{"slug": "i-open-sourced-memduck-a-self-hosted-ai-memory-workspace", "title": "I open sourced memduck, a self-hosted AI memory workspace", "summary": "Memduck, a self-hosted AI memory workspace designed to solve the problem of scattered context across browser tabs, screenshots, chat messages, and copied text. Users can save material from various sources into a local workspace, then ask questions and trace answers back to original sources. The tool prioritizes local-first operation and source transparency over hosted knowledge apps.", "body_md": "I built memduck because useful context keeps disappearing across links, copied text, screenshots, and chat messages.\n\nMost of my actual working memory is not in one clean notes app. It is spread across browser tabs, saved links, snippets, screenshots, Telegram messages, and random text I copied while researching something. Later, when I want to ask a question about that material, I usually have to reconstruct the context manually.\n\nmemduck is my attempt at a small, self-hosted workspace for that problem.\n\nGitHub: [https://github.com/tageecc/memduck](https://github.com/tageecc/memduck)\n\n## What it does\n\nmemduck lets you save material from browser pages, pasted text, screenshots, and chat channels into a local memory workspace. Then you can ask questions against the saved material and trace answers back to the original sources.\n\nThe current version includes:\n\n- a Next.js workspace for asking and managing saved memory\n- local SQLite storage and local file assets\n- browser extension capture\n- channel configuration for browser, Telegram, DingTalk, Slack, Discord, Feishu, WhatsApp, and webhook-style inputs\n- model/provider configuration in the UI\n- background compilation for summaries, topics, embeddings, and retrieval data\n\n## Why self-hosted\n\nI wanted this to be closer to a personal memory engine than another hosted knowledge app. The goal is to keep the runtime simple enough to inspect and run locally, while still making AI retrieval useful.\n\nIt is still early, but it is already useful for the workflow I care about: save context first, ask later, and keep the source trail visible.\n\n## Try it\n\n```\nnpm install -g memduck@latest\nmemduck\n```\n\nOr from source:\n\n```\ngit clone https://github.com/tageecc/memduck.git\ncd memduck\npnpm install\npnpm memduck dev\n```\n\nIf you care about local-first tools, personal knowledge workflows, or AI memory with source-backed answers, I would like feedback.", "url": "https://wpnews.pro/news/i-open-sourced-memduck-a-self-hosted-ai-memory-workspace", "canonical_source": "https://dev.to/tage_cc_b441e6b367279d2fa/i-open-sourced-memduck-a-self-hosted-ai-memory-workspace-ko5", "published_at": "2026-05-21 07:35:30+00:00", "updated_at": "2026-05-21 08:05:44.224547+00:00", "lang": "en", "topics": ["open-source", "developer-tools", "artificial-intelligence", "products", "data"], "entities": ["memduck", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/i-open-sourced-memduck-a-self-hosted-ai-memory-workspace", "markdown": "https://wpnews.pro/news/i-open-sourced-memduck-a-self-hosted-ai-memory-workspace.md", "text": "https://wpnews.pro/news/i-open-sourced-memduck-a-self-hosted-ai-memory-workspace.txt", "jsonld": "https://wpnews.pro/news/i-open-sourced-memduck-a-self-hosted-ai-memory-workspace.jsonld"}}