mem-search

Installation
Summary

Search persistent cross-session memory to answer questions about previous work and past solutions.

  • Three-layer workflow: search for IDs and metadata (50–100 tokens per result), optionally view timeline context around interesting results, then batch-fetch full details only for filtered IDs
  • Search parameters include query text, project name, observation type (bugfix, feature, decision, discovery, change), and date range filtering
  • Timeline tool shows observations, sessions, and prompts interleaved chronologically around an anchor point to understand context
  • Batch get_observations call retrieves complete details (500–1000 tokens each) for multiple IDs in a single request, avoiding N individual fetches
SKILL.md

Memory Search

Search past work across all sessions. Simple workflow: search -> filter -> fetch.

When to Use

Use when users ask about PREVIOUS sessions (not current conversation):

  • "Did we already fix this?"
  • "How did we solve X last time?"
  • "What happened last week?"

3-Layer Workflow (ALWAYS Follow)

NEVER fetch full details without filtering first. 10x token savings.

Step 1: Search - Get Index with IDs

Use the search MCP tool:

Related skills
Installs
3.1K
GitHub Stars
76.5K
First Seen
Feb 7, 2026