Xpersona
H

Hermes Memory

CLAWHUB · Unverified

Hermes风格自驱记忆系统。模仿Hermes Agent的记忆机制，定期自检记忆健康度、自动提醒整理、保持记忆精简高效。 Skill: Hermes Memory Owner: jdvrommel Summary: Hermes风格自驱记忆系统。模仿Hermes Agent的记忆机制，定期自检记忆健康度、自动提醒整理、保持记忆精简高效。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-17T06:57:47.909Z | auto hermes-memory 1.0.0 发布，提供 Hermes 风格的自驱记忆自检和整理提醒工具。 - 支持定期（每天1次）自动检测 MEMORY.md 和 USER.md 文件的使用率 - 达到设定阈值时主动提醒进行记忆整理 - 自动存档和管理历史记忆，保持文件精简高效 - 提供手动运行和定时任务(cron)两种自检方式 - 与 Hermes Agent 的主要区别：整理建议为手动，记忆上限为建议而非硬性 Archive index: Archive v1.0

62
Rank
84
Safety
975
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 975 downloads reported by the source. Last updated 10/11/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s17en3vn8kpe9qzqmt8djzrjhh84dc6x:hermes-memory
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jdvrommel-hermes-memory/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

3,724 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: hermes-memory
version: 1.0.0
description: Hermes风格自驱记忆系统。模仿Hermes Agent的记忆机制，定期自检记忆健康度、自动提醒整理、保持记忆精简高效。
author: 林林
tags:
  - memory
  - self-improving
  - hermes
  - 记忆系统
---

# Hermes风格自驱记忆系统

模仿Hermes Agent的记忆自检机制，定期检查记忆健康度并主动整理。

## 核心机制

| 文件 | 用途 | 建议大小 |
|------|------|---------|
| MEMORY.md | Agent长期记忆 | ≤2200字 |
| USER.md | 用户画像 | ≤1375字 |
| ~/self-improving/ | 技能记忆 | 按需 |

## 功能

- 📊 记忆使用率监控
- 💡 整理建议提醒
- 🔄 自动存档旧记忆
- ⏰ 定时自检（每天1次）

## 运行方式

**手动自检：**
```bash
python3 ~/self-improving/hermes-memory/memory_health.py
```

**自动定时（每天收盘后17:30自检一次）：**
```bash
# 添加到crontab
crontab -e
# 写入：
30 17 * * 1-5 /home/linuxbrew/.linuxbrew/bin/python3 /home/jdvrommel/self-improving/hermes-memory/memory_health.py >> /home/jdvrommel/self-improving/hermes-memory/health.log 2>&1
```

## 触发整理的条件

- MEMORY.md使用率 ≥70% → 建议精简
- MEMORY.md使用率 ≥90% → 必须整理
- USER.md使用率 ≥90% → 必须整理

## 和Hermes的区别

| 功能 | Hermes | 这个Skill |
|------|--------|---------|
| 记忆限制 | 固定2200/1375字 | 建议上限 |
| 自动整理 | Agent自动 | 提示+手动 |
| 记忆工具 | add/replace/remove | 文件编辑 |
| 快照机制 | 冻结快照 | 实时更新 |

_meta.json

{
  "ownerId": "kn7anx58f1k47eb32kqpmt2cz984c7vv",
  "slug": "hermes-memory",
  "version": "1.0.0",
  "publishedAt": 1776409067909
}

skill-card.md

## Description:

Hermes Memory helps agents check local memory-file health, surface cleanup reminders, and keep memory files concise.

This skill is ready for commercial/non-commercial use.

## Publisher:

[jdvrommel](https://clawhub.ai/user/jdvrommel)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent operators use this skill to monitor OpenClaw memory, profile, and state files and receive reminders when memory content should be reduced or reorganized.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The health check reads sensitive OpenClaw memory, profile, and state files.

Mitigation: Review the script before installing and run it only in workspaces where reading those files is acceptable.

Risk: The script reads all top-level files in ~/self-improving during each check.

Mitigation: Limit the scan to an explicit allowlist of expected memory files before scheduling regular runs.

Risk: The cron example runs automatically on weekdays and uses hard-coded local paths.

Mitigation: Adjust paths for the deployment environment and confirm the schedule before enabling cron.

## Reference(s):

- [Hermes Memory on ClawHub](https://clawhub.ai/jdvrommel/skills/hermes-memory)

## Skill Output:

**Output Type(s):** [text, shell commands, configuration, guidance]

**Output Format:** [Plain text status report with shell command examples and an optional JSON state file]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May exit non-zero when cleanup is recommended.]

## Skill Version(s):

1.0.0 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to Hermes Memory and adjacent AI workflows.