dsh-dev-databases
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-dev-databases
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-dev-databases in your terminal to install; the plugin source is hosted at https://github.com/uckkk/dsh-dev-databases .
About this plugin
In everyday development you often need to quickly recall or look up local data entries within a session—API config snippets, debugging notes, dev reminders, and so on. dsh-dev-databases is built for exactly that: it gives your DeepSeek Harness session a lightweight, purely local entry-memory capability, with no external database service and no network connection required.
The plugin exposes exactly two tools: list_database to enumerate all stored entries, and get_database to fetch a specific record by its id or name. It is implemented in pure Node.js, so once installed you can invoke the registered tools directly in a conversation with no extra configuration or background processes to manage.
It is well suited for developers who want a small local record layer inside their AI-assisted workflow without the overhead of a full database middleware. If all you need is to stash a handful of dev notes or config snippets and retrieve them on demand, this plugin is light, focused, and just enough.
Use Cases
- Quickly list all stored dev note entries during a session
- Look up a specific API config or debug record by name
- Store and retrieve lightweight dev data without launching an external database
Best For
- Developers who want a lightweight local record layer without a full database
- Engineers who stash and retrieve dev notes inside an AI-assisted workflow
- Users who prefer purely local zero-network tooling
Related Plugins
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.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.