New to Claude Skills? Learn how to install them →

mem0ai on GitHub

Mem0 Search

Free

Quickly search and retrieve memories with compact results.

by mem0ai63k stars on mem0ai/mem0
Updated Aug 7, 2026
Get this skill

Free · Opens the source repo

What Mem0 Search does

Mem0 Search is a lightweight skill designed for efficient memory lookups within the Mem0 framework. It allows users to perform quick searches or retrieve specific memories by their IDs, making it ideal for developers and designers who need to reference past decisions or notes without sifting through extensive details. This skill is particularly beneficial when you need to verify if a specific decision has been recorded or to resolve citations that reference memory IDs.

The execution process begins with the user inputting a search query. If the query matches a specific memory ID format, the skill directly retrieves that memory. If not, it runs two parallel search queries: one broad search for general memories and another targeted search focused on decisions. This dual approach ensures that users can access relevant information quickly and efficiently, with results displayed in a compact format that highlights the type, content, date, and ID of each memory.

Mem0 Search is particularly useful in collaborative environments where tracking decisions and maintaining a clear record of past discussions is crucial. By providing a straightforward way to access this information, it enhances productivity and supports better decision-making processes. The compact output format is designed for quick scanning, allowing users to find what they need without unnecessary distractions.

This skill is best suited for users who frequently interact with the Mem0 system and require rapid access to their recorded memories. Whether you're a developer needing to check past implementation decisions or a designer looking for historical context on design choices, Mem0 Search streamlines the lookup process and keeps your workflow efficient.

When to use it

Use this skill when you need to quickly find or verify information stored in your memories.

When not to use it

This skill may not be suitable for users who require detailed context or comprehensive browsing of memory categories.

What you can build with it

Quick Decision Verification

Use Mem0 Search to quickly check if a specific decision was recorded in your memories.

Rapid Memory Lookup

Perform a fast search for past notes or decisions without needing to browse through extensive categories.

Resolving Citations

Easily resolve citations that reference memory IDs by using the direct lookup feature.

How to install Mem0 Search

View source

1. Install with the skills CLI

npx skills add mem0ai/mem0/mem0-search --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by mem0ai

Mem0 Search

Quick search with compact output. Lighter than /mem0-tour.

Execution

Step 1: Parse query

The user provides a search query: /mem0-search auth middleware

If no query provided, ask: "What should I search for?"

Memory ID detection: If the query matches any of these patterns, treat it as a direct memory ID lookup instead of a search:

  • Bare hex: ^[a-f0-9]{8}$ (short ID) or ^[a-f0-9]{8}-[a-f0-9-]+$ (full UUID)
  • Citation ref: [mem0:<hex>] — extract the hex portion

When an ID is detected:

  1. Call get_memory(<id>) directly (if short ID, try as prefix of full UUID)
  2. If found, skip to Step 3 and display the single result
  3. If not found, fall through to search using the ID as query text

Step 2: Search

Run 2 parallel search_memories calls:

  1. Broad: query=<user's query>, filters={"AND": [{"user_id": "<id>"}, {"app_id": "<pid>"}]}, top_k=10, rerank=true
  2. Targeted: query=<user's query>, filters={"AND": [{"user_id": "<id>"}, {"app_id": "<pid>"}, {"metadata": {"type": "decision"}}]}, top_k=5, rerank=true

Step 3: Display

Deduplicate by ID, then show compact results:

## mem0 search: "<query>" (<N> results)

1. [decision] Auth module uses JWT with RS256 keys (2025-05-15) [mem0:a3f8b2c1]
2. [anti_pattern] Don't use symmetric HS256 — leaked in env (2025-05-10) [mem0:7e2d9f4a]
3. [convention] All middleware in src/middleware/ (2025-05-08) [mem0:c4d5e6f7]

Format: <number>. [<type>] <content, 80 chars> (<date>) [mem0:<short_id>]

If no results:

No memories matching "<query>" for project <project_id>.

Output formatting

IMPORTANT: Do NOT use markdown in your output. OpenCode TUI renders text verbatim — markdown like bold, ## headers, and | table | syntax appears as raw characters. Use plain text with indentation for structure. Use dashes for lists. Use spaces to align columns instead of markdown tables.

Frequently asked questions about Mem0 Search

Similar skills