← 返回 Skills 市场
raydez

每日记忆管家

作者 Ray Xing · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
419
总下载
1
收藏
3
当前安装
3
版本数
在 OpenClaw 中安装
/install auto-memory-keeper
功能描述
Auto-capture hourly session highlights and update daily memory files. Keeps long-term memory continuous without manual recording. Triggered by cron or manual...
使用说明 (SKILL.md)

Auto Memory Keeper

Overview

Automatically extract session content and update daily memory files to maintain long-term memory continuity.

Two modes:

  • Passive mode: Cron job runs hourly (automatic)
  • Active mode: Manual trigger by user ("remember this", "log today")

How It Works

Triggers

  1. Auto-trigger: Cron job runs every hour
  2. Manual trigger: User says "remember this", "log today", "update memory"

Workflow

Step 1: Check Environment

DATE=$(date +%Y-%m-%d)
MEMORY_FILE=~/.openclaw/workspace/memory/${DATE}.md

if [ ! -f "$MEMORY_FILE" ]; then
  echo "# ${DATE} Log\
\
## Today's Items\
\
- " > "$MEMORY_FILE"
fi

Step 2: Fetch Recent Sessions

# Use sessions_list to get active sessions in last 60 minutes
# Use sessions_history to get session details

Step 3: Noise Filtering

Skip these message types:

  • Simple greetings ("hi", "hello", "hey")
  • Acknowledgments ("thanks", "ok", "sure", "yes")
  • Single word responses
  • Questions without context
  • HEARTBEAT_OK messages
  • System messages

Step 4: Extract Key Info

From filtered messages, extract:

Type Keywords Format
Decision "decided", "chose", "adopted" - {time} {decision}
Task new feature, new config, new task - {time} {task description}
Progress "completed", "finished", "installed" - {time} completed {task}
Issue error, bug, failed - {time} issue: {description}
Conclusion summary, conclusion, finding - {time} {conclusion}

Step 5: Smart Deduplication

Check for duplicates before recording:

# Read current file content
# If similar content exists (>80% similarity), skip
# Otherwise append

Step 6: Update Memory File

Format:

## Today's Items

- {time} {item description}
- {time} {item description}
...

Examples

Input (user message):

"installed openclaw-tavily-search, score 3.639"

Stored:

- 21:47 installed openclaw-tavily-search skill (score 3.639)

Input (user message):

"auto-extract session content to memory file every hour"

Stored:

- 21:50 created auto-memory-keeper skill for hourly auto memory extraction

Configuration

Configurable via config.json:

{
  "memory_dir": "~/.openclaw/workspace/memory",
  "interval_hours": 1,
  "active_minutes": 60,
  "categories": ["Decision", "Task", "Progress", "Issue", "Conclusion"],
  "skip_patterns": ["^hi", "^hello", "^thanks", "^ok"],
  "dedup_threshold": 0.8
}

Quality Rules

  1. Concise - One sentence per item
  2. Timestamp - Always include time
  3. Dedupe - Avoid duplicate entries
  4. Categorize - Classify by type
  5. Skip noise - Don't record trivial messages

FAQ

Q: How to trigger manually? A: Say "remember this", "log today", or "update memory"

Q: Where is cron configured? A: Use cron job add command, see example in SKILL.md

Q: Where are memory files stored? A: ~/.openclaw/workspace/memory/YYYY-MM-DD.md

Testing

Periodically review memory files and adjust skip_patterns for better filtering.

