Open-source alternatives to Spyglass

Epicenter is a local-first knowledge management system and data orchestrator designed to structure information generated by large language models into validated schemas. It functions as a storage architecture that persists application data in human-readable files and databases to ensure user ownership and portability. The system distinguishes itself by projecting language model outputs into structured, schema-validated tables and utilizing conflict-free replicated data types to synchronize application state across multiple devices without a central server. This allows for offline access and c

Monolith is a single-file HTML web archiver and asset bundler. It functions as a command-line interface and programmatic library designed to save complete web pages and their associated assets into a single HTML file for offline viewing. The tool crawls URLs to discover and fetch linked stylesheets, scripts, and images, which are then embedded into the document as data URLs. It includes capabilities for session injection via external cookie files and authentication handling to backup protected or member-only content. The project covers broader functional areas including automated web scrapin

dn is a self-hosted personal web archiving system that automatically intercepts and stores web pages on a local device. It uses a proxy-based request interception model to capture browser traffic and save content for offline access without an internet connection. The system features a local full-text search engine that indexes all saved page content for information retrieval across the collection. It includes a dedicated browser interface that simulates online connectivity to serve archived files, mimicking the original live web environment. Administrative control is provided through a web-b

dn is a local browser data archive and web archiver designed to save and render web pages from Chromium browsers for offline viewing and permanent storage. It functions as a self-hosted repository for browsing history and page content, operating as an offline web content server that hosts saved data as if the original sites were still online. The system includes a full-text search engine that indexes all saved web pages, enabling the instant recovery of specific information across the local collection. It utilizes a domain-based filtering system to block specific website addresses from being

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

Notable is a local-first markdown note taking application and document manager. It functions as a personal knowledge base that persists notes as plain text files on the local disk to ensure data portability and user ownership. The application provides a markdown editor featuring a split-pane live preview for real-time rendering of content, including mathematical expressions and diagrams. Information is organized through a hierarchical tagging system that allows for nested labels and multi-dimensional categorization. The software includes tools for bulk note management to apply operations acr

Notesnook is a cross-platform note-taking application designed for private knowledge management. It functions as a secure personal information manager that prioritizes user data confidentiality by employing client-side end-to-end encryption for all stored notes, attachments, and metadata. By utilizing a local-first synchronization model, the application ensures that information remains accessible offline while maintaining a consistent state across desktop and mobile devices. The platform distinguishes itself through a focus on privacy-centric organization and secure information handling. User

Karakeep is a self-hosted, open-source platform designed for personal knowledge management and web content archiving. It functions as a centralized repository where users can capture, organize, and preserve bookmarks, notes, and media files, ensuring long-term access to digital information even if original sources are removed or modified. The system distinguishes itself through its automated content processing and security-focused architecture. It utilizes headless browser crawling and optical character recognition to ingest and index web content, while a modular artificial intelligence pipel

Boostnote is a local-first note management system and markdown text editor designed for personal knowledge management. It functions as a desktop application that reads and writes markdown files directly to the local disk, allowing for the creation of a searchable personal knowledge base and digital garden. The application provides a writing interface that renders markdown syntax in real time. It is used to organize fragmented information, maintain project documentation, and author structured technical guides.

Trilium is a hierarchical personal knowledge base and digital garden tool designed to organize information into a tree of linked nodes. It functions as a JavaScript programmable wiki and a self-hosted note server, allowing users to maintain a private database of documents synchronized across multiple devices. The platform distinguishes itself through an embedded scripting engine for automating tasks and a REST API that exposes internal data and actions to external tools. Users can further extend the system by modifying the user interface layout and styling through a custom theme engine. The

This project is a technical reference knowledge base and developer cheat sheet repository. It functions as a searchable collection of quick-reference guides, CLI command patterns, and code snippets for various operating systems, cloud platforms, and infrastructure tools. The system operates as a markdown-based technical knowledge base, where content is stored in plain text files and rendered as a static site. This approach enables a personal knowledge management system that utilizes version control and a directory-based navigation hierarchy to organize technical notes for long-term retrieval.

Neorg is a knowledge management framework for Neovim designed for organizing notes, tasks, and structured data using a custom hierarchical text format. It functions as a personal knowledge base and a system for generating structured text documents. The framework integrates project management and time tracking directly into the editor environment. It enables the creation of typeset documents and professional slideshow presentations by converting raw structured text into formatted visual layouts. The system covers a broad range of productivity capabilities, including personal knowledge managem

This project is a community-curated directory of open-source software designed for deployment in private server environments and home labs. It serves as a comprehensive resource for discovering independent, self-hosted alternatives to mainstream cloud services, enabling users to maintain full data ownership and control over their digital infrastructure. The directory is structured through a hierarchical taxonomy that organizes a vast collection of applications into logical categories, ranging from media management and data analytics to private communication and team productivity tools. It dis

markdown-clipper is a browser extension that converts website content into markdown files for offline storage and personal knowledge bases. It functions as a content extractor and HTML to markdown converter that removes layout clutter to isolate primary text. The tool includes a specific integration for sending clipped web content directly into vaults and folders within the Obsidian note-taking application. It also supports batch processing to convert all open browser tabs into individual markdown files. The extension covers a broad range of extraction capabilities, including capturing selec

