dsh-layered-memory

Name: dsh-layered-memory
Author: JunNanLYS

PluginConfirmed pluginCommunity

JunNanLYS/dsh-layered-memory · updated yesterday

View source ↗

Installation

dsh plugin --profile web add dsh-layered-memory

dsh plugin --profile web add https://github.com/JunNanLYS/dsh-layered-memory

dsh plugin --profile web add /path/to/dsh-layered-memory

dsh plugin --profile dsh-tui add @deepseek-harness-tui/dsh-tui

dsh plugin --profile web add .

dsh plugin --profile web add github:JunNanLYS/dsh-layered-memory

Plugins in this repository

dsh-bench-runnerv0.2.0✓
DSH-MemBench 自动化基准驱动器：装入专用 bench profile，apply 即按场景库驱动 Agent 跑记忆准确率测试
package.json
bench/harness/dsh-bench-runner/package.json
dsh.bundle.patch
bench/harness/dsh-bench-runner/cordis.patch.yml
Official core packages (4)
- @deepseek-ai/dsh-agent0.1.0-rc.8shared
- @deepseek-ai/dsh-llm0.1.0-rc.8shared
- @deepseek-ai/dsh-session0.1.0-rc.8shared
- @deepseek-ai/schemastery^3.18.1shared
dsh-layered-memoryv0.11.0✓
L0~L3 分层蒸馏记忆插件 for DeepSeek Harness：自动捕获对话（L0）、抽取原子记忆（L1）、整合场景块（L2）、蒸馏核心画像/团队方法论（L3），并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。
package.json
package.json
dsh.bundle.patch
cordis.patch.yml
Official core packages (9)
- @deepseek-ai/cordis^4.0.1shared
- @deepseek-ai/dsh-agent^0.1.2-alpha.1shared
- @deepseek-ai/dsh-home-paths^0.1.2-alpha.1shared
- @deepseek-ai/dsh-llm^0.1.2-alpha.1shared
- @deepseek-ai/dsh-session^0.1.2-alpha.1shared
- @deepseek-ai/dsh-settings^0.1.2-alpha.1shared
- @deepseek-ai/dsh-system-prompt^0.1.2-alpha.1shared
- @deepseek-ai/dsh-tools^0.1.2-alpha.1shared
- @deepseek-ai/schemastery3.18.2private copy

Paths are pinned to commit 69028fbee43e

Overview

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

Repository check result

Results are bound to the listed commit and cover only static checks run by this registry. The Evidence Score measures reviewable information; it is not a compatibility percentage or a security guarantee.

Static repository check

Sep 8, 2026, 9:25 AM

Medium risk

Checked commit: 69028fbee43e
Evidence Score: 97/100
Static risk: Medium risk
Files scanned: 4
Findings: 1

Evidence breakdown

Source provenance25/25

Install documentation25/25

Maintenance17/20

Compatibility evidence20/20

Security signals10/10

Compatibility confidence: Medium

Findings (1)

Mediumdeps.core-package-installed
package.jsondependencies
```
"@deepseek-ai/schemastery": "3.18.2"
```

Not run

Dependency advisory database scan
Installation execution test
Runtime behavior verification

Scanner 1.0.0 · Scorer 1.0.0