Windows Local Embedding

在 Windows 上为 OpenClaw 配置本地 embedding / 本地记忆检索时使用。适用于：下载并接入 `nomic-embed-text-v1.5.Q8_0.gguf`、把 `memorySearch.provider` 改成 `local`、检查 `openclaw memory status...

This skill is coherent and focused on enabling local embeddings on Windows. Before proceeding: (1) backup your C:\Users\...\.openclaw\openclaw.json, (2) verify the HuggingFace download URL and that the file header reads 'GGUF' and file size ≈139 MB, (3) be aware 'npm install node-llama-cpp' will download native binaries and may require admin rights — inspect or run in a test environment if unsure, (4) the provided verification script imports a module from your OpenClaw installation (call-C5sk0PsH.js); inspect that file if you have concerns about running code from the app directory, and (5) if you want stricter isolation, perform the model installation and testing on a non-critical machine or VM first.

Type: OpenClaw Skill Name: windows-local-embedding Version: 1.0.0 The skill provides instructions for configuring local embeddings on Windows, which involves high-risk operations such as downloading external models from HuggingFace, modifying the 'openclaw.json' configuration file, and executing 'npm install' to add dependencies. It also includes a diagnostic JavaScript file (check_memory.mjs) that imports internal application modules from the installation directory. While these actions are consistent with the stated goal of troubleshooting, the reliance on shell execution and package installation for system-level changes qualifies as high-risk behavior without evidence of malicious intent.