dsh-daily-digest
Run the following command in DeepSeek Harness:
dsh plugin install zhaoxuejie/dsh-daily-digest
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install zhaoxuejie/dsh-daily-digest inside DeepSeek Harness to install this plugin (source: https://github.com/zhaoxuejie/dsh-daily-digest), then restart the web server and the daily digest card will appear in the lower-right corner.
About this plugin
A day of heavy AI collaboration often ends with the painful task of reconstructing what you actually did: which jobs completed, how many session rounds were logged, which request errors slipped through. dsh-daily-digest automatically tracks task completions, session trajectories, and request errors in DSH, persists them day by day so nothing is lost on restart, and lets you copy a well-structured daily or weekly report with one click before you leave the office.
Rather than building a flashy dashboard, it exposes a set of lightweight endpoints: the summary for today, a report for any given date, a seven-day trend, and range aggregation. All responses are plain JSON or Markdown with no UI dependency. A floating card in the lower-right corner of the web page shows live statistics and a trend bar, ready to copy. The data semantics are carefully defined: only background jobs count as tasks, sessions are tracked by startup versus resume, and titles prefer the event stream with a service fallback, so the numbers hold up under scrutiny.
If you spend every day running jobs, tuning prompts, and writing docs inside DeepSeek Harness and need to regularly report AI collaboration output to your team, this plugin fills the missing link of automatic accounting and ready-to-share reporting.
Screenshots
Use Cases
- Copy a one-click daily AI work digest at end of day
- Submit a weekly AI output summary to the team
- Review task and session success trends over the past seven days
- Pinpoint time windows where request errors were concentrated
Best For
- Solo developers who run jobs in DSH daily
- Engineers who need to report AI collaboration output to a team on a schedule
- Independent workers who want automatic work-log accumulation without manual tracking
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
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.

