AI agent memory resource center
Guides, architecture patterns, and comparisons for building AI agents with persistent memory.
Concepts
Foundational ideas behind AI agent memory — what it is, why it matters, and how it differs from traditional approaches.
What is AI agent memory?
A complete guide to AI agent memory — what it is, why agents need it, how it works, and the key patterns for building memory systems that scale.
RAG vs agent memory: what's the difference?
RAG retrieves static documents. Agent memory stores evolving knowledge. Here's where they overlap, where they diverge, and when to use each.
Architecture
Design patterns and technical decisions for building agent memory systems that scale.
Memory scopes for AI agents
Why flat memory breaks down, how scope hierarchies prevent context pollution, and how to design a scoping model for AI agent memory systems.
Memory consolidation: auto-dream, but auditable
db0 clusters related memories and merges them automatically — with an audit trail, configurable thresholds, and cross-framework support.
Why AI agents forget (and what to do about it)
Context windows are not memory. Here's why agents lose knowledge and the architectural patterns that fix it.
Comparisons
How db0 compares to other memory solutions and approaches.
db0 vs Mem0
Memory retrieval vs full data lifecycle — how db0 and Mem0 approach agent memory differently.
db0 vs CLAUDE.md
Static files vs dynamic scoped memory — when each approach works and where they break down.
db0 vs DIY stack
Redis + pgvector + Postgres vs one SDK — the trade-offs of building your own agent data layer.
Framework guides
Practical guides for adding persistent memory to popular AI agent frameworks.
How Claude Code memory works
Inside Claude Code's CLAUDE.md memory system — how it stores context, where it breaks down, and how db0 extends it.
LangChain deprecated its memory — now what?
BufferMemory is gone. Here's what replaced it and how to add persistent memory to LangChain agents.
Long-term memory for Vercel AI SDK
Adding persistent, scoped memory to AI SDK chatbots and agents with middleware.
How OpenClaw memory works
OpenClaw's compaction-based memory system explained, and how to make it persist across sessions.