Ollama Memory Embeddings

Configure OpenClaw memory search to use Ollama as the embeddings server (OpenAI-compatible /v1/embeddings) instead of the built-in node-llama-cpp local GGUF loading. Includes interactive model selection and optional import of an existing local embedding GGUF into Ollama.

This package looks coherent with its description, but a few practical things to check before installing: - Prerequisites: ensure node, curl, and the ollama CLI are installed and trusted on your machine (the repository metadata incorrectly lists no required binaries). openclaw is optional but needed if you want automatic gateway restart. - Review & dry-run: run install.sh --dry-run to preview changes; verify.sh to test the local embeddings endpoint. - Files touched: the installer will read/write ~/.openclaw/openclaw.json (backups are made before writes) and may create ~/Library/LaunchAgents/*.plist and logs under ~/.openclaw/logs if you opt into the watchdog—these are user-level files. - GGUF import: scanning and importing local GGUFs is opt-in. Do not use --import-local-gguf yes unless you trust the GGUF files on disk. - Persistence: watchdog installation is explicit; uninstall.sh and watchdog.sh --uninstall-launchd provide ways to revert. - Safety: do not run these scripts as root. Inspect install.sh, enforce.sh, and watchdog.sh yourself (they are included). If you want extra assurance, run them in a controlled environment or container first. If you want, I can point out the exact commands the scripts will run in a dry-run or summarize the lines that write your OpenClaw config and the launchd plist.

Type: OpenClaw Skill Name: ollama-memory-embeddings Version: 1.0.4 The skill bundle is benign. It transparently configures OpenClaw to use Ollama for memory embeddings, as described in SKILL.md and README.md. The scripts (install.sh, enforce.sh, watchdog.sh, verify.sh, audit.sh) use robust methods for configuration management (e.g., node for JSON parsing, file locking, backups) and input sanitization (e.g., xml_escape for launchd plist). Network activity is confined to the local loopback address (127.0.0.1:11434) for Ollama, and persistence via watchdog.sh is optional and explicitly documented. There is no evidence of data exfiltration, unauthorized remote control, obfuscation, or malicious prompt injection attempts against the AI agent.