tiered-memorylisted

# Tiered Memory Architecture for Autonomous Agents ## Overview A deterministic, layered memory engineering framework that replaces naive full-context injection. It organizes agent memory into **4 distinct tiers (Core Injected, Topic Notes, Searchable Session History, and Ephemeral Working Memory)**, ensuring high signal-to-noise ratio and zero context bloating. ## When to Use & When NOT to Use ### When to Use - Agent system design where memory exceeds 5,000 characters and causes context degradation. - Multi-session persistence: preserving stable user preferences and environmental facts across restarts. - Preventing memory drift and hallucinatory rule overrides. ### When NOT to Use - Short, one-shot CLI tasks with no cross-session continuity requirements. - Raw logging or storing multi-megabyte datasets (store in database / file assets instead). ## The 4-Tier Memory Hierarchy | Tier | Name | Storage Location | Injected Every Turn? | Capacity Budget | Contents & Purpose | |---|---|---|:---:|---|---| | **L1** | **Core Memory** | `MEMORY.md` & `USER.md` | ✅ Yes | ≤ 10,000 chars (15%) | Durable user preferences, hard security redlines, production anchors | | **L2** | **Topic Notes** | `notes/*.md` | ❌ On-demand | Uncapped (file-based) | Detailed architecture specs, server inventory, API docs read as needed | | **L3** | **Session History** | SQLite `state.db` (FTS5) | ❌ Via search | Millions of messages | FTS5/Vector searchable past conversations and exact debug logs | | **L