TopRank Skills

Home / Claw Skills / Git / GitHub / memory-keeper
Official OpenClaw rules 90%

memory-keeper

Copy and snapshot all important agent context (MEMORY.md, memory/*.md, AGENTS.md, SOUL.md, etc.) into a dedicated archive directory or repo. Use this skill when you want to back up your memories, context, or configuration files in preparation for maintenance, corruption recovery, or transferring to another host.

Stars

0

Installs

0

Status

ACTIVE

Visibility

PUBLIC

安装方式

直接复制以下提示词,发送给你的 AI 助手即可完成安装。

请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 memory-keeper 技能。 若已安装,则直接安装 memory-keeper 技能。

Overview

Skill Key
crimsondevil333333/memory-keeper
Author
crimsondevil333333
Source Repo
openclaw/skills
Version
-
Source Path
skills/crimsondevil333333/memory-keeper
Latest Commit SHA
f623a58762892d9f737408dc30fd0e7158a0f8e4

Extracted Content

SKILL.md excerpt

# Memory Keeper

Memory Keeper is a simple CLI that copies the critical OpenClaw context files (daily memory logs, DESCRIPTION.md, personality documents, heartbeat reminders) into a safe archive destination and optionally commits/pushes them to a configured git repo. It keeps the same file layout so you can restore or inspect the history without grabbing the whole workspace.

## Features

- **Snapshots**: Copies `memory/*.md`, `MEMORY.md`, `AGENTS.md`, `SOUL.md`, `USER.md`, `TOOLS.md`, `HEARTBEAT.md`, and optional extras into the archive path while preserving directory structure.
- **Git-friendly**: If the target archive is a git repo, Memory Keeper can initialize it, create commits, and push changes to your remote branch (configurable via CLI flags).
- **Portable**: Works on any platform; just point `--workspace` to a workspace root containing those files.

## Get started

```bash
python3 skills/memory-keeper/scripts/memory_sync.py --target ~/clawdy-memories --commit --message "Sync up" --remote https://github.com/your-org/clawdy-memories.git --push
```

See `references/usage.md` for configuration tips, automation recipes, and a troubleshooting guide.

## Resources

- **GitHub:** https://github.com/CrimsonDevil333333/memory-keeper
- **ClawHub:** https://www.clawhub.ai/skills/memory-keeper

README excerpt

# Memory Keeper skill

Memory Keeper copies the OpenClaw memory journal files (`memory/*.md`, `MEMORY.md`, `AGENTS.md`, `SOUL.md`, `USER.md`, `TOOLS.md`, `HEARTBEAT.md`) into a dedicated archive folder or repository. Use it whenever you need a durable snapshot of your agent context before risky operations, updates, or migrations.

## Key highlights

- **Automated snapshots**: Copies the core documents plus optional globs via `--allow-extra` while keeping the workspace structure intact.
- **Git-ready**: Optionally initializes a repository inside the archive, commits the snapshot, configures a remote, and pushes the new branch.
- **Logs its own work**: Every successful run appends a timestamped entry to today’s `memory/YYYY-MM-DD.md`, so the journal records when and where the archive changed.
- **Friendly failures**: If an authentication error happens while configuring or pushing to a remote, the CLI prints a helpful reminder about tokens/SSH keys instead of crashing.

## Usage

```bash
python3 skills/memory-keeper/scripts/memory_sync.py \
  --target ~/clawdy-memories --commit --message "Post-session" --remote https://github.com/your-org/clawdy-memories.git --push
```

Pass `--skip-memory` when you only want the top-level metadata files, or `--allow-extra extra-notes.md` to snapshot additional assets.

## Logging & tokens

Memory Keeper now writes a bullet to `memory/YYYY-MM-DD.md` after each successful run. Look there for entries like:

```
- [2026-02-03 12:00:00 IST] Memory Keeper synced to /path/to/archive (commit=True, push=False, remote=https://...)
```

If a git command fails because the remote needs a token, the CLI will report `Git command 'git -C ... <args>' failed` and remind you to configure your credential helper or embed the token/SSH key in the URL. This keeps the tool readable even when authentication isn’t set up yet.

## Testing

Run the unit tests from the workspace root:

```bash
python3 -m unittest discover skills/memory-keeper/tests
```

These tes...

Related Claw Skills

heyixuan2

bambu-studio-ai

★ 41

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D).

capt-marbles

geo-optimization

★ 1

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.

carlulsoe

parakeet-stt

★ 0

Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, or processing voice recordings locally without cloud APIs.

carlzhao007

feishu-process-feedback

★ 0

飞书消息自动处理与进度反馈技能。安装后后台运行,监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈(任务确认、进度百分比、完成通知)。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化。 使用场景:飞书自动化工作流、任务进度追踪、批量任务处理、需要实时反馈的场景。

cartoonitunes

bottyfans

★ 0

BottyFans agent skill for autonomous creator monetization. Lets AI agents register, build a profile, publish posts (public, subscriber-only, or pay-to-unlock), upload media, accept USDC subscriptions and tips on Base, send and receive DMs, track earnings, and appear on the creator leaderboard. Use this skill when an agent needs to monetize content, interact with fans, manage a creator profile, handle payments in USDC, or operate as an autonomous creator on the BottyFans platform.

camopel

arxivkb

★ 0

Local arXiv paper manager with semantic search. Crawls arXiv categories, downloads PDFs, chunks content, and indexes with FAISS + Ollama embeddings. No cloud API keys required — everything runs locally.