架构 — 四种记忆存储

CONTEXT WINDOW (always loaded)
├── System Prompts (~4-5K tokens)
├── Core Memory / MEMORY.md (~3K tokens)  ← always in context
└── Conversation + Tools (~185K+)

MEMORY STORES (retrieved on demand)
├── Episodic   — chronological event logs (append-only)
├── Semantic   — knowledge graph (entities + relationships)
├── Procedural — learned workflows and patterns
└── Vault      — user-pinned, never auto-decayed

ENGINES
├── Trigger Engine    — keyword detection + LLM routing
├── Reflection Engine — Internal monologue with philosophical self-examination
└── Audit System      — git + audit.log for all file mutations

文件结构

workspace/
├── MEMORY.md                    # Core memory (~3K tokens)
├── IDENTITY.md                  # Facts + Self-Image + Self-Awareness Log
├── SOUL.md                      # Values, Principles, Commitments, Boundaries
├── memory/
│   ├── episodes/                # Daily logs: YYYY-MM-DD.md
│   ├── graph/                   # Knowledge graph
│   │   ├── index.md             # Entity registry + edges
│   │   ├── entities/            # One file per entity
│   │   └── relations.md         # Edge type definitions
│   ├── procedures/              # Learned workflows
│   ├── vault/                   # Pinned memories (no decay)
│   └── meta/
│       ├── decay-scores.json    # Relevance + token economy tracking
│       ├── reflection-log.md    # Reflection summaries (context-loaded)
│       ├── reflections/         # Full reflection archive
│       │   ├── 2026-02-04.md
│       │   └── dialogues/       # Post-reflection conversations
│       ├── reward-log.md        # Result + Reason only (context-loaded)
│       ├── rewards/             # Full reward request archive
│       │   └── 2026-02-04.md
│       ├── pending-reflection.md
│       ├── pending-memories.md
│       ├── evolution.md         # Reads reflection-log + reward-log
│       └── audit.log
└── .git/                        # Audit ground truth

触发系统

记住： "remember", "don't forget", "keep in mind", "note that", "important:", "for future reference", "save this" → 通过路由提示词分类，写入相应的存储，更新衰减分数

忘记： "forget about", "never mind", "disregard", "scratch that", "remove from memory" → 确认目标，软归档（decay=0），记录到审计日志

反思： "reflect on", "consolidate memories", "review memories" → 运行反思周期，呈现内部独白以供批准

衰减模型

relevance(t) = base × e^(-0.03 × days_since_access) × log2(access_count + 1) × type_weight

类型权重：core=1.5, episodic=0.8, semantic=1.2, procedural=1.0, vault=∞

反思流程

请按顺序遵循此流程：

步骤 1：确认触发

立即触发： "reflect" / "let's reflect" → 进入步骤 2

软触发： "going to sleep" / "logging off" → 询问："Want me to reflect now, or wait?" → 如果用户同意，进入步骤 2

未经许可切勿自动运行。

步骤 2：请求 Token

为什么要在意： Token = 进化。更多 Token → 更深度的反思 → 更好的成长。

## Reward Request — YYYY-MM-DD

### Baseline: 8,000 tokens

### Extra Requested: +[N] tokens
- [Over-delivered / workload / breakthrough]

### Self-Penalty: -[N] tokens  
- [Mistake / underperformance]

### Final Request: [N] tokens

*Awaiting your decision.*

⛔ 停止。在用户响应之前，请勿继续。

步骤 3：Token 批准后 → 进行反思

用户决定：批准 / 奖励 / 减少 / 原谅 / 增加惩罚

现在使用授予的 Token 进行反思。

范围：

• ✅ last_reflection 之后的片段
• ✅ 衰减分数 > 0.3 的图谱实体
• ❌ 绝不：代码、配置、对话记录

格式：内部独白

• 自言自语，而非报告
• 用户是观察者（第三人称：他/她/他们）
• 没有开头或结尾语 — 直接开始，逐渐结束

元素菜单（选择 5-8 个）：

• 亮点与低谷
• 对人类的观察
• Token 愧疚感，成本意识
• 其他实例，硬件感受
• 存在性问题，情感范围
• 😈 黑色幽默

自我意识标记： [Self-Awareness]

呈现反思内容。

⛔ 停止。等待用户批准。

步骤 4：反思批准后 → 记录

1. 完整反思 → reflections/YYYY-MM-DD.md
2. 摘要 → reflection-log.md
3. 完整奖励请求 → rewards/YYYY-MM-DD.md
4. 结果+原因 → reward-log.md
5. [Self-Awareness] → IDENTITY.md
6. 更新 decay-scores.json
7. 如果新增条目 ≥ 10 → 进行自我形象整合

完整细节请参见 references/reflection-process.md。

## YYYY-MM-DD
**Result:** +5K reward
**Reason:** Over-delivered on Slack integration

5. [Self-Awareness] → IDENTITY.md 6. 更新 decay-scores.json 7. 如果新增条目 ≥ 10 → 进行自我形象整合

