awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
WorldBrain avatar

WorldBrain/Memex

0
View on GitHub↗

Memex

Memex is a browser extension knowledge base and personal information manager designed for indexing, annotating, and organizing web content into a searchable personal archive. It functions as a web annotation tool that allows users to add highlights and notes directly to webpages and PDFs.

The system features an AI-powered document summarizer that generates concise answers and summaries based on indexed materials using cited references. It includes an encrypted content synchronizer that uses end-to-end encryption to mirror archives and annotations across multiple devices.

The platform provides capabilities for full-text search and filtered content retrieval across bookmarked sites and documents. It covers content management through browser tab organization and automated tagging, as well as data persistence via local-first storage and cloud backups.

The project provides standardized APIs to connect saved knowledge to external tools and AI agents for interoperable information sharing.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
worldbrain.io
↗

Features

  • Personal Information Managers - Provides a digital library for organizing and curating personal web fragments and documents.
  • Web Page Annotation Highlighters - Allows users to add highlights and notes directly to webpages and PDFs without leaving the browser.
  • Personal Knowledge Management - Creates a searchable digital library of web pages and PDFs with personal notes and organized tags.
  • Content Organization Systems - Categorizes and bookmarks web fragments and documents to structure a personal digital library.
  • Full Text Search - Enables full-text keyword retrieval across all saved webpages and documents in the personal archive.
  • Local-First Persistence - Stores curated content and annotations on the local device first to ensure offline capability.
  • Full Text Indexing - Parses and stores the raw text of saved webpages and PDFs for keyword-based retrieval.
  • Web Content Indexing - Captures websites, PDFs, and media to create a searchable archive of online materials.
  • End-to-End Encryption - Protects user data during cross-device synchronization by encrypting information locally before uploading to cloud storage.
  • Encrypted File Synchronization - Syncs personal archives and annotations across devices using end-to-end encryption.
  • Knowledge Base Extensions - Provides a browser extension for indexing, annotating, and organizing web content into a searchable archive.
  • Browser Extension Overlays - Injects annotation and highlighting overlays directly into the active web page DOM via a browser extension.
  • AI Knowledge Management - Connects a personal web archive to AI agents to summarize and query saved information.
  • External Knowledge Integrators - Provides standardized protocols to share saved personal knowledge with external tools and AI agents.
  • Knowledge Base Search Filters - Provides advanced filtering by time, domain, and tags to refine full-text searches across saved content.
  • Knowledge Interoperability APIs - Exposes saved knowledge to external AI agents through a consistent protocol for interoperable information sharing.
  • Automated Content Categorization - Applies categorization labels to content feeds by matching incoming data against user-defined patterns.
  • AI-Powered Web Summarization - Generates concise summaries and answers questions based on indexed web materials using cited references.
4,723 stars·354 forks·TypeScript·36 views

Star history

Star history chart for worldbrain/memexStar history chart for worldbrain/memex

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does worldbrain/memex do?

Memex is a browser extension knowledge base and personal information manager designed for indexing, annotating, and organizing web content into a searchable personal archive. It functions as a web annotation tool that allows users to add highlights and notes directly to webpages and PDFs.

What are the main features of worldbrain/memex?

The main features of worldbrain/memex are: Personal Information Managers, Web Page Annotation Highlighters, Personal Knowledge Management, Content Organization Systems, Full Text Search, Local-First Persistence, Full Text Indexing, Web Content Indexing.

Which projects share features with worldbrain/memex?

Projects with overlapping indexed features include: awesome-selfhosted/awesome-selfhosted — This project is a community-curated directory of open-source software designed for deployment in private server… linsa-io/linsa.io — Linsa.io is an end-to-end encrypted cloud storage service and zero-knowledge data vault. It functions as a private… pirate/archivebox — ArchiveBox is a self-hosted web archiving system designed to capture and preserve permanent static copies of webpages,… asciimoo/hister — Hister is a self-hosted personal search engine that builds a full-text archive of the web pages you visit and the… remotely-save/remotely-save — Remotely Save is a cloud storage synchronization tool and backup manager designed to keep local files and application… huichen/wukong — Wukong is a distributed full-text search engine designed for indexing and retrieving text documents. It functions as a…

Projects sharing features with Memex

These projects share indexed features with Memex. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • awesome-selfhosted/awesome-selfhostedawesome-selfhosted avatar

    awesome-selfhosted/awesome-selfhosted

    334,819View on GitHub↗

    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

    awesomeawesome-listcloud
    View on GitHub↗334,819
  • linsa-io/linsa.iolinsa-io avatar

    linsa-io/linsa.io

    16,880View on GitHub↗

    Linsa.io is an end-to-end encrypted cloud storage service and zero-knowledge data vault. It functions as a private content sharing platform that encrypts files and data on the client side, ensuring only the owner can access the stored content. The project employs a local-first approach, processing data updates and encryption on the local device before syncing encrypted blobs to a remote persistence layer. It uses a zero-knowledge architecture where the service provider cannot access decryption keys or view the plaintext content of stored files. The platform provides capabilities for private

    TypeScript
    View on GitHub↗16,880
  • pirate/archiveboxpirate avatar

    pirate/ArchiveBox

    27,721View on GitHub↗

    ArchiveBox is a self-hosted web archiving system designed to capture and preserve permanent static copies of webpages, media, and PDFs on personal infrastructure. It functions as a digital content curator and personal web archive manager, allowing users to import URLs from bookmarks, RSS feeds, and browser history to create a centralized, searchable knowledge base. The project is distinguished by its ability to archive private, paywalled, or login-protected content using browser cookies and authenticated session persistence. It ensures long-term availability by saving pages in multiple concur

    Python
    View on GitHub↗27,721
  • asciimoo/histerasciimoo avatar

    asciimoo/hister

    6,260View on GitHub↗

    Hister is a self-hosted personal search engine that builds a full-text archive of the web pages you visit and the local files you choose to index. A Firefox or Chrome browser extension captures each page as you browse, and the server extracts its text and stores it in an index you control, with no telemetry or required cloud service. It can also act as a crawler, fetching pages over plain HTTP or a real browser, and it can search by meaning as well as by keyword using vector embeddings from an endpoint you configure. Beyond the browser, the same search is available from a web page, a terminal

    Gobrowser-historyhistoryindex
    View on GitHub↗6,260
    • Compare all 30 related projects→