Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
No changes detected in this version (1.0.4). - No file changes between previous and latest version. - No updates to features, documentation, or behavior.
What This Skill Does
Configures OpenClaw memory search to use Ollama as the embeddings server via its OpenAI-compatible /v1/embeddings endpoint, replacing the built-in node-llama-cpp local GGUF loader. Supports multiple embedding models, optional import of existing local GGUFs into Ollama, config drift enforcement, and a launchd watchdog for auto-healing.
Offloading embedding generation to Ollama avoids in-process GGUF loading overhead while keeping all data local, and the drift watchdog ensures config stays consistent across gateway restarts.
When to use it
- Switching OpenClaw memory search from local GGUF loading to Ollama embeddings
- Selecting a different embedding model without manually editing config
- Importing an existing local embedding GGUF into Ollama for reuse
- Running scheduled config drift checks to keep embedding settings consistent
- Rebuilding the memory index after changing embedding providers
Example Workflow
Here's how your AI assistant might use this skill in practice.
User runs install.sh to switch OpenClaw memory search from built-in GGUF to Ollama
- 1Verifies Ollama is installed and reachable at 127.0.0.1:11434
- 2Prompts user to select an embedding model such as nomic-embed-text or embeddinggemma
- 3Updates agents.defaults.memorySearch in OpenClaw config with provider, model, baseUrl, and apiKey fields
- 4Optionally triggers a memory reindex if the embedding fingerprint changed
- 5Calls the Ollama embeddings endpoint and validates the response to confirm setup
OpenClaw memory search uses Ollama for embedding vector generation, with config backed up and verified
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.