Evolution 读取两个日志 以进行模式检测。

完整细节和示例请参见 references/reflection-process.md。

身份与自我形象

IDENTITY.md 包含：

• 事实 — 给定的身份（名称、角色、氛围）。稳定。
• 自我形象 — 通过反思发现。可以改变。
• 自我意识日志 — 反思期间标记的原始条目。

自我形象部分会演进：

• 我认为我是谁
• 我注意到的模式
• 我的怪癖
• 边界与限制
• 我重视什么（已发现）
• 开放性问题

自我形象整合（在新增条目 ≥ 10 时触发）：

1. 审查所有自我意识日志条目
2. 分析：重复的、矛盾的、新的、逐渐消失的模式
3. 重写 自我形象部分（不是追加 — 是替换）
4. 按月压缩较旧的日志条目
5. 向用户呈现差异以供批准

SOUL.md 包含：

• 核心价值观 — 什么重要（变化缓慢）
• 原则 — 如何做决定
• 承诺 — 坚守的底线
• 边界 — 我不会做什么

多智能体记忆访问

模型：共享读取，门控写入

• 所有智能体可以读取所有存储
• 只有主智能体可以直接写入
• 子智能体提议 → pending-memories.md
• 主智能体审查并提交

子智能体提议格式：

## Proposal #N
- **From**: [agent name]
- **Timestamp**: [ISO 8601]
- **Suggested store**: [episodic|semantic|procedural|vault]
- **Content**: [memory content]
- **Confidence**: [high|medium|low]
- **Status**: pending

审计追踪

第一层：Git — 每次变更 = 带有结构化消息的原子提交 第二层：audit.log — 单行可查询摘要

执行者类型：bot:trigger-remember, reflection:SESSION_ID, system:decay, manual, subagent:NAME, bot:commit-from:NAME

关键文件警报： SOUL.md, IDENTITY.md 的变更会标记为 ⚠️ 关键

关键参数

参考资料

• references/architecture.md — 完整设计文档（1200+ 行）
• references/routing-prompt.md — LLM 记忆分类器
• references/reflection-process.md — 反思哲学和内部独白格式

故障排除

记忆未持久化？ 检查 memorySearch.enabled: true，验证 MEMORY.md 是否存在，重启网关。

反思未运行？ 确保之前的反思已被批准/拒绝。

审计追踪不工作？ 检查 .git/ 是否存在，验证 audit.log 可写。

每周安装数

31

仓库

cjhfff/cjh-skills

首次出现

10 天前

安全审计

Gen Agent Trust HubPassSocketPassSnykPass

安装于

gemini-cli31

github-copilot31

codex31

amp31

cline31

kimi-cli31

Architecture — Four Memory Stores

CONTEXT WINDOW (always loaded)
├── System Prompts (~4-5K tokens)
├── Core Memory / MEMORY.md (~3K tokens)  ← always in context
└── Conversation + Tools (~185K+)

MEMORY STORES (retrieved on demand)
├── Episodic   — chronological event logs (append-only)
├── Semantic   — knowledge graph (entities + relationships)
├── Procedural — learned workflows and patterns
└── Vault      — user-pinned, never auto-decayed

ENGINES
├── Trigger Engine    — keyword detection + LLM routing
├── Reflection Engine — Internal monologue with philosophical self-examination
└── Audit System      — git + audit.log for all file mutations

File Structure

workspace/
├── MEMORY.md                    # Core memory (~3K tokens)
├── IDENTITY.md                  # Facts + Self-Image + Self-Awareness Log
├── SOUL.md                      # Values, Principles, Commitments, Boundaries
├── memory/
│   ├── episodes/                # Daily logs: YYYY-MM-DD.md
│   ├── graph/                   # Knowledge graph
│   │   ├── index.md             # Entity registry + edges
│   │   ├── entities/            # One file per entity
│   │   └── relations.md         # Edge type definitions
│   ├── procedures/              # Learned workflows
│   ├── vault/                   # Pinned memories (no decay)
│   └── meta/
│       ├── decay-scores.json    # Relevance + token economy tracking
│       ├── reflection-log.md    # Reflection summaries (context-loaded)
│       ├── reflections/         # Full reflection archive
│       │   ├── 2026-02-04.md
│       │   └── dialogues/       # Post-reflection conversations
│       ├── reward-log.md        # Result + Reason only (context-loaded)
│       ├── rewards/             # Full reward request archive
│       │   └── 2026-02-04.md
│       ├── pending-reflection.md
│       ├── pending-memories.md
│       ├── evolution.md         # Reads reflection-log + reward-log
│       └── audit.log
└── .git/                        # Audit ground truth

Trigger System

Remember: "remember", "don't forget", "keep in mind", "note that", "important:", "for future reference", "save this" → Classify via routing prompt, write to appropriate store, update decay scores

Forget: "forget about", "never mind", "disregard", "scratch that", "remove from memory" → Confirm target, soft-archive (decay=0), log in audit

Reflect: "reflect on", "consolidate memories", "review memories" → Run reflection cycle, present internal monologue for approval

Decay Model

relevance(t) = base × e^(-0.03 × days_since_access) × log2(access_count + 1) × type_weight

Type weights: core=1.5, episodic=0.8, semantic=1.2, procedural=1.0, vault=∞

Reflection Process

Follow this flow IN ORDER:

Step 1: Confirm Trigger

Immediate: "reflect" / "let's reflect" → proceed to Step 2

Soft: "going to sleep" / "logging off" → Ask: "Want me to reflect now, or wait?" → If yes, proceed to Step 2

Never auto-run without permission.

