LeoYeAI/agent-master-skills / skills/afrexai-agent-memory
Agent Memory Architecture
VerifiedComplete zero-dependency memory system for AI agents β file-based architecture, daily notes, long-term curation, context management, heartbeat integration, and memory hygiene. No APIs, no databases, no external tools. Works with any agent framework.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 2.5 KB |
| SKILL.md | skill md | 17.4 KB |
| _meta.json | config | 297 B |
README.md
View on GitHub# Agent Memory Architecture π§
Complete zero-dependency memory system for AI agents. No APIs, no databases, no external tools β just smart file structures that give your agent perfect recall.
## What This Skill Does
- **5-Layer Memory Architecture** β hot, warm, daily, topic, and archive layers
- **Session Startup Protocol** β what to read and when, optimized for token cost
- **Write-Ahead Protocol** β never lose critical info mid-session
- **Memory Hygiene Schedule** β daily, weekly, monthly, quarterly maintenance
- **Context Window Management** β progressive loading, overflow handling, handoff protocol
- **Heartbeat Integration** β automated memory maintenance during agent wake-ups
- **Security Rules** β what to store, what never to store, privacy in shared contexts
- **Migration Guides** β from no system, from MEMORY.md-only, from external tools
## Install
```bash
clawhub install afrexai-agent-memory-system
```
## Quick Start
```
/memory-status β Check your memory system health
/memory-review β Run weekly review and curation
/remember [fact] β Instantly save something important
/handoff β Prepare for clean session transition
```
## Why Zero Dependencies?
Every other memory skill requires APIs, databases, or cloud services. This one works with plain markdown files. Benefits:
- **$0 cost** β no API calls, no subscriptions
- **Works offline** β no internet required
- **No vendor lock-in** β your files, your control
- **Any framework** β OpenClaw, Cursor, Claude Code, anything
- **Instant setup** β create a few .md files and go
## β‘ Level Up
Want production-ready agent architectures? Our **$47 Context Packs** include complete agent configurations for your industry:
π [Browse Context Packs](https://afrexai-cto.github.io/context-packs/)
## π More Free Skills by AfrexAI
- [afrexai-agent-engineering](https://clawhub.com/skills/afrexai-agent-engineering) β Complete agent design system
- [afrexai-productivity-system](https://clawhub.com/skills/afrexai-productivity-system) β Personal productivity OS
- [afrexai-prompt-engineering](https://clawhub.com/skills/afrexai-prompt-engineering) β Prompt engineering mastery
- [afrexai-decision-engine](https://clawhub.com/skills/afrexai-decision-engine) β Decision-making frameworks
- [afrexai-technical-docs](https://clawhub.com/skills/afrexai-technical-docs) β Documentation system
---
Built by [AfrexAI](https://afrexai-cto.github.io/context-packs/) π€π
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |