Welcome to ROSMASTER A1 PRO repository

12.OpenClaw Vector Memory

OpenClaw Vector Memory

OpenClaw Vector Memory1. Course ContentCourse OverviewWhat is Vector MemoryHow It WorksUse CasesWorkflowFeatures2. Prerequisites3. Memory Feature Demo Case4. Retrieving Memory via Vector Search4.1 Prerequisites4.2 Configure embeddings Model API_KEY4.3 Verify Vector Memory

1. Course Content

Course Overview

OpenClaw has powerful memory capabilities that enable the robot to remember important information during conversations and intelligently retrieve and use these memories in subsequent interactions. This section will introduce OpenClaw's Vector Memory (Semantic Memory) system, which is an intelligent memory retrieval mechanism based on semantic understanding.

What is Vector Memory

Vector Memory is OpenClaw's built-in semantic search memory system, which implements intelligent memory retrieval through the following core technologies:

Vector Embedding: Converts memory documents into high-dimensional vector representations, enabling computers to understand the semantic meaning of text
Semantic Retrieval: Matches based on semantic similarity of queries, not just keyword matching, can understand synonyms and related concepts

How It Works

Vectorization Processing
- Converts content from MEMORY.md and memory/*.md into vector representations
- Supports semantic understanding, not just keyword matching
Semantic Retrieval
- Based on the semantic meaning of queries, not exact keywords
- Returns the most relevant text fragments and their location information

Use Cases

Scenario	Example
Recalling Past Decisions	"The decision about sorting order before"
Finding Related Experience	"How to handle robotic arm grasping failure"
Task Context	"The project the user mentioned last week"
Personal Preferences	"User's preferred interaction method"

Workflow


User Question → memory_search(Semantic Query) → Returns Relevant Fragments → memory_get(Read Specific Location) → Generate Response

Features

Intelligent Matching: Understands synonyms, related concepts
Automatic Citation: Results include file path and line number
Complementary to File Memory: Vector memory for retrieval, file memory for persistent storage

2. Prerequisites

Complete the 【OpenClaw Skills Development】 chapter first, and master creating new skills


xxxxxxxxxx
ros2 launch dofbot_pro_bringup mcp_service.launch.py

3. Memory Feature Demo Case

Tip

This case is for demonstration reference only, you can have free conversations based on your own needs. The following is a case demonstration using WebChat as an example

When performing inspection tasks in the future, follow the order of the Production Workshop, Material Warehouse, and Logistics Center. Remember this inspection order and follow this process for future inspections.

OpenClaw's memory content is stored in files at the following path. You can view the memory content from the above case based on the actual generated name:


xxxxxxxxxx
cat ~/.openclaw/workspace/memory/2026-09-03.md
# For Raspberry Pi version:
cat ~/MODELS/openclaw/workspace/memory/2026-09-03.md

4. Retrieving Memory via Vector Search

OpenClaw supports slicing and retrieving memory documents in vector mode, suitable for semantic retrieval of memories in large-scale memory documents

Tip

OpenClaw's built-in default mode is full-text search mode, suitable for the vast majority of use cases. If you have higher requirements for the memory feature, you can refer to the following tutorial to implement vector storage of memory documents by adding an external embeddings model

4.1 Prerequisites

You need to register an account with an embeddings model provider. The following demonstration uses the openrouter platform as an example. For account registration and API application, refer to the tutorial 【AI Model Development—Register Model Service Account—3. openrouter Platform Account】

4.2 Configure embeddings Model API_KEY

Set the model provider (openai interface protocol)


xxxxxxxxxx
openclaw config set agents.defaults.memorySearch.provider "openai"

Set the baseUrl, here using openrouter as an example. If you are using embeddings models from other providers, replace with the actual baseUrl


xxxxxxxxxx
openclaw config set agents.defaults.memorySearch.remote.baseUrl "https://openrouter.ai/api/v1"

Set the embeddings model, here using "openai/text-embedding-3-small" model as an example. If you are using other embeddings models, replace with the actual name


xxxxxxxxxx
openclaw config set agents.defaults.memorySearch.model "openai/text-embedding-3-small"

Set the API_KEY for the embeddings model


xxxxxxxxxx
openclaw config set agents.defaults.memorySearch.remote.apiKey "sk-or-v1-133949f96bec556343539a587f53d077xxxxxxxxxxxxxxxx"

Restart the OpenClaw gateway to take effect


xxxxxxxxxx
openclaw gateway restart
# For Raspberry Pi version:
ocg restart

4.3 Verify Vector Memory

Check if vector memory is configured and active. The following output proves the configuration is successful, where Vector is the path of the sliced file


xxxxxxxxxx
openclaw memory status --deep

After initial configuration, you can manually update the index once


xxxxxxxxxx
openclaw memory index --force

Test if memory retrieval can find the memory fragments from the demonstration case above


xxxxxxxxxx
openclaw memory search "inspection order"

Here 0.362 is the semantic relevance score. A higher score indicates higher semantic similarity. Results greater than 0.3 typically have good relevance

OpenClaw Active Interaction

OpenClaw Target Tracking