Asher-2000/dsh-memory-connect ↗★ 7

@asherliner/dsh-memory-connect

提供跨会话记忆、语义召回与LLM整合功能 适合需要跨会话长期记忆、避免上下文爆炸并使用SQLite存储的用户。

套件
@asherliner/dsh-memory-connect
相容性
待驗證
Harness 依賴範圍
^0.1.0-rc.7
Cordis 依賴範圍
^4.0.1
版本
0.6.1
授權
MIT
最近更新
2026年8月27日

安裝

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Asher-2000/dsh-memory-connect

Configuration

Basic Options

OptionDefaultDescription
path(required)Path to SQLite memory database
openAtstartupWhen to open: startup, first-query, never
maxRecallCount10Max memories to recall per session
decayRate0.02Decay constant (higher = faster decay)
journalModewalSQLite journal mode

Scheduler Options

OptionDefaultDescription
schedulerEnabledtrueEnable periodic maintenance
schedulerDecayIntervalMs3600000Decay interval (ms), default 1h
schedulerConsolidateIntervalMs21600000Consolidation interval (ms), default 6h

Context Explosion Prevention Options

OptionDefaultDescription
maxContextTokens4000Max tokens for memory context injection
smartPrioritizationtrueEnable smart memory prioritization
enableCompressiontrueEnable memory compression

Soul Options

OptionDefaultDescription
enableSoultrueEnable global Soul injection
soulPath~/.dsh/soul.mdCustom Soul file path

Semantic Embedding Options (optional)

OptionDefaultDescription
embeddingEnabledfalseEnable semantic (vector) recall via local embedding server
embeddingUrlhttp://127.0.0.1:8765Embedding server base URL
embeddingModelBAAI/bge-small-zh-v1.5Model name (must match the server)
embeddingWeight0.7RRF fusion weight for semantic results (0–1)

To use semantic recall, start the bundled embedding server first: