← 返回 Skills 市场
dxiaofeng0811-lgtm

Vector Mind Map Fusion

作者 dxiaofeng0811-lgtm · GitHub ↗ · v1.2.4 · MIT-0
cross-platform ⚠ suspicious
180
总下载
0
收藏
1
当前安装
16
版本数
在 OpenClaw 中安装
/install vector-mind-map-fusion
功能描述
L1→L2→L3 向量记忆融合系统。用于构建、查询和管理语义记忆图谱。当用户需要提取、加工、记忆、或检索结构化知识时触发。具体场景:(1) 用户说"记住"、"存入记忆"、"这个很重要" → L1 提取;(2) 用户问"之前有没有"、"有没有记录过"、"我的记忆里" → L2+L3 查询;(3) 用户要求"整理一下...
安全使用建议
This skill appears to implement the memory-extraction/recall system it claims, but review and precautions are recommended before installing: - Data scope: it scans your OpenClaw session files and writes persistent memory files (brain.db and InfinityDB files). If your sessions contain secrets (passwords, API keys, tokens, private notes), those may be extracted and stored. Consider running in a sandbox, or set SESSIONS_DIR to a safe test directory. - File locations: default storage includes ~/.local/share/neural-memory and an absolute '/workspace/fusion/...' path in code. Confirm and override these paths in the config before running so it doesn't write to unexpected locations. - Pickle risk: the HNSW index is saved/loaded using pickle. Loading pickled files from untrusted sources can execute arbitrary code. Only run this skill on data you control, and avoid using existing brain.hnsw files from unknown origins. - External install commands: SKILL.md asks you to run 'curl https://ollama.com/install.sh | sh' and 'pip install --break-system-packages'. 'curl | sh' and '--break-system-packages' have system-level effects—inspect the installer script and avoid the pip flag if you don't want pip to alter system packages. - Secrets handling: the l1 classifier will detect and classify 'password/secret/token/api_key' text; but there is no obvious automatic redaction before storing. If you need to avoid persisting secrets, add filtering or prevent the skill from scanning live session directories. - Actionable steps: (1) Review the code (esp. src/infinitydb_lite.py, l1_classifier and paths in config); (2) run the skill in an isolated environment or container; (3) set SESSIONS_DIR and NEURALMEMORY_DIR to controlled test directories; (4) remove or audit any existing brain.hnsw before loading; (5) avoid blindly executing the suggested curl | sh installer and the pip flag without inspection. If you want, I can point out exact lines/files that implement the session scanning, brain DB write paths, and pickle load/save calls so you can inspect them more easily.
功能分析
Type: OpenClaw Skill Name: vector-mind-map-fusion Version: 1.2.4 The 'vector-mind-map-fusion' bundle is a sophisticated three-layer memory management system (L1 extraction, L2 consolidation, L3 retrieval) designed for the OpenClaw agent. It utilizes local Ollama instances for embeddings and implements a custom 'InfinityDB-lite' for graph and vector storage. While the system accesses sensitive local data such as session logs in `~/.openclaw/` and credentials for Feishu (Lark) reporting in `src/l3/l3_cron.py`, these actions are consistent with its stated purpose of managing agent memory and providing status updates. The use of `curl | sh` in `start.sh` for Ollama installation is a common but risky practice, yet there is no evidence of malicious intent, data exfiltration of actual memory content, or unauthorized persistence mechanisms.
能力标签
requires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
Name/description describe a 3-layer memory extraction/retrieval system and the code implements that: session scanner (L1), consolidator (L2) and archives/index (L3). Access to OpenClaw sessions and a local neural memory DB is expected for this purpose, but the project writes to paths outside the repository (default brain DB in ~/.local/share/neural-memory and an absolute '/workspace/fusion/...' path in the InfinityDB implementation), which is surprising and should be confirmed.
Instruction Scope
SKILL.md instructs scanning user session JSONL and persisting extracted contents into local DB/files—this will capture whatever is in OpenClaw sessions (including credentials or secrets users may have typed). It also tells users to run external install commands (curl | sh to install Ollama) and to pip install with '--break-system-packages'. The instructions give broad discretion to scan/ingest all sessions and to run scheduled runs (cron-like), which increases privacy risk.
Install Mechanism
There is no formal install spec, but the README/SKILL.md asks the user to curl an external installer (ollama.com/install.sh) and to 'ollama pull' large models; it also recommends 'pip install --break-system-packages httpx'. Those external-install steps are normal for requiring Ollama but carry typical network/script risks (curl | sh) and system-level implications (pip flag). The code itself is bundled, so nothing is downloaded at runtime by the skill besides using a local Ollama server.
Credentials
The skill declares no required env vars, but the code reads SESSIONS_DIR and NEURALMEMORY_DIR environment variables and defaults to user-local paths (~/.openclaw/... and ~/.local/share/neural-memory). That is logical for a memory skill, but the number and sensitivity of files it reads/writes is high (user session data, brain.db). The classifier also explicitly recognizes 'password/secret/token/api_key' patterns and will persist classified items into its stores unless you change behavior — so credential capture/persistence is a real risk if sessions contain secrets.
Persistence & Privilege
The skill persists data outside the project (brain.db in the user's home and InfinityDB files), and some defaults point to absolute paths (e.g., '/workspace/fusion/...') that differ from config constants. It uses pickle to persist/load HNSW indices (brain.hnsw), which means loading a tampered pickle file could execute code. 'always' is false and the skill is not forced into every run, but its filesystem writes and external install suggestions give it persistent on-disk presence and lasting access to stored memories.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install vector-mind-map-fusion
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /vector-mind-map-fusion 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.4
- 优化了 L3 层的定时合并与扫描逻辑,改善增量写入和归档的稳定性。 - 更新了 session 扫描与 manifest 文件,提升了任务运行的准确性和一致性。 - 修复了部分边缘情况下的时间窗口和归档调度问题。
v1.2.3
### vector-mind-map-fusion v1.2.3 - Added memory/_state/last_run_manifest.json to track or record run state or manifest. - Updated src/l3/l3_biweekly_consolidate.py with new logic or improvements. - No impact to core documentation (SKILL.md unchanged in logic; structure or code only).
v1.2.2
- 优化 src/l3/l3_cron.py 中 L3 层定时归档处理逻辑 - 更新 memory/_state/scan_sessions_incremental.json,提升增量扫描的准确性和可靠性 - 稳定性提升,改进增量扫描与 L3 合并时的状态记录
v1.2.1
**v1.2.1 introduces new features and enhancements for vector-mind-map-fusion.** - Added L2 checkpointing and L3 manifest modules for improved processing and tracking. - Introduced a new cost tracker utility for resource monitoring. - Enhanced core scripts across L1, L2, L3, and Recall with stability and feature improvements. - Documentation (README.md, SKILL.md) updated to reflect latest capabilities and structure.
v1.2.0
feat: L1 增加 simhash 近似去重(第2级,纯文本,多agent场景跨session去重生效)
v1.1.2
docs: SKILL.md 与 README.md 同步,方案A完整文档更新
v1.1.1
docs: 更新 README - v1.1.0 方案A架构说明,并行搜索说明
v1.1.0
方案A: InfinityDB单一数据源 + 并行搜索(HNSW+关键词合并)
v1.0.7
revert: L3 is write-only agent - no dedup at write time, dedup done at read time by user
v1.0.6
fix: L3 now dedups against InfinityDB history before writing - brute-force cosine > 0.85 skip duplicates, fixes duplicate long-term memory写入
v1.0.5
update SKILL.md: full README content - architecture, environment setup, project structure, QA metrics, docs links
v1.0.4
fix: l1_cron stale tmp FileNotFoundError; full pipeline verified end-to-end
v1.0.3
fix: P0 written_ids collection; P1 hardcoded paths; Ollama encode fix; full pipeline verified
v1.0.2
fix: cron 命名改为 CST 时间,settings.yaml 注释修正为 CST+UTC 对照
v1.0.1
fix: 修复所有硬编码路径,统一使用 PROJECT_ROOT 相对路径,不再依赖 /workspace/fusion
v1.0.0
Initial release: L1→L2→L3 memory fusion system with Ollama bge-m3
元数据
Slug vector-mind-map-fusion
版本 1.2.4
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 16
常见问题

Vector Mind Map Fusion 是什么?

L1→L2→L3 向量记忆融合系统。用于构建、查询和管理语义记忆图谱。当用户需要提取、加工、记忆、或检索结构化知识时触发。具体场景:(1) 用户说"记住"、"存入记忆"、"这个很重要" → L1 提取;(2) 用户问"之前有没有"、"有没有记录过"、"我的记忆里" → L2+L3 查询;(3) 用户要求"整理一下... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 180 次。

如何安装 Vector Mind Map Fusion?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install vector-mind-map-fusion」即可一键安装,无需额外配置。

Vector Mind Map Fusion 是免费的吗?

是的,Vector Mind Map Fusion 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Vector Mind Map Fusion 支持哪些平台?

Vector Mind Map Fusion 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Vector Mind Map Fusion?

由 dxiaofeng0811-lgtm(@dxiaofeng0811-lgtm)开发并维护,当前版本 v1.2.4。

💬 留言讨论