dsh-mirror
Run the following command in DeepSeek Harness:
dsh plugin install webkubor/dsh-mirror
Paste the following prompt into your AI chat to install this plugin:
To install the dsh-mirror plugin, run: dsh plugin install webkubor/dsh-mirror. The source repository is available at https://github.com/webkubor/dsh-mirror.
About this plugin
dsh-mirror is a memory-category plugin for the DeepSeek Harness platform, released under the MIT license. It extends the memory dimension of the Harness ecosystem, helping users manage and leverage memory-related information within DeepSeek interaction workflows.
The plugin is still in its early stages, and the README does not yet detail specific features. Based on its classification, dsh-mirror targets developers and users who need to enhance memory handling in DeepSeek Harness. If you are working with the Harness platform and care about extensibility in the memory module, this project is worth watching for future updates.
Use Cases
- Extending memory capabilities within DeepSeek Harness
- Supporting the memory module in Harness interaction workflows
- Exploring and building memory-based applications on the Harness platform
Best For
- Developers working with the DeepSeek Harness platform
- Engineers interested in extending the Harness memory module
- Technologists exploring the Harness plugin ecosystem
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.