jihe520/mindpocket

Open-source, free, multi-platform, one-click deploy, AI Agent–integrated personal bookmarking system｜完全开源、免费、多端、一键部署、AI Agent 集成的个人收藏夹系统

What it solves

MindPocket is a personal bookmarking system that solves the problem of cluttered, unorganized saved content. It uses AI to automate the tedious parts of bookmark management, such as summarizing long pages and generating relevant tags, making it easier to retrieve information later.

How it works

The system is built as a serverless application deployed on Cloudflare's infrastructure. It utilizes a Retrieval-Augmented Generation (RAG) pipeline to process saved content, enabling AI-powered summarization and smart tagging. It provides a unified experience across a web app, mobile app, and browser extension, and includes a CLI for integration with external AI agents.

Who it’s for

It is designed for users who want a free, self-hosted, and multi-platform way to organize their digital clippings and bookmarks with AI assistance.

Highlights

  • Zero Cost Deployment: Runs entirely on the Cloudflare free tier using Workers, D1, Vectorize, and R2.
  • AI-Powered Organization: Uses RAG for automatic content summarization and tag generation.
  • Multi-Platform Access: Available via Web, iOS, Android, and browser extensions.
  • Agent Ready: Includes an official CLI and a specific agent skill to allow AI agents to manage bookmarks on the user's behalf.

Related

  • Project
    karakeep-app/karakeep

    A self-hostable bookmarking app that uses AI for automatic tagging, summarization, and semantic search to organize large collections of links and files.

  • Project
    RMA-MUN/RAGNotebook

    An AI-powered personal knowledge management tool that integrates note-taking with Neo4j knowledge graphs and GraphRAG to prevent knowledge fragmentation.

  • Project
    labring/FastGPT

    FastGPT is an open‑source platform for building AI agents and LLM‑driven applications. It provides a visual Flow editor, knowledge‑base (RAG) support, plugin hot‑reloading, debugging tools, and can be run locally via Docker or deployed on Sealos/Kubernetes. A hosted SaaS version and a commercial edition are also offered.

  • Project
    mudler/LocalRecall

    A lightweight, offline RESTful API for managing vector-based knowledge bases, enabling AI agents to handle local long-term and short-term memory without cloud services.

  • Project
    LightningRAG/LightningRAG

    A full-stack RAG framework with a visual agent orchestration canvas and webhook connectors for deploying AI agents to third-party messaging platforms.