📦 Z1 Memory Palace v3.0

v3.0.0

基于文件的长期 AI 记忆系统，集成 BGE-M3 向量搜索、元数据过滤、复合评分、图邻居扩展与自动记忆管理

0· 30·0 当前·0 累计

by @z1one0415

文件处理数据分析自动化系统工具搜索引擎优化

下载技能包

安全扫描

VirusTotal

可疑

查看报告

OpenClaw

可疑

high confidence

该技能宣称的“零基础设施、本地当前目录”行为，与内含脚本中硬编码的单一用户绝对 vault 路径及路径/名称不匹配不符——该包会修改磁盘文件，若未调整路径直接运行，可能脆弱或带来意外。

评估建议

Don't run these scripts unchanged. Key risks and actions to consider: - The code hardcodes ROOT = /Users/zhouyi0415126.com/ai_matrix/vault/01_core; it will not operate on a palace/ you create in the current directory. Before running, either change ROOT to a safe test directory or run inside a disposable copy of your repository. - The scripts perform filesystem writes (rename backup of manifest, overwrite index files, write graph JSON). Backup your data first and inspect the manifest/index files ...

详细分析 ▾

⚠ 用途与能力

The skill claims a file-based, zero-infrastructure memory palace you can initialize in the current working directory, but the Python and shell scripts are written to operate on a hardcoded absolute ROOT (/Users/zhouyi0415126.com/ai_matrix/vault/01_core). That means running the provided scripts will not act on the local 'palace/' you create unless you edit the code. This mismatch is unexpected for the claimed purpose and suggests poor packaging or that the code was copied from a single developer's machine.

⚠ 指令范围

SKILL.md tells the agent/user to create palace/ in the current directory and run pip install FlagEmbedding and the build/query scripts. The code, however, reads/writes manifests, index and graph files under the absolute ROOT path and performs file operations (renaming manifest to a .backup, writing indexes, writing graph_neighbors). auto_maintain.sh also cd's into the hardcoded path and calls scripts under scripts/watchdog/, but the included files are in scripts/ (no watchog subdir). These instructions will either fail or operate on unexpected files; they also perform writes/renames on the user's filesystem (expected for an indexer but important to be explicit).

ℹ 安装机制

There is no formal install spec; SKILL.md suggests pip install FlagEmbedding. That is a moderate-risk dependency (unknown third-party package) but not inherently malicious. Because this is instruction-only with code files, nothing is automatically written to disk by the registry, but following the instructions will install a third-party Python package and run local scripts that modify files.

ℹ 凭证需求

The skill does not request environment variables or credentials. However, it expects filesystem access to a specific absolute path and will read and write files there (manifests, index, backups, graph). That filesystem access is proportional for a local memory manager, but the hardcoded path is disproportionate to the 'zero-infrastructure' claim and increases risk of accidental modification of unrelated user data if the path is adapted incorrectly.

ℹ 持久化与权限

The skill is not marked 'always' and does not itself install persistent agents. It contains an auto_maintain.sh that is intended to be run by a LaunchAgent daily (comment only). If a user or integrator wires this into a scheduler, it will perform recurring writes and rebuilds on the hardcoded vault. That persistent operation would increase blast radius, so treat automated scheduling cautiously.

安全有层次，运行前请审查代码。

运行时依赖

无特殊依赖

安装命令

点击复制

官方npx clawhub@latest install z1-memory-palace

镜像加速npx clawhub@latest install z1-memory-palace --registry https://cn.longxiaskill.com

技能文档

Memory Palace 面向 AI 代理的零基础设施（无需 Docker、无需外部服务）文件型长期记忆系统。

架构 palace/ ├── grand_hall/ # 全局导航、房间地图、日志 ├── chambers/ # 代理专属知识（每代理一间） ├── project_rooms/ # 长期项目存储 ├── reflection_wing/ # 已提炼洞察：原则、内核、模式 ├── dispatch_corridor/ # 任务路由与状态跟踪 ├── conflict_room/ # 冲突解决记录 └── archive_basement/ # 冷存（默认搜索排除）

快速开始 # 1. 初始化宫殿结构 mkdir -p palace/{grand_hall,chambers,project_rooms,reflection_wing,dispatch_corridor,conflict_room,archive_basement} # 2. 安装 BGE-m3 pip install FlagEmbedding # 3. 构建索引 python3 scripts/build_index_bge.py --force # 4. 查询 python3 scripts/query_bge.py "你的搜索词" python3 scripts/query_bge.py --type palace --priority high "查询" python3 scripts/query_bge.py --details "查询" # 显示子分 python3 scripts/query_bge.py --raw "查询" # 纯余弦（v2 兼容）

搜索评分复合分 = 0.5×语义 + 0.25×时效 + 0.25×重要度语义：BGE-m3 余弦相似度（截断至 [0,1]）时效：基于文件 mtime 的 30 天半衰衰减重要度：priority 映射（high=1.0, medium=0.6, low=0.3）

关键脚本 build_index_bge.py 构建 BGE-m3 向量索引，支持增量维护 query_bge.py 复合评分搜索，支持元数据过滤、raw 模式 graph_router.py 构建 1-hop [[links]] 邻居图 cold_zone_blinding_patch.py 排除 archive_basement 搜索

索引清单格式 watchdog_manifest_v1.jsonl 中每条记录： {"path":"palace/chambers/01_agent/accumulated_knowledge.md","type":"palace","priority":"high"} 字段：path（必填）、type（元数据过滤）、priority（重要度评分）

记忆代谢详见 references/memory_metabolism.md： 3 级升级路径：Project Room → Reflection Wing → Constitution 5 类输出：principle card、prompt kernel、failure pattern、thinking path、constitution candidate 低价值内容反向淘汰规则

数据来源：ClawHub ↗ · 中文优化：龙虾技能库