search-memory
Local-first memory search and indexing for Openclaw. Use when you need to (1) index memory files, (2) search memory from the CLI, or (3) wire a slash command for memory lookup.
Why use this skill?
Efficiently index and search local Markdown memory files with OpenClaw. Improve agent context and retrieval with keyword and recency-based search.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/trumppo/search-memoryWhat This Skill Does
The search-memory skill provides a robust, local-first retrieval system for OpenClaw agents. It allows for the indexing of local Markdown-based memory files and provides an efficient CLI interface to query this information. By utilizing a hybrid approach of keyword scoring and recency-based boosting, it ensures that the most relevant and up-to-date context is retrieved for the agent, helping it maintain long-term memory across sessions without relying on external cloud databases.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/trumppo/search-memory
Ensure that your environment has the necessary dependencies for running the python scripts. Once installed, verify the installation by running the indexing script to parse your existing memory folder structure.
Use Cases
This skill is ideal for users who manage large repositories of technical documentation, personal journals, or project notes in Markdown format. Developers can use it to quickly surface implementation details from past projects, while researchers can use it to synthesize findings scattered across multiple local files. It is also perfect for wiring into custom slash commands, enabling users to trigger context-aware memory lookups directly from the OpenClaw chat interface.
Example Prompts
- "Search my memory for 'authentication flow' and summarize the steps I noted last month."
- "Look up recent notes on the API refactoring project and tell me what the next pending task is."
- "Search my local files for any mention of 'database optimization' and give me the top 3 relevant points."
Tips & Limitations
The indexer is incremental, meaning you should run the script regularly after updating your memory files to keep the cache fresh. The cache is stored in memory/cache/, so be mindful of file permissions in that directory. Currently, the search is limited to Markdown files within the specified memory/ structure; it does not support indexing of non-text binary files or external web URLs. For optimal performance, keep your primary MEMORY.md updated, as the system places high priority on these central files during the scoring process.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-trumppo-search-memory": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution
Related Skills
mem
Search local memory index (local-first). Use for /mem queries in Telegram.
fullbackup
Create a full local backup of the OpenClaw workspace and configuration using the existing backup-local.sh script. Use for /fullbackup in Telegram or when the user asks for a complete local backup.
gh
Use the GitHub CLI (gh) to perform core GitHub operations: auth status, repo create/clone/fork, issues, pull requests, releases, and basic repo management. Trigger for requests to use gh, manage GitHub repos, PRs, or issues from the CLI.
gitbackup
Create a local Git bundle backup of the OpenClaw workspace repository. Use when running /gitbackup in Telegram or when the user asks to back up Git history/refs to a local file.