OpenClaw的Engram-技能（skill）的描述

AI智能体的持久化语义记忆层。采用本地优先存储（SQLite+LanceDB）和Ollama嵌入。跨会话存储和召回事实、决策、偏好、事件、关系。支持记忆衰减、去重、记忆类型（5种类型）、记忆关系（7种图关系类型）、智能体/用户范围界定、语义搜索、上下文感知召回、从文本中自动提取（规则/LLM/混合方式）、导入/导出、REST API、MCP协议。解决上下文窗口和压缩失忆问题。服务器位于localhost:3400，仪表板位于/dashboard。通过npm安装（engram-memory），需要带有nomic-embed-text模型的Ollama。

OpenClaw's Engram skill

Persistent semantic memory layer for AI agents. Local-first storage (SQLite+LanceDB) with Ollama embeddings. Store and recall facts, decisions, preferences, events, relationships across sessions. Supports memory decay, deduplication, typed memories (5 types), memory relationships (7 graph relation types), agent/user scoping, semantic search, context-aware recall, auto-extraction from text (rules/LLM/hybrid), import/export, REST API, MCP protocol. Solves context window and compaction amnesia. Server at localhost:3400, dashboard at /dashboard. Install via npm (engram-memory), requires Ollama with nomic-embed-text model.

Engram - skill原始代码包

该作者的其他技能