Hyper-Extract is a framework designed for automated knowledge extraction, graph construction, and retrieval-augmented generation. It functions as a command-line tool that transforms unstructured text into structured knowledge graphs and hypergraphs, enabling users to build interconnected, searchable, and machine-readable data repositories from their documents. The system distinguishes itself through its focus on personal knowledge management and incremental processing. It allows users to update existing knowledge bases by processing only new document deltas, avoiding redundant computation. Th

This project is a self-hosted personal information manager and private dashboard. It serves as a centralized web application for aggregating personal data, including finances, schedules, contacts, and goals, within a private database. The system functions as an encrypted password manager for secure credential storage, a personal finance tracker for monitoring spending and product prices, and a personal knowledge base for categorized research, notes, and travel plans. It also maintains a historical record of personal achievements and life accomplishments. The application provides tools for pe

Dokploy is a self-hosted platform-as-a-service designed to simplify the deployment and management of containerized applications and databases. It provides a centralized control plane that decouples administrative management from application workloads, allowing users to oversee infrastructure across multiple server nodes through a unified web interface or a command-line tool. The platform distinguishes itself through an extensive library of pre-configured application templates, enabling the rapid deployment of databases, identity providers, and various productivity or development tools. It sup

Buku is a personal bookmark manager that provides a command line interface, a portable bookmark database, and a self-hosted server for organizing web links. It functions as a command line knowledge base for saving, tagging, and searching web resources. The system features a portable, mergeable database that supports AES-256 encryption and is designed for cross-device data synchronization. It includes a RESTful API and a self-hosted web interface, allowing users to manage their collection via a browser or programmatic requests. Capabilities include automatic metadata fetching to populate page

Deep Searcher is an open-source retrieval-augmented generation engine that indexes private documents into a vector database and uses large language models to answer complex questions with cited reasoning. It functions as both a command-line interface and a web API research tool, enabling users to load data and generate comprehensive reports by combining indexed private information with LLM-powered analysis. The system distinguishes itself through a plugin-based provider architecture that supports multiple embedding models, LLM providers, vector databases, and file loaders as interchangeable c

Electric is a Postgres data synchronization engine and replication proxy designed to enable local-first software. It replicates data from Postgres databases to client-side stores in real time using logical replication, allowing applications to maintain a local embedded database for offline access and low-latency updates. The system distinguishes itself by using shapes to filter and authorize specific subsets of database rows and columns before streaming them to clients or edge workers. It further supports multi-user collaboration by integrating a conflict-free replicated data type framework t

Publii is a local static site generator and offline content management system. It operates as a desktop application that renders content into HTML files on a local machine, removing server-side vulnerabilities and eliminating the need for a live database or active internet connection during the authoring process. The system is distinguished by a focus on privacy and search engine optimization. It includes built-in tools for GDPR compliance, such as cookie consent management and the ability to restrict third-party embeds until user consent is provided. For visibility, it automates the generati

FreeTube is a privacy-focused desktop application for watching YouTube videos without ads, tracking cookies, or the requirement of a Google account. It functions as a local-first subscription manager that tracks channels and playlists in local files instead of a centralized cloud account. The application avoids tracking-heavy official APIs by using a content extractor that parses web pages directly. To further protect user identity, it can route network traffic through proxies or Tor to mask the hardware IP address. The software provides tools for distraction-free viewing, including the abil

LLocalSearch is a privacy-focused search engine and agent framework that uses locally hosted large language models to search the internet and aggregate answers. It functions as a retrieval augmented generation interface where all queries and processing remain on the user's own hardware to ensure data privacy and remove dependency on external cloud API providers. The system employs a chain of autonomous agents that perform recursive internet searches, calling search tools multiple times to gather and synthesize information. It coordinates these models to reason through complex queries, providi

Openwork is an LLM agent orchestration platform and cross-platform desktop application designed for building and running automated workflows. It serves as a local AI agent host and session manager, allowing users to connect local project folders to various large language models and remote cloud workers. The project distinguishes itself through a local-first execution model that enables agents to process files directly on a host machine. It implements human-in-the-loop permissioning to intercept agent resource requests, requiring explicit user approval before accessing specific local system fi

Cashew is a local-first budgeting application and personal finance tracker designed to log income and expenses across multiple accounts. It functions as a multi-currency expense manager and personal net worth dashboard, storing financial records in an on-device database to ensure private financial data storage. The project distinguishes itself through a focus on privacy and flexibility, offering optional personal cloud synchronization for multi-device access and biometric security to protect sensitive information. It features a currency conversion engine that calculates total values across di

Blossom is a self-hosted, containerized note-taking application designed for private knowledge management. It functions as a centralized repository for personal documentation, allowing users to maintain full ownership of their data by hosting the platform on their own server infrastructure. The application centers on a markdown-based productivity workflow that synchronizes plain-text files across multiple devices. By utilizing a local-first state management model, it ensures immediate interaction with files while asynchronously reconciling changes through a private server backend. This approa

Dash-iOS is a mobile documentation reader and technical reference library designed for Apple devices. It functions as an offline browser that allows users to store, view, and search technical reference materials locally on their device. The application provides a local-first approach to documentation storage, enabling users to access API guides and technical manuals without an active internet connection. It utilizes a local search index and metadata management to facilitate rapid lookups and navigation across stored documentation sets.