Memory Proactive

This skill describes the current proactive recall surfaces that remain useful in the local repository.

Layered Context Injection

Primary engine: tiered_context_injector.py

It combines multiple recall paths before the next interaction:

• recent session recall from shared SQLite state
• governance-backed object and hub recall
• knowledge note recall
• optional live Hindsight recall when the query profile needs it

Example:

python3 scripts/tiered_context_injector.py --query "user preferences"

Useful knobs:

• --min-score 0.3
• --max-results 10
• --recall "project status" "system config"
• --domains project,stock

Generic Domain Routing

Helper: domain_memory.py

This is a lightweight legacy helper for splitting local memory into generic domains so one topic does not crowd out everything else.

Example domains:

• project
• stock
• system
• marketing
• relationship
• general

Example:

python3 scripts/domain_memory.py check project "Milestone planning note"
python3 scripts/domain_memory.py status

Guidance

• use generic domains, not user- or project-specific hardcoded labels
• keep recall queries portable across agent runtimes
• treat this skill as an optional helper layer, not a required production contract

Memory Starter Kit

Hermes-only historical note: this skill is kept for repository continuity, not as a current portable install contract.

Current Status

The old four-layer description is obsolete. The maintained local/public build is the three-layer sidecar documented in:

• README.md
• ARCHITECTURE.md
• docs/compatibility-matrix.md

Use This Skill For

• understanding the historical evolution of the project
• mapping old Hermes deployments to the current sidecar surfaces
• identifying which older helpers are no longer part of the default install set

Do Not Use This Skill As

• a production installation guide
• a multi-agent compatibility contract
• a source of current runtime dependencies

Current Portable Runtime

Use the installed scripts under $AGENT_HOME/scripts/ together with:

• session_to_gbrain.py
• memory_governance_rebuild.py
• tiered_context_injector.py
• memory_guardian.py
• memory_maintenance_cycle.py
• sidecar_acceptance_check.py

Historical Notes

• older Hermes deployments used additional local helpers not shipped by the current installer
• legacy bridge layers mentioned in earlier versions were removed from the maintained public stack
• if a teammate is working from old notes, reconcile them against docs/compatibility-matrix.md before changing runtime behavior

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

# 每日归档
schedule: "30 3 * * *"
script: $AGENT_HOME/scripts/archive_sessions.py

# 每周生命周期
schedule: "0 4 * * 0"
script: $AGENT_HOME/scripts/memory_lifecycle.py