Memory V2
v0.1.0基于中文向量嵌入和知识图谱，实现语义搜索、实体提取及自动管理的高效记忆系统。
⭐ 0· 55·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (向量记忆 + 知识图谱 + 实体提取 + 管理) match the included source files (vector-store.js, graph-store.js, ner-extractor.js, memory-manager.js). Declared dependencies (@xenova/transformers, @lancedb/lancedb) are appropriate for embedding/NER and a local vector DB. No unrelated environment variables, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructions are focused: npm install, instantiate MemorySystem, add/search memories, run maintenance. Runtime code only reads/writes local DB and graph files, loads models via the transformers pipeline, and does not reference system credentials or unrelated system files. The one runtime network activity is model downloads (noted in docs).
Install Mechanism
There is no registry install spec, but SKILL.md instructs using npm install which pulls packages from the public npm registry (package-lock shows standard npm URLs). This is expected. Runtime model downloads (Transformers.js pipeline) will fetch large model files (~500MB) from model hosts (e.g., Xenova/Hugging Face) on first run — this is expected but worth noting because it contacts external hosts and consumes bandwidth/storage.
Credentials
The skill requires no environment variables or credentials. All storage is local (configurable dbPath/graphPath). No secrets-like env vars are declared or accessed in code. Allowing the user to point storage paths to arbitrary locations is normal but means the skill will persist data where configured.
Persistence & Privilege
always:false (default). The skill writes persistent artifacts to disk (vector DB and graph JSONL files) and downloads model files on first use; it does not modify other skills or global agent settings. Persisting user data and large model files is expected behavior but users should be aware of storage and retention implications.
Assessment
This skill appears coherent and implements what it claims. Key things to consider before installing: 1) It will run npm install (pulling packages from npm) and on first run will download large ML model files (~500MB) from external model hosts — expect network use and disk space consumption. 2) Data (vector DB and graph) is stored on disk by default (./vector-db and ./memory/ontology); point those paths to a suitable directory and ensure permissions are acceptable. 3) The skill requests no credentials and has no hidden network endpoints in the code, but the embedding/NER model selection is configurable — avoid pointing to untrusted models since a malicious model could change runtime behavior. 4) Review and run the included tests in a sandboxed environment if you want to validate behavior before integrating into production. If you need higher assurance, verify the exact model download hosts used at runtime and consider pinning model sources/versions.Like a lobster shell, security has layers — review code before you run it.
latestvk97bf949tr7rh7rz6fp7723fjx83q8g5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.