Skip to content

AI Agent 记忆管理系统:P0/P1/P2 优先级 + 自动归档,Token 降 78%

Notifications You must be signed in to change notification settings

jzOcb/openclaw-memory-management

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OpenClaw Memory Management System

中文版

Does your AI Agent get dumber as it remembers more? This system helps you manage OpenClaw memory efficiently, reducing token usage by 78%.

Based on @ohxiyu's P0/P1/P2 priority system.

Results

Before                        After
├── Lines: 427                ├── Lines: 96  (-77%)
├── Tokens: 6,618             ├── Tokens: 1,488  (-78%)
├── Maintenance: Manual       ├── Maintenance: Auto cron
├── Iron Rules: 17 scattered  ├── Iron Rules: 5 centralized
└── Lesson recall: Full scan  └── Lesson recall: Semantic search

Three-Layer Memory Architecture

MEMORY.md (Hot Memory)        ← Loaded every session, ≤200 lines
├── [P0] Core identity        ← Never expires
├── [P1][date] Active project ← 90-day TTL
└── [P2][date] Temporary      ← 30-day TTL

memory/lessons/*.jsonl        ← Structured lessons, semantic search
memory/archive/               ← Expired content, searchable but not loaded
memory/YYYY-MM-DD.md          ← Daily raw logs

Quick Start

1. Copy template files

cp templates/MEMORY.md ~/.openclaw/workspace/MEMORY.md
cp scripts/memory-janitor.py ~/.openclaw/workspace/scripts/
mkdir -p ~/.openclaw/workspace/memory/{archive,lessons}

2. Set up auto-archive cron

# Daily at 4 AM UTC
(crontab -l 2>/dev/null; echo "0 4 * * * python3 ~/.openclaw/workspace/scripts/memory-janitor.py >> ~/.openclaw/workspace/logs/memory-janitor.log 2>&1") | crontab -

3. Test manually

# Preview mode (no changes)
python3 scripts/memory-janitor.py --dry-run

# Show statistics
python3 scripts/memory-janitor.py --stats

# Run archival
python3 scripts/memory-janitor.py

Files

File Description
scripts/memory-janitor.py Auto-archive script, P2>30d/P1>90d → archive
templates/MEMORY.md Hot memory template with P0/P1/P2 format
templates/AGENTS-rules.md 5 core principles example
templates/lessons.jsonl Structured lesson format

P0/P1/P2 Priority System

Format: - [Priority][Date] Content

  • P0 — Core identity, never expires. e.g., user preferences, safety rules
  • P1 — Active projects, 90-day TTL. e.g., current projects, recent strategies
  • P2 — Temporary, 30-day TTL. e.g., debug notes, one-time events
- [P0] User prefers Chinese responses
- [P1][2026-02-07] TaxForge v1.4.0 released
- [P2][2026-02-05] Debugged cron timezone issue

Core Principles (for AGENTS.md)

Keep only 5 rules. Store other lessons in lessons/*.jsonl for semantic search:

  1. Real money = correctness > speed — Use identical tested code for transactions
  2. Confirm before external actions — Ask before sending emails, tweets, public posts
  3. Two automation systems — Check both system crontab + OpenClaw cron
  4. Process isolation — Long-running bots need setsid, or they get killed by session cleanup
  5. Platform rules first — Read settlement rules before trading on new platforms

Skills / Integration

OpenClaw Skill

cp -r skills/memory-management ~/.openclaw/skills/
# or
cp -r skills/memory-management ~/clawd/skills/

Claude Code

Option 1: Add CLAUDE.md to project root:

cp claude-code/CLAUDE.md ~/your-project/CLAUDE.md

Option 2: Add as a rule:

mkdir -p ~/your-project/.claude/rules
cp claude-code/.claude/rules/memory-management.md ~/your-project/.claude/rules/

Credits

  • @ohxiyu — Original P0/P1/P2 priority system
  • OpenClaw — AI Agent platform

License

MIT

About

AI Agent 记忆管理系统:P0/P1/P2 优先级 + 自动归档,Token 降 78%

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages