← Back to Skills Marketplace
Memory Search
by
aigentic-net
· GitHub ↗
· v1.0.0
3600
Downloads
4
Stars
47
Active Installs
1
Versions
Install in OpenClaw
/install memory-search
Description
Search and retrieve relevant information from your indexed memory files using semantic queries and direct file reads for context.
Usage Guidance
Install this only if you want the agent to use stored memory and enabled transcripts when answering personal-context questions. Review what you keep in memory, avoid indexing highly sensitive notes you do not want resurfaced, and expect relevant memory snippets to influence normal answers.
Capability Analysis
Type: OpenClaw Skill
Name: memory-search
Version: 1.0.0
The skill bundle is designed to allow the AI agent to search and retrieve information from its own memory files using `memory_search` and `memory_get` tools. The `SKILL.md` instructions are clear, focused on the stated purpose, and explicitly forbid the agent from attempting to run shell commands (like `cat` or `ls`) to read memory files or to configure/debug the search system. There is no evidence of intentional harmful behavior, data exfiltration, malicious execution, persistence, or prompt injection attempts against the agent to perform actions beyond its stated purpose.
Capability Assessment
Purpose & Capability
The capability is coherent with the stated purpose: it describes `memory_search` and `memory_get` for semantic search and targeted reads of MEMORY.md, memory/*.md, and enabled session transcripts.
Instruction Scope
The instructions broadly encourage memory lookup for prior conversations, preferences, dates, relationships, todos, and project history, but they also define cases where memory should not be used and advise limited fetching.
Install Mechanism
The package contains only SKILL.md with no executable scripts, dependencies, install hooks, shell commands, or environment setup.
Credentials
Access to memory files and enabled transcripts is sensitive but proportionate for a memory-search skill and is disclosed in the artifact.
Persistence & Privilege
The skill relies on an existing memory index and does not create new persistence, request credentials, spawn background workers, use network access, or seek elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install memory-search - After installation, invoke the skill by name or use
/memory-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of memory-search skill.
- Provides two tools: `memory_search` for semantic vector search in memory files, and `memory_get` for reading file sections by line range.
- Enables efficient retrieval of prior conversations, preferences, dates, project history, and other personal context.
- Includes clear usage guidelines, tips, and examples for common scenarios.
- Indexing is automatic; no manual setup required.
- Strictly prohibits accessing memory files via shell commands—use provided APIs only.
Metadata
Frequently Asked Questions
What is Memory Search?
Search and retrieve relevant information from your indexed memory files using semantic queries and direct file reads for context. It is an AI Agent Skill for Claude Code / OpenClaw, with 3600 downloads so far.
How do I install Memory Search?
Run "/install memory-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Memory Search free?
Yes, Memory Search is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Memory Search support?
Memory Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Memory Search?
It is built and maintained by aigentic-net (@aigentic-net); the current version is v1.0.0.
More Skills