dsh-potassium
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-potassium
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-potassium in DeepSeek Harness to install; source: https://github.com/uckkk/dsh-potassium
About this plugin
dsh-potassium addresses a simple yet often overlooked problem: how to gather scattered fields step by step into a clean JSON structure when you are offline and do not want to spin up any external service. It uses no database, makes no remote API calls, and runs entirely inside the Node.js runtime, so it keeps working even with the network cable unplugged.
Two capabilities stand out. First, it is a pure Node implementation with zero network dependencies, meaning it just works without environment fuss. Second, it walks you through each field in sequence and assembles a well-formed JSON object at the end, eliminating the tedium of hand-building structures. The code path is short, auditable, and free of unnecessary abstractions.
It is built for developers who need lightweight memory management while keeping full control over local data flow-tiny offline recorders, form builders, or any small-to-mid project that would rather not reach for Redis or MongoDB.
Use Cases
- Offline step-by-step field collection into clean JSON
- Lightweight local record keeping without a database
- Local form building and scattered data assembly
Best For
- Developers needing offline memory management
- Small-to-mid teams that avoid extra services
- Indie devs who value short, auditable code paths
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.