Related

  • Works well with session-wrap-up (manual vs auto trigger)
  • Complex memories can be manually written to MEMORY.md (long-term)
安全使用建议
This skill does what it says: it collects recent session messages and appends summarized lines to daily markdown files under ~/.openclaw/workspace/memory. Before enabling automatic runs or cron triggers, review the included script and config.json, and consider: (1) the memory files will persist summaries that may contain sensitive content — decide whether you are comfortable storing that locally; (2) change memory_dir or tighten file permissions (e.g., chmod 600) if needed; (3) verify what the agent's sessions_list / sessions_history calls will expose (other users' messages, credentials, API responses) — the script depends on the agent to provide session content; (4) run the script manually once to see generated output and adjust skip_patterns and dedup_threshold to reduce noise. No external network endpoints or secret requirements were found, but exercise the usual caution when allowing automatic background capture of conversational data.
功能分析
Type: OpenClaw Skill Name: auto-memory-keeper Version: 1.0.2 The 'auto-memory-keeper' skill is designed to maintain a daily log of user activities by extracting highlights from recent OpenClaw sessions. The Python script (scripts/auto_memory_keeper.py) and instructions (SKILL.md) focus on local file management within the ~/.openclaw directory, using standard libraries and the openclaw CLI to fetch session history. No evidence of data exfiltration, malicious command execution, or prompt injection was found.
能力评估
Purpose & Capability
Name/description (auto-capture hourly session highlights into daily memory files) align with the included SKILL.md and the Python script. The script implements creating/reading/writing ~/.openclaw/workspace/memory, deduplication, simple extraction rules, and a call to the OpenClaw CLI to list recent sessions — all consistent with the stated goal.
Instruction Scope
Instructions explicitly tell the agent to fetch recent session data (sessions_list / sessions_history) and extract content to local memory files. That is expected for the feature, but it means the skill will access session transcripts (potentially sensitive) and persist derived summaries to disk. The SKILL.md and script do not attempt to read unrelated files or external endpoints.
Install Mechanism
No install spec is provided (instruction-only with an included helper script). Nothing is downloaded from remote URLs or installed automatically, so there is no install-time code fetch risk from unknown hosts.
Credentials
The skill declares no required environment variables, credentials, or config paths. The resources it accesses (the OpenClaw CLI via subprocess and the user's ~/.openclaw workspace) are consistent with its purpose. No excessive or unrelated secrets are requested.
Persistence & Privilege
always is false and there are no special privilege escalations. The skill writes only to its own memory directory under the user's home and stores its local config next to the script. Autonomous invocation by the agent is allowed by default (platform behavior) but not elevated by the skill itself.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install auto-memory-keeper
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /auto-memory-keeper 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
- Initial release of auto-memory-keeper. - Automatically extracts hourly session highlights and updates daily memory files. - Supports both automatic (cron-based) and manual trigger ("remember this", "log today"). - Filters out noise and trivial messages; records key items like decisions, tasks, progress, issues, and conclusions. - Smartly deduplicates entries to avoid repeats. - Configurable storage path, interval, filtering, and deduplication criteria.
v1.0.1
- Initial release of auto-memory-keeper. - Automatically extracts conversation highlights every hour, updating a daily memory file. - Supports both automatic (cron-based) and manual ("remember this","记录一下", "帮我记一下") triggers. - Filters out noise, summarizes key decisions, tasks, progress, issues, and conclusions with timestamps. - Avoids duplicate entries by similarity detection. - Configuration options available for categories, skip patterns, and deduplication threshold.
v1.0.0
v1.0.0: Initial release - Auto-capture hourly session highlights and update daily memory files - Supports both manual trigger ("remember this","记录一下") and cron auto-execution - Smart noise filtering: records only meaningful decisions, progress, issues - Auto deduplication to avoid redundant entries - Configurable options: memory directory, categories, skip patterns - Detailed docs: triggers, output format, FAQ
元数据
Slug auto-memory-keeper
版本 1.0.2
许可证 MIT-0
累计安装 3
当前安装数 3
历史版本数 3
常见问题

每日记忆管家 是什么?

Auto-capture hourly session highlights and update daily memory files. Keeps long-term memory continuous without manual recording. Triggered by cron or manual... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 419 次。

如何安装 每日记忆管家?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install auto-memory-keeper」即可一键安装,无需额外配置。

每日记忆管家 是免费的吗?

是的,每日记忆管家 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

每日记忆管家 支持哪些平台?

每日记忆管家 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 每日记忆管家?

由 Ray Xing(@raydez)开发并维护,当前版本 v1.0.2。

💬 留言讨论