dsh-barium
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-barium
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-barium in the terminal to install this memory plugin; full source is available at https://github.com/uckkk/dsh-barium
About this plugin
In the DeepSeek Harness ecosystem, memory plugins are responsible for preserving state across sessions. Many implementations, however, rely on external network services or third-party storage, which raises concerns in offline or privacy-sensitive scenarios. dsh-barium was built with exactly that need in mind: it is written in pure Node.js and makes zero network requests at runtime, keeping every read and write fully local.
As a memory-category plugin, dsh-barium's core role is to provide a lightweight, self-contained memory channel for Harness. The absence of external dependencies means no extra runtime overhead and no risk of data leaving your machine, making it a good fit for developers working on privacy-sensitive or fully offline projects.
If you value minimal dependencies and a clone-and-go experience, or you are assembling a completely offline DeepSeek Harness workflow, dsh-barium is worth a look. It does nothing flashy; it simply nails local memory the dependable way it was designed to.
Use Cases
- Retaining cross-session memory in an offline DeepSeek Harness setup
- Preventing memory data from leaving the machine in privacy-sensitive projects
- Quickly wiring in memory capability with zero dependencies in a minimal workflow
Best For
- Developers who prefer fully offline and local execution
- Teams with strict data-privacy requirements
- Plugin users seeking a zero-dependency, zero-config experience
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.