DeepSeek HarnessHub
Submit plugin

Aik358/dsh-auto-memory ↗★ 63

@a9i5k4/dsh-auto-memory

Proactive associative memory for DSH: zero-prompt recall injected before the model speaks, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers, PLAN whiteboard, water-level sensing. Local-first, model-agnostic, zero deps. 主动联想记忆+Astra 式上下文管理:自动唤回/自动沉淀/技能固化/交接账本与白板跨窗口续命/水位感知。

AI Analysis

适合需要跨会话记忆唤回、自动沉淀知识和技能固化的深度用户。

memoryskills
Package
@a9i5k4/dsh-auto-memory
Version
2.4.2
License
BSD-3-Clause
Last updated
Sep 12, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Aik358/dsh-auto-memory

README

Read the full README ↗

Configuration

Config file ~/.dsh/dsh-auto-memory.json (everything adjustable in the Settings GUI, zh/en UI and panel font size included):

{
  "userMemoryDir": "~/.dsh/memory",
  "memoryRoot": "~/.dsh/memory/workspaces",
  "injectEnabled": true,
  "injectBudgetChars": 2400,
  "recentDaysInjected": 1,
  "reflectEnabled": true,
  "autoConsolidate": true,
  "autoConsolidateCooldownMinutes": 30,
  "autoConsolidateDailyMax": 8,
  "unattendedMode": false,
  "unattendedAuto": false,
  "unattendedAutoHours": ["22:00-08:00"],
  "memoryHubEnabled": true,
  "externalSources": { "workbuddy-user": true, "claude-global": true },
  "dayBoundaryMinutes": 450
}

Full key reference lives in the Settings page — every switch has a description, and every welcome-tour switch maps 1:1 to settings.