dsh-mnemosyne
Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, and a Settings panel. Data lives under ~/.dsh/mnemosyne.
AI 분석
核心用途是为 DSH 提供完全本地化的向量记忆管理。适合需要 Agent 具备本地知识库检索、长期记忆存储与遗忘管理的用户。必要条件是本地需安装 uv 工具以配置 CLI。
설치
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rebron1900/dsh-mnemosyneConfiguration
Configuration comes from two sources: the plugin's own DSH settings (~/.dsh/settings.yaml under the mnemosyne: namespace) and Mnemosyne's flat ~/.dsh/mnemosyne/config.yaml. The panel shows config.yaml values first; missing values display default placeholders.
| Group | Fields | Source |
|---|---|---|
| Plugin | cli / defaultTopK / timeoutMs / dataDir | DSH settings / cordis.patch.yml |
| Embedding | noEmbeddings / embeddingModel / embeddingDim / embeddingApiUrl / embeddingApiKey | config.yaml no_embeddings / embedding_* |
| LLM | llmEnabled / llmBaseUrl / llmApiKey / llmModel / llmTimeout | config.yaml llm_* |
| Recall | polyphonicRecall | config.yaml polyphonic_recall |
| Working Memory | wmMaxItems / wmTtlHours | config.yaml wm_* |
| Working Memory | autoSleep / sleepThreshold / ignorePatterns | config.yaml auto_sleep_enabled / sleep_threshold / ignore_patterns |
| Automatic Memory | promptSection / autoSync / autoPrefetch / prefetchTopK / prefetchMinQueryLen | DSH settings / cordis.patch.yml |
Note: The Automatic Memory fields are DSH-side config (saved via the Settings panel, not written to
config.yaml). Changing them requires a DSH restart to take effect, since they control plugin hook registration at startup.
Saving writes to the corresponding config file and runs mnemosyne config reload. "Reset to Defaults" restores all panel-managed keys to Mnemosyne upstream defaults; additional config can be edited directly in ~/.dsh/mnemosyne/config.yaml. Most settings hot-reload except vec_type and other startup-bound options.