DeepSeek Harness (DSH) academic writing guard for papers — 论文去AI味 / AI-writing style detection, evidence preservation, journal-fit calibration, manuscript proofreading, writing_audit & automatic checks. Local, zero network, zero LLM.

Evidence-based learning engine for OpenCode — learn anything, verify by free recall, schedule with FSRS, adapt from your own data.

An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.