deepseek-knowz-plugin
Run the following command in DeepSeek Harness:
dsh plugin install knowz-io/deepseek-knowz-plugin
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install knowz-io/deepseek-knowz-plugin in DeepSeek Harness to install this plugin; source code is available at https://github.com/knowz-io/deepseek-knowz-plugin
About this plugin
Every agent conversation starts from scratch, and once context is gone, it is gone for good. The Knowz plugin bridges DeepSeek Harness agents to a hosted Knowz vault over MCP, giving agents a persistent, queryable memory layer that turns scattered chat history into structured, reusable knowledge.
The plugin ships a full skill set: knowz-ask to question the vault, knowz-search to retrieve entries, knowz-browse to walk directories, knowz-save to archive new content, and knowz-amend to revise existing items. Supporting skills such as knowz-setup, knowz-status, knowz-flush, and knowz-auto handle mapping, health checks, cache cleanup, and automated triggers. No secrets are baked into the package, and personal and business tenants can run side by side without conflict.
It is built for individual developers and small teams who want their AI agent to remember project conventions, accumulate domain vocabulary, and reuse answers across sessions without standing up a vector database or writing a custom RAG pipeline from scratch.
Use Cases
- Reuse project conventions and domain vocabulary across sessions
- Let agents query, retrieve, and archive entries in a hosted vault
- Attach a structured knowledge lookup and accumulation layer to AI workflows
Best For
- Individual developers who need an external knowledge layer for their agents
- Small teams that want to accumulate domain knowledge over time
- AI application developers who prefer a hosted service over self-hosted RAG
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.