases. The platform functions as a unified workspace that synchronizes data from GitHub repositories and integrates Gmail accounts. It incorporates conversational AI chatbots and translation tools for automated text and voice interactions, alongside a real-time communication hub featuring audio and video cal

xtuner is a comprehensive training engine for large language models, offering a toolkit for pre-training, supervised fine-tuning, and the optimization of vision-language multimodal models. It serves as a distributed training accelerator and a specialized framework for scaling Mixture-of-Experts models and aligning model behavior through reinforcement learning from human feedback. The project distinguishes itself through advanced memory and compute optimizations, such as sequence parallelism for ultra-long context windows and interleaved pipeline parallelism to reduce GPU idle time. It provide