dsh-remember
Cross-session long-term memory for the DeepSeek Harness: a two-phase extraction/consolidation pipeline over a file-based memory workspace, recall injection, a citation feedback loop, lease-based job semantics, plus a settings page, a sidebar status panel and a memory viewer.
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Arborsm/dsh-remember说明文档
阅读完整 README ↗Configuration
Every field has a default; the plugin works out of the box. Override via cordis.yml or the config: block of a dev overlay. Field definitions live in src/config.ts.
Commonly tuned:
| Field | Default | Description |
|---|---|---|
enabled | true | Master switch |
generateMemories | true | Run extraction and consolidation |
useMemories | true | Inject the memory summary into prompts |
extractModel / consolidationModel | '' | provider/model; empty = deployment default |
workspaceDir / dbPath | '' | Empty = under ~/.dsh-memory/ |
summaryTokenLimit | 2500 | Token cap for the injected summary |
scanIntervalMinutes | 15 | Background scan interval |
minRolloutIdleHours | 1 | Idle time before a session becomes extractable |
maxUnusedDays | 30 | Retention for never-cited memories |
There are 23 fields in total (scheduling, retries, concurrency, consolidator tool deny-list, …) — see src/config.ts. All of them are editable on the settings page.