提供基于6层架构的分层记忆管理，支持SQLite存储、本地嵌入搜索、中文分词、时间衰减及REST/WebSocket接口。

This skill implements a local memory system that reads your agent session logs and writes a memory index, archive files, dream logs and stats. Before installing or enabling it: - Review and approve which directory it will use (MEMORY_DIR/SESSION_DIR). Note: one file hardcodes /root/.openclaw/agents/main/sessions — update or audit that path if you don't want it to read system sessions. - Expect it to automatically create memory entries from recent conversations (auto-write/dream-cycle). If that behaviour is undesirable, turn off autoWrite in config. - If you enable embedding providers, the skill may require API keys (DOUBAO/DASHSCOPE/@xenova) not declared in the registry metadata — confirm which secrets you supply. - Run the skill in an isolated environment or with restricted filesystem permissions until you are comfortable with its behavior; inspect the omitted/remaining files (embedder/tokenizer and any network code) before granting network or session access. - If you plan to run the API/WS panel, bind it to localhost or a controlled interface and consider firewalling the ports. These inconsistencies look like sloppy configuration rather than clear malicious intent, but they materially affect privacy — treat the skill as potentially sensitive and verify config/paths and optional code before use.

Type: OpenClaw Skill Name: layered-memory-sys Version: 1.1.3 The skill implements a sophisticated multi-layered memory system for AI agents, featuring automated memory consolidation ("dream mode") and session log analysis. It is classified as suspicious due to significant security vulnerabilities: the REST API and WebSocket servers (src/api/server.mjs, src/api/ws.mjs) lack authentication and implement a permissive CORS policy ("*"), potentially exposing sensitive conversation history to unauthorized access. Additionally, the system automatically transmits session data to external AI providers (Doubao at ark.cn-beijing.volces.com and Dashscope at dashscope.aliyuncs.com) for summarization and embeddings, which are high-risk data handling practices despite being documented features.