dsh-diary
Run the following command in DeepSeek Harness:
dsh plugin install hyperMoss/dsh-diary
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install hyperMoss/dsh-diary in DeepSeek Harness to install this plugin; source available at https://github.com/hyperMoss/dsh-diary
About this plugin
Every time a session ends, the context disappears. dsh-diary solves this by giving the agent a persistent, date-stamped Markdown journal, so every conversation can be saved as searchable, editable, and traceable text that accumulates across days and sessions.
The plugin registers ten tools that cover the full entry lifecycle: create, list, read, update, delete, and full-text search. Multiple entries on the same day are supported via a slug. A template system with built-in placeholders for date, title, tags, year, month, and day keeps formatting consistent, and templates can be created, overwritten, or deleted on the fly. On the browser side, a monthly diary board and a template management panel let you create, preview, and delete entries and templates without touching the filesystem directly.
Built for individuals who want their agent to remember, teams that need auditable work logs, and anyone tired of re-explaining context from scratch. Install it, and let the agent write things down.
Use Cases
- Let the agent log work updates and decisions across sessions, picking up context on the next startup
- Generate formatted weekly reports and retrospectives in bulk with custom placeholder templates
- Browse, create, and delete journal entries in a monthly board UI without touching the filesystem
Best For
- Solo developers who want their agent to remember between sessions
- Tech teams that need AI-assisted work logging and auditable notes
- Individuals who treat their agent as a digital secretary
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.