Search Memory for Openclaw

A high-performance local indexing and search utility designed to retrieve information from project memory files using keyword scoring and recency boosts.

trumppo
v0.1.0
Feb 9, 2026
1
2.5k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install search-memory

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install search-memory using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Search Memory?

Search Memory is a specialized utility within the ecosystem of Openclaw Skills that provides local-first indexing and retrieval capabilities. It is designed to bridge the gap between static documentation and active agent context by allowing users to index their MEMORY.md and various markdown files within a dedicated memory directory. By utilizing this skill, developers can ensure their AI agents have immediate access to historical project data without the overhead of cloud-based vector databases.

This tool is particularly effective for teams maintaining long-term project logs, as it prioritizes information density and relevance. As one of the core Openclaw Skills, it facilitates a more intelligent interaction model where the agent can self-query project history to provide more accurate and context-aware coding assistance.

Search Memory Use Cases

  • Rapidly retrieving specific implementation details from long-term project logs.
  • Indexing project documentation to provide context for AI coding agents.
  • Implementing slash commands for quick memory lookups during active development.
  • Managing large-scale markdown knowledge bases with recency-weighted search results.

How Search Memory Works

  1. The indexing engine scans the root MEMORY.md file and all markdown content within the memory subdirectories.
  2. An incremental cache is generated and stored locally to ensure fast subsequent searches.
  3. The search algorithm applies keyword scoring to identify the most relevant documents.
  4. A recency boost is applied to the scoring logic, giving higher priority to files modified within the last 30 to 90 days.
  5. The system returns the top-ranked results directly to the CLI or the calling agent.

Search Memory Setup

To get started with this skill, you need to initialize your index and then perform your first search. Run the following commands in your terminal:

# Build or update the incremental search index
scripts/index-memory.py

# Search the index for a specific query
scripts/search-memory.py "your query" --top 5

Search Memory Data Schema & Taxonomy

Component Description
Source Files MEMORY.md and memory/**/*.md
Cache Directory memory/cache/
Ranking Method Keyword Scoring + Recency Boost (30/90 days)
Output Format Console-friendly list of top relevant matches

Search Memory Advanced Features

  • Incremental cache support to minimize processing time on large repositories.
  • Customizable recency boosting to tune search relevance for Openclaw Skills.
  • CLI-native interface allowing for easy piping into other development tools.
  • Support for deep-directory scanning of markdown files for comprehensive knowledge retrieval.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*