mem-search

Query claude-mem's persistent memory store with keyword and project filters.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/Intelligent-Resourcing-Team-Environment/claude-memory --skill mem-search-intelligent-resourcing-team-environment
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mem-search
Source: https://github.com/Intelligent-Resourcing-Team-Environment/claude-memory/tree/main/plugin/skills/mem-search
Command: npx skills add https://github.com/Intelligent-Resourcing-Team-Environment/claude-memory --skill mem-search-intelligent-resourcing-team-environment

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Locating and reconciling past work across multiple sessions is difficult and error-prone; mem-search provides a guided way to query, filter, and retrieve contextual observations from claude-mem.

Core Features & Use Cases

  • Unified memory search: Query across all sessions to surface relevant observations, decisions, and learnings.
  • Contextual timelines: Retrieve surrounding context around an identified item to understand the sequence of events.
  • Controlled data fetch: Filter results before fetching full details to optimize token usage and avoid data overload.

Quick Start

Ask the AI to locate relevant past work by querying claude-mem's memory store and returning a concise context.

Frequently Asked Questions about mem-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search across past sessions to find previous decisions and learnings?

To search past sessions, you query a persistent cross-session memory store using keyword search and filters by project or type. This returns relevant past observations, decisions, and learnings.

What is the best way to retrieve context around a specific past observation?

Retrieving contextual timelines is the best way to get surrounding context. After locating an identified item, you fetch the sequence of events to understand the full historical background of that observation.

How do I minimize token usage when fetching historical work data?

You minimize token usage by filtering results before fetching full details. This controlled data fetch approach optimizes data transfer by narrowing down items in the memory store before retrieval.

Can I filter memory search results by project or type?

Yes, you can filter memory search results by project or type. The search workflow allows you to apply filters to the cross-session memory store to narrow down observations before fetching full details.

Does cross-session memory search work without setting up a persistent memory store?

No, cross-session memory search requires a persistent memory store to function. It queries this store to locate past work, meaning prior observations and decisions must be saved there for retrieval.