Open Source TypeScript Library Management Software

Open Science is an open-source, local-first AI research workbench built for scientific discovery on macOS, Windows, and Linux. Researchers can describe a task in plain language and let an agent inspect files, execute Python or R, search the web, and call scientific data connectors. The system is model-agnostic, allowing users to connect supported providers, compatible gateways, or subscription-based backends. It produces reproducible reports, tables, figures, and other artifacts inside a unified project workspace. Users can inspect tool activity, approve sensitive actions, branch earlier conversations, and compare alternative research paths without losing prior work. Immutable artifact versions and detailed provenance connect results to code, inputs, execution history, environment evidence, conversation context, and review findings.

Device Activity Tracker is a platform created to monitor and log the activity of digital devices across networks, giving users visibility into usage patterns, connection events, app launches, and interaction timelines that can be applied for security monitoring, parental oversight, productivity tracking, or device lifecycle analytics. It integrates with devices via sensors or APIs, continually capturing activity metrics and reporting them to a centralized dashboard that visualizes patterns over time, highlights anomalies, and correlates events across systems or users. Because it is designed with privacy and transparency in mind, the tracker offers configurable retention policies and granular consent controls, ensuring administrators can tailor what gets logged and how long data is stored.

OpenScience is an open-source AI workbench for scientific research. It lets users give an agent a research goal, then have it read literature, form hypotheses, write and run code, run experiments, analyze results, and write up findings. The workspace runs in the browser and includes a file tree, editor, terminal, session history, and scientific rendering for molecules, structures, genomes, and plots. It supports frontier, open-weight, and local models through bring-your-own-key provider configuration. The project includes research agents, domain specialists, critique agents, literature-review agents, and more than 290 scientific skills. OpenScience is especially useful for machine learning, biology, physics, chemistry, and research automation workflows that need tool use and provenance.

Agentero is an open-source research workspace that connects academic literature management, note-taking, and AI agents in a unified desktop application. It provides PDF reading, highlighting, annotation, and full-text searching. Scientific papers can be converted into structured Markdown and LaTeX, including formulas and tables, for improved AI interpretation. Its bidirectional Markdown notes maintain links between research materials and recorded insights. Users can query documents through local AI agents or external MCP-compatible applications. Literature discovery tools support academic feeds, arXiv recommendations, and citation tracking. Agentero integrates with Zotero for library migration and bibliographic exports. Research files remain accessible in standard local folders, with optional S3 synchronization and command-line automation across Windows, macOS, and Linux.

ArchiveWeb.page is a free, open-source web archiving application designed to capture and preserve interactive websites with high fidelity. It operates as a Chrome or Chromium browser extension and a standalone Electron desktop application. Users can record websites while browsing, preserving page content and associated network resources. The system uses Chrome's debugging protocol to capture network traffic during recording sessions. Archived content is stored locally through the browser's IndexedDB storage system. Integrated replay functionality allows users to revisit preserved websites without relying on the original servers. The application builds on ReplayWeb.page and wabac.js for archive playback. Its desktop edition also supports archived Flash content and additional sharing capabilities.

Maths, CS & AI Compendium is an open educational project that explains mathematics, computing, and artificial intelligence from foundational concepts through advanced engineering topics. It favors intuition, practical context, and connected explanations over dense textbook notation. Its chapters cover vectors, matrices, calculus, statistics, probability, machine learning, language processing, computer vision, speech, multimodal learning, robotics, and graph neural networks. It also addresses operating systems, algorithms, production software, GPU programming, AI inference, and ML systems design. Readers need only elementary mathematics and basic Python knowledge to begin. A bundled MCP server lets compatible AI assistants use the locally cloned compendium as a knowledge base. The repository is useful for self-study, interview preparation, and deeper AI research engineering training.

PageLM is an open-source AI-powered education platform that transforms study materials into interactive learning experiences inspired in part by the NotebookLM style of knowledge interaction. It is built to help students, educators, and researchers turn documents and topics into more engaging forms of study rather than leaving content in static notes or isolated files. The platform includes a broad set of learning tools such as contextual chat, Cornell-style note generation, flashcards, quizzes, AI podcasts, voice transcription, homework planning, exam simulation, debate practice, and a personalized study companion. It supports uploaded documents including PDF, DOCX, Markdown, and TXT, allowing users to ground questions and generated materials in source content. On the technical side, it supports multiple model providers, multiple embedding back ends, WebSocket streaming for real-time generation, persistent content storage, and structured markdown outputs.

Qualify is a lightweight micro-CRM prototype and automation framework geared toward helping small teams and individual users manage leads, tasks, customer interactions, and simple sales pipelines without the overhead of traditional enterprise platforms. Rather than trying to replicate every feature of a full CRM suite, it focuses on core workflows like capturing leads, tracking stages, logging interactions, and generating reminders or alerts for follow-ups so that users spend more time building relationships and less time navigating interface complexity. Built with simplicity and extensibility in mind, the project includes REST APIs, database models, and a user interface that can be extended or embedded into existing internal systems. Because it prioritizes lean data structures and predictable code paths, developers can customize pipelines, fields, and behaviors to align with their unique business logic.