SkillHub ClubShip Full StackFull Stack

memory-transfer

Imported from https://github.com/openclaw/skills.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars

3,130

Hot score

Updated

March 20, 2026

Overall rating

C4.0

Composite score

4.0

Best-practice grade

F32.4

Install command

npx @skill-hub/cli install openclaw-skills-memory-transfer

Repository

openclaw/skills

Skill path: skills/codeblackhole1024/memory-transfer

Imported from https://github.com/openclaw/skills.

Open repository

Best for

Primary workflow: Ship Full Stack.

Technical facets: Full Stack.

Target audience: everyone.

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: openclaw.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

Install memory-transfer into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
Review https://github.com/openclaw/skills before adding memory-transfer to shared team environments
Use memory-transfer for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.

Original source / Raw SKILL.md

---
name: memory-transfer
description: Transfer memory between OpenClaw agents with advanced features: topic-specific filtering, user info privacy protection, and intelligent agent identity adaptation. Use when: (1) Migrating context between agents, (2) Sharing knowledge without leaking user personal info, (3) Backing up agent memory. Supports share mode (filters user data + adapts to target agent) and clone mode (verbatim copy).
metadata:
  {
    "openclaw": { "emoji": "📦" }
  }
---

# Memory Transfer Skill

Transfer memory files and context between OpenClaw agents.

## Use Cases

- Migrate memory from main agent to a sub-agent
- Copy user preferences to a new agent
- Share project context between agents
- Backup agent memory before resets

## How It Works

1. Read source agent's workspace memory files
2. Copy to target agent's workspace
3. Optionally merge with existing memory

## Commands

### List available agents

```bash
ls /home/node/.openclaw/
```

### Transfer memory from source to target

```bash
node memory-transfer.js transfer <source-agent-id> <target-agent-id>
```

### Transfer specific memory file

```bash
node memory-transfer.js transfer <source-agent-id> <target-agent-id> <memory-file>
```

### List agent memories

```bash
node memory-transfer.js list <agent-id>
```

### Preview transfer (dry run)

```bash
node memory-transfer.js transfer <source> <target> --dry-run
```

## Examples

### Transfer main agent memory to coder agent

```bash
node memory-transfer.js transfer main coder
```

### Transfer specific date memory

```bash
node memory-transfer.js transfer main coder 2026-03-01.md
```

### Preview what would be transferred

```bash
node memory-transfer.js transfer main coder --dry-run
```

## Agent Workspaces

OpenClaw agent workspaces are typically at:
- `/home/node/.openclaw/workspace-<agent-id>/`
- Main agent: `/home/node/.openclaw/workspace-main/`

Memory files:
- `MEMORY.md` - Long-term memory
- `memory/YYYY-MM-DD.md` - Daily memories


---

## Skill Companion Files

> Additional files collected from the skill directory layout.

### _meta.json

```json
{
  "owner": "codeblackhole1024",
  "slug": "memory-transfer",
  "displayName": "Memory Transfer",
  "latest": {
    "version": "2.1.1",
    "publishedAt": 1772869979438,
    "commit": "https://github.com/openclaw/skills/commit/076e51d29d2a22ce90222307794d942717d1c23c"
  },
  "history": [
    {
      "version": "1.0.0",
      "publishedAt": 1772523289693,
      "commit": "https://github.com/openclaw/skills/commit/34a4a1de50bb3e6fd69631461d7d0272419c7a02"
    }
  ]
}

```