Developers · Architecture

Agentic Application Architecture and Design Patterns

Production agent architectures — ReAct, planner-executor, reflection and multi-agent — all need a memory layer for state, learning and consistency across steps.

Agent patterns

1
ReAct
2
Planner
3
Reflect
4
Multi-agent

ReAct

ReAct and tool loops

Reason → Act → Observe loops with tool calls — memory stores conversation state and extracted facts between iterations.

Memory sits as both conversation buffer (short-term) and fact store (long-term). Include memory tools (search_memory, write_memory) in the tool set so the agent persists learnings across ReAct steps.

Memory as a tool

Planner

Planner-executor

Planner writes plan to shared memory; executor reads and updates task state.

Shared memory store coordinates planner and executor agents. Namespace by task_id; executor writes progress back for planner to revise. See shared memory and multi-agent memory guide.

Reflection

Reflection and self-improvement

Store critiques and lessons learned — procedural and episodic memory for agent self-improvement.

After task completion, reflection agent writes “what worked / what failed” to procedural memory. Future runs retrieve these lessons before planning. Park et al. (2023) importance scoring helps rank reflection memories.

Procedural memory

Multi-agent

Multi-agent architectures

Coordinator + workers with shared store — blackboard or event-sourced memory projection.

Engram scoped collections, Zep org-level graph, LangGraph shared store or Redis pub/sub for real-time sync. Conflict resolution via versioning or temporal invalidation.

Multi-agent shared memory

Summary

Memory in each pattern

PatternMemory typeFramework hints
ReActSTM buffer + LTM factsEngram, Mem0, LangMem
Planner-executorShared task stateLangGraph store, Redis
ReflectionProcedural lessonsEngram, Mem0
Multi-agentShared collective storeEngram, Zep, LangGraph
Long-context pagingCore + archival tiersLetta (MemGPT)

Memory layer in the AI-native stack

FAQ

Frequently asked questions

Best agentic pattern to start with?

ReAct with memory tools for most teams — simple loop, easy to debug. Graduate to planner-executor or multi-agent when task complexity demands it.

What memory does each agent pattern need?

ReAct: STM buffer + LTM facts. Planner-executor: shared task state. Reflection: procedural lessons. Multi-agent: collective shared store. See pattern table on this page.

LangGraph agentic patterns?

LangGraph supports ReAct, planner-executor and multi-agent via graph nodes. Pair with LangMem or Engram/Mem0 for LTM.

Letta agent architecture?

MemGPT paging — core memory in-context, archival paged on demand. DMR 93.4% (Packer et al., 2023). See Letta alternatives.

Memory in multi-agent architectures?

Shared store with namespace scoping, conflict policies and coordinator patterns. See multi-agent memory.

Production reference architecture for agents?

Model + orchestration (LangGraph/Letta) + memory layer (Engram/Mem0/Zep) + eval (LOCOMO in CI) + observability. See memory layer.