dsh-link-collect
Run the following command in DeepSeek Harness:
dsh plugin install suomir1995/dsh-link-collect
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install suomir1995/dsh-link-collect in your terminal (source at https://github.com/suomir1995/dsh-link-collect ), then restart your profile to see the Bookmarks entry in the sidebar.
About this plugin
Bookmarks scattered across browser profiles are out of sync, loosely structured, and invisible to your AI agent. dsh-link-collect brings a local-first bookmark library into DeepSeek Harness: every collection is a plain .md file, every entry carries a title, URL, one-line description, tags, and free-form body text, so your data stays portable, version-controllable, and fully yours.
The plugin offers full CRUD on collections and links, automatically fetches and caches site icons (favicon.ico, then HTML extraction, then DuckDuckGo fallback) into an icons/ folder, and provides keyword, tag, and collection-scoped search across the whole library. You can hot-swap the library directory from the UI without restarting. Three agent tools—link_collect_search, link_collect_add, and link_collect_list—let an AI assistant query existing bookmarks, add or update links with automatic URL deduplication, and even create a collection on the fly when one does not yet exist.
It is built for DeepSeek Harness users who prefer a Markdown-native, self-hosted bookmark workflow over cloud services, and who want their agent to help organize and retrieve links during conversations. Every HTTP route is guarded by loopback and same-origin checks, and all Markdown writes go through an atomic rename with a single-writer queue to prevent concurrent corruption.
Use Cases
- Ask your agent to search saved articles by keyword or tag mid-conversation
- Create themed collections and locate pages instantly via tag and full-text search
- Hot-swap library directories to isolate bookmarks per project or role without restarting
Best For
- Developers who prefer Markdown-based, fully self-hosted bookmark management
- DeepSeek Harness users who want their agent to organize and retrieve links
- Privacy-conscious users who avoid cloud-synced browser bookmarks
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.