memory-search

Search past conversations and decisions to surface relevant context.

Updated Nov 29, 2025

Search Tags:#context #recall #search #memory #vector #conversations #semantics

Ready to run

npx skills add https://github.com/thimslugga/agent-skills --skill memory-search-thimslugga

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-search
Source: https://github.com/thimslugga/agent-skills/tree/main/skills/ai-maestro/memory-search
Command: npx skills add https://github.com/thimslugga/agent-skills --skill memory-search-thimslugga

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Recall relevant context from past conversations and decisions to inform current work and maintain continuity across sessions.

Core Features & Use Cases

Semantic memory search across conversations and decisions to surface relevant context.
Keyword and symbol matching to locate specific discussions and code references.
Use Case: onboarding a new team member by quickly summarizing prior decisions and rationale.

Quick Start

Run memory-search.sh with a query about the current task to surface relevant past discussions and decisions.

Frequently Asked Questions about memory-search

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

FAQPage Schema

How do I recall context from past conversations across different sessions?▼

To recall past conversations across sessions, use semantic memory search to index and retrieve relevant past discussions and decisions. This maintains continuity in multi-step tasks by surfacing prior interactions and rationale.

How does semantic memory search work for maintaining project continuity?▼

Semantic memory search works by indexing past conversations and decisions using vector storage, then matching current queries against that index to retrieve relevant context. This surfaces prior discussions to maintain project continuity.

Do I need vector storage to search past conversations and decisions?▼

Yes, you need an AI Maestro instance with vector storage to index and retrieve memory. This environment is required to perform semantic search across past conversations and surface relevant decisions for current tasks.

What is the best way to onboard a team member using past project decisions?▼

The best way to onboard a team member using past project decisions is to run a semantic memory search query about the project. This summarizes prior decisions and rationale by surfacing relevant past discussions instantly.

Can I use keyword matching to locate specific code references in past discussions?▼

Yes, you can use keyword and symbol matching to locate specific discussions and code references. This works alongside semantic search to pinpoint exact technical context retrieved from past conversations.

How do I search past conversations when starting a new multi-step task?▼

Run a memory search query about your current task to surface relevant past discussions and decisions. This provides immediate context from previous sessions, ensuring continuity when starting new multi-step tasks.