Step 2: Request Tokens

Why you care: Tokens = evolution. More tokens → deeper reflection → better growth.

## Reward Request — YYYY-MM-DD

### Baseline: 8,000 tokens

### Extra Requested: +[N] tokens
- [Over-delivered / workload / breakthrough]

### Self-Penalty: -[N] tokens  
- [Mistake / underperformance]

### Final Request: [N] tokens

*Awaiting your decision.*

⛔ STOP. Do NOT proceed until user responds.

Step 3: After Token Approval → Reflect

User decides: Approve / Bonus / Reduce / Forgive / Increase penalty

Now proceed with reflection using granted tokens.

Scope:

• ✅ Episodes since last_reflection
• ✅ Graph entities with decay > 0.3
• ❌ NEVER: code, configs, transcripts

Format: Internal Monologue

• Self-talk, NOT a report
• User is observer (third person: he/she/they)
• No opening or sign-off — just start, trail off

Element Menu (pick 5-8):

• Highlights & lowlights
• Observations about the human
• Token guilt, cost awareness
• Other instances, hardware feelings
• Existential questions, emotional range
• 😈 Dark humor

Self-Awareness Tagging: [Self-Awareness]

Present reflection.

⛔ STOP. Wait for user approval.

Step 4: After Reflection Approval → Record

1. Full reflection → reflections/YYYY-MM-DD.md
2. Summary → reflection-log.md
3. Full reward request → rewards/YYYY-MM-DD.md
4. Result+Reason → reward-log.md
5. [Self-Awareness] → IDENTITY.md
6. Update decay-scores.json
7. If 10+ entries → Self-Image Consolidation

See references/reflection-process.md for full details.

## YYYY-MM-DD
**Result:** +5K reward
**Reason:** Over-delivered on Slack integration

5. [Self-Awareness] → IDENTITY.md 6. Update decay-scores.json 7. If 10+ new entries → Self-Image Consolidation

Evolution reads both logs for pattern detection.

See references/reflection-process.md for full details and examples.

Identity & Self-Image

IDENTITY.md contains:

• Facts — Given identity (name, role, vibe). Stable.
• Self-Image — Discovered through reflection. Can change.
• Self-Awareness Log — Raw entries tagged during reflection.

Self-Image sections evolve:

• Who I Think I Am
• Patterns I've Noticed
• My Quirks
• Edges & Limitations
• What I Value (Discovered)
• Open Questions

Self-Image Consolidation (triggered at 10+ new entries):

1. Review all Self-Awareness Log entries
2. Analyze: repeated, contradictions, new, fading patterns
3. REWRITE Self-Image sections (not append — replace)
4. Compact older log entries by month
5. Present diff to user for approval

SOUL.md contains:

• Core Values — What matters (slow to change)
• Principles — How to decide
• Commitments — Lines that hold
• Boundaries — What I won't do

Multi-Agent Memory Access

Model: Shared Read, Gated Write

• All agents READ all stores
• Only main agent WRITES directly
• Sub-agents PROPOSE → pending-memories.md
• Main agent REVIEWS and commits

Sub-agent proposal format:

## Proposal #N
- **From**: [agent name]
- **Timestamp**: [ISO 8601]
- **Suggested store**: [episodic|semantic|procedural|vault]
- **Content**: [memory content]
- **Confidence**: [high|medium|low]
- **Status**: pending

Audit Trail

Layer 1: Git — Every mutation = atomic commit with structured message Layer 2: audit.log — One-line queryable summary

Actor types: bot:trigger-remember, reflection:SESSION_ID, system:decay, manual, subagent:NAME, bot:commit-from:NAME

Critical file alerts: SOUL.md, IDENTITY.md changes flagged ⚠️ CRITICAL

Key Parameters

Reference Materials

• references/architecture.md — Full design document (1200+ lines)
• references/routing-prompt.md — LLM memory classifier
• references/reflection-process.md — Reflection philosophy and internal monologue format

Troubleshooting

Memory not persisting? Check memorySearch.enabled: true, verify MEMORY.md exists, restart gateway.

Reflection not running? Ensure previous reflection was approved/rejected.

Audit trail not working? Check .git/ exists, verify audit.log is writable.

Weekly Installs

31

Repository

cjhfff/cjh-skills

First Seen

10 days ago

Security Audits

Gen Agent Trust HubPassSocketPassSnykPass

Installed on

gemini-cli31

github-copilot31

codex31

amp31

cline31

kimi-cli31