🧠
AI EngineeringPython

Memory Archivist

by mage0535

Memory Archivist is an AI Engineering skill for Claude Code, published by mage0535 in hermes-memory-installer.

204 stars12 forkson mage0535/hermes-memory-installerAdded 2026/09/05Repository updated 2026/08/22
agent-memoryai-agentclaude-codeclicodexcursorgbrainhermeshindsightknowledge-graphllmmemorymulti-agentproductionpythonragretrievalsemantic-searchsidecarvector-memory
Install in seconds
Install Memory Archivist
Copy Memory Archivist into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/mage0535/hermes-memory-installer/tree/main/skills/memory-archivist ~/.claude/skills/memory-archivist

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/mage0535/hermes-memory-installer.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/memory-archivist/SKILL.md in mage0535/hermes-memory-installer
Installs to
~/.claude/skills/memory-archivist
Collection
One of 3 skills cataloged from this repository
Category
AI Engineering3101 skills

What Memory Archivist does

Memory Archivist automates session archiving, knowledge graph sync, and memory lifecycle management. Use it to summarize conversations, sync state.db to gbrain, and clean stale memory.

Memory Archivist is cataloged under AI Engineering on DirSkills. Memory Archivist comes from a repository tagged agent-memory, ai-agent, claude-code, cli and codex.

Documentation

README

Memory Archivist

进阶记忆层。实现自动化: 会话归档 → gbrain 知识图谱同步 → 记忆清理。

核心脚本

1. 会话归档 (archive_sessions.py)

从 state.db 提取完整对话 → 生成结构化摘要 → 写入 gbrain

python3 scripts/archive_sessions.py --session-id <id>

2. 自动摘要 (auto_session_summary.py)

分析对话关键决策/学习/变更 → 生成 session_summary.md

3. 知识图谱同步 (session_to_gbrain.py)

增量同步: Hermes state.db → gbrain pages, 含 timeline + tags + wikilinks

python3 scripts/session_to_gbrain.py --resume  # 断点续传

4. 记忆生命周期 (memory_lifecycle.py)

  • 检测 stale 记忆 (>30天未访问)
  • 标记 expired 记忆 (>90天)
  • 自动清理, 保护已标注 keep 的记忆

5. 记忆守护 (memory_guardian.py)

11.7KB, 最全面的记忆管理:

  • 容量检测 (memory tool 5KB cap)
  • 冲突检测 (新旧信息矛盾)
  • 智能压缩 (合并重复条目)
  • 过期清理

6. 记忆反思 (memory_reflect.py)

周期性运行, 分析近期记忆趋势, 生成用户画像更新建议

Cron 配置

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Memory Archivist

  • What else does mage0535 publish alongside Memory Archivist?

    Memory Archivist is one of 3 skills that DirSkills catalogs from mage0535/hermes-memory-installer, the repository it ships in. Its siblings there include Memory Proactive and Memory Starter Kit. Each one is a separate skill with its own page in this directory, installs the same way Memory Archivist does, and is maintained by mage0535 in that same repository. The rest of the collection is listed on the mage0535/hermes-memory-installer page.

  • How does Memory Archivist compare to other AI Engineering skills?

    Memory Archivist ranks #2803 by stars among the 3101 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Memory Archivist against them. Open each page to compare what they document and how they install.