Memory Search

Name: Memory Search
Author: davila7

davila7/claude-code-templates

141 installs
30.1k repo stars
Updated August 4, 2026
davila7/claude-code-templates

Implement retrieval over agent long-term memory: chunking, indexing, query routing, and ranking so assistants recall prior sessions and project facts accurately.

About

Guides Claude to design memory-search for AI agents: ingestion, embeddings, filters, query APIs, and grounding rules so assistants retrieve the right prior context without hallucinating or leaking unrelated session data.

Chunking and metadata strategies
Hybrid keyword plus vector retrieval
Recency and relevance ranking
Tool schemas for memory lookup
Privacy and scope boundaries

Memory Search by the numbers

141 all-time installs (skills.sh)
Ranked #3,470 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/davila7/claude-code-templates --skill memory-search

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/davila7/claude-code-templates/memory-search.svg)](https://skillselion.com/skills/davila7/claude-code-templates/memory-search)

Installs	141
repo stars	★ 30.1k
Last updated	August 4, 2026
Repository	davila7/claude-code-templates ↗

What it does

Implement retrieval over agent long-term memory: chunking, indexing, query routing, and ranking so assistants recall prior sessions and project facts accurately.

Files

SKILL.mdMarkdownGitHub ↗

AI Maestro Memory Search

Search your conversation history using semantic, keyword, and symbol matching. Recall past decisions, discussions, and context across sessions. Part of the AI Maestro suite.

Prerequisites

Requires AI Maestro running locally. Memory indexing uses CozoDB for vector search.

# Install memory tools
git clone https://github.com/23blocks-OS/ai-maestro-plugins.git
cd ai-maestro-plugins && ./install-memory-tools.sh

Core Behavior

Before starting any task, search memory for relevant context:

Receive instruction -> Search memory -> Then proceed

Commands

Command	Description
`memory-search.sh "<query>"`	Hybrid search (recommended)
`memory-search.sh "<query>" --mode semantic`	Find conceptually related
`memory-search.sh "<query>" --mode term`	Exact text matching
`memory-search.sh "<query>" --mode symbol`	Code symbol matching
`memory-search.sh "<query>" --role user`	Only user messages
`memory-search.sh "<query>" --role assistant`	Only assistant messages

Search Modes

Mode	Best For
`hybrid` (default)	General search, most cases
`semantic`	Related concepts, different wording
`term`	Exact function/class names
`symbol`	Code identifiers across contexts

Usage Examples

# User asks to continue previous work
memory-search.sh "authentication"

# Find a specific component discussion
memory-search.sh "PaymentService" --mode term

# Find related design discussions
memory-search.sh "error handling patterns" --mode semantic

# Find code symbol references
memory-search.sh "processPayment" --mode symbol

Combining with Other Skills

For complete context, pair with docs-search and graph-query:

memory-search.sh "feature"       # What did we discuss?
docs-search.sh "feature"         # What do docs say?
graph-describe.sh ComponentName  # What is the structure?

Full AI Maestro Experience

This skill is part of the AI Maestro platform, which provides 6 skills for AI agent orchestration: messaging, memory, docs, graph, planning, and agent management.