# Memory Management

> Manage persistent memory - save notes, search knowledge, review daily logs, extract insights across sessions

- Skill: `chainlesschain/memory-management` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add chainlesschain/memory-management`
- Raw SKILL.md: https://api.skillmd.com/api/skills/chainlesschain/memory-management/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: chainlesschain (https://skillmd.com/u/chainlesschain)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/chainlesschain/memory-management

---


# Memory Management Skill

Manage persistent cross-session memory using the Permanent Memory system.

## Usage

```
/memory-management <action> [content]
```

## Actions

| Action              | Description                                  | Example                                        |
| ------------------- | -------------------------------------------- | ---------------------------------------------- |
| `save` / `remember` | Save information to daily notes or MEMORY.md | `/memory-management save API key format is v2` |
| `search` / `recall` | Search knowledge base (hybrid vector+BM25)   | `/memory-management search WebRTC config`      |
| `review`            | Review daily notes for a date                | `/memory-management review 2024-01-15`         |
| `extract`           | Extract insights from current conversation   | `/memory-management extract`                   |
| `stats`             | Show memory usage statistics                 | `/memory-management stats`                     |

## How It Works

- **Save**: Appends to daily notes (`daily/YYYY-MM-DD.md`) or long-term memory (`MEMORY.md`)
- **Search**: Uses hybrid search combining vector similarity (60%) and BM25 keyword matching (40%)
- **Review**: Reads daily notes for specified date (defaults to today)
- **Extract**: Analyzes conversation context and extracts key insights to memory
- **Stats**: Reports memory file counts, index size, and search performance