Veritas Memory v2 🧠

Conversation is ground truth. Files are cache.

v1 问题：STATE.md 被当作记忆本体，手动维护必然漏。v2 反转：对话即记忆，文件是自动同步的索引。

Architecture

PRIMARY:  sessions_history (last 30 messages)  ← Ground truth
INDEX:    STATE.md (auto-synced)                ← Hot cache, ≤2000 tokens
LONG-TERM: MEMORY.md                            ← Curated, ≤100 lines
RAW:      memory/YYYY-MM-DD.md                  ← Manual notes on demand

Quick Start

1. AGENTS.md 启动协议 v3

新会话启动时：
1. sessions_history(your_last_session, limit=30) → 读对话原文
2. STATE.md 当前状态区 → 快速索引
3. MEMORY.md → 长期上下文
4. 冲突 → 对话为准，修正 STATE.md

2. 去掉手动 WAL，改为会话结束自动同步

对话中不打断写文件。会话结束时：

## Session End Auto-Sync

spawn sub-agent with:
  task: "Read this conversation transcript. Extract key changes:
    - Decisions made
    - Company/project status changes
    - System/infrastructure changes
    - New todos or completed todos
    Append to STATE.md event timeline. Update MEMORY.md if long-term facts changed."

3. Memory Tender（可选，每 2-3 天）

合并旧事件、清理过时记忆、交叉验证。

Core Files

Lessons from v1

1. 对话是记忆本体。 新会话先读 sessions_history，不依赖二手笔记。
2. 不打断写文件。 手工 WAL 必然漏。自动同步比勤奋可靠。
3. 小文件大索引。 STATE.md 保持 ≤50 行、MEMORY.md ≤100 行。信息膨胀就删旧留新。
4. 冲突时对话赢。 文件过期了就修文件，不要用过期信息反驳对话。

ClawHub Package

veritas-memory/
  SKILL.md              ← This file
  templates/
    STATE.md            ← Template
    MEMORY.md           ← Template
    AGENTS_startup.md   ← Startup protocol snippet
  scripts/
    auto-sync.md        ← Sub-agent prompt for session-end sync
    memory-tender.md    ← Periodic maintenance prompt

Bidirectional Verification

Logs are the referee between user and agent.

Agent says X, user says Y:
  → Check sessions_history
  → Agent wrong → "You're right. I misremembered." → Fix cache
  → User wrong → "According to our conversation on [date], we said X. Want to change?"
  → Both right, different times → Clarify timeline

Never say "You're wrong." Present facts neutrally.