Use Case
Ollama Memory Embeddings is a powerful AI agent skill that extends your assistant with new capabilities. 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 guide walks you through installing Ollama Memory Embeddings, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Ollama Memory Embeddings: npx clawhub@latest --dir ~/.claude/skills install ollama-memory-embeddings
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to documents & notes to trigger Ollama Memory Embeddings
Review the output and refine your prompt for better results
Combine Ollama Memory Embeddings with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Ollama Memory Embeddings
Help me get started with Ollama Memory Embeddings
What can Ollama Memory Embeddings do for my documents & notes workflow?
Show me an example of using Ollama Memory Embeddings
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install ollama-memory-embeddingsOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install ollama-memory-embeddingsβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/ollama-memory-embeddings/π‘Extract and place the folder at the path above, then restart your agent.