Memory Types · Multi-agent

Shared Memory in Multi-Agent Systems

Shared memory in multi-agent systems lets multiple AI agents read and write a common memory store — enabling coordination, shared context and collective learning, with consistency challenges to manage.

Shared store

A1
Agent 1
Shared store
A2
Agent 2

Definition

What is shared (collective) agent memory?

A common store accessible by an agent pool — team knowledge, shared task state, customer records — vs per-agent private memory.

Collective memory enables agent teams to build on each other’s work: a research agent writes findings, a writing agent reads them, a reviewer agent adds corrections — all through one memory layer. Also called multi-agent memory store or team memory.

Multi-agent shared memory guide

Disambiguation

OS “shared memory” vs agent shared memory

This page is about AI agents sharing a memory layer — not Python multiprocessing.shared_memory or Linux IPC shared memory.

Queries for “python shared memory” and “linux shared memory” refer to operating-system inter-process communication — a different topic entirely. Here we mean multiple LLM agents reading and writing a common semantic or graph memory store.

Patterns

Patterns for multi-agent shared memory

PatternHow it worksPros / cons
Shared vector store + namespaceOne collection; filter by agent_idSimple; needs conflict handling
Shared graph + provenanceEdges tagged with writing agentAudit trail; Zep/Graphiti fit
Blackboard architectureCentral board agents read/writeClassic MAS pattern; coordinator needed
Coordinator writes, workers readLead agent owns memory writesLow conflict; bottleneck risk
Event bus + projectionAgents publish events; memory layer projects stateScalable; eventual consistency

Consistency

The consistency and conflict problem

When two agents write conflicting facts, you need resolution strategies.

  • Last-write-wins — simplest; risky for high-stakes facts
  • Versioning — keep history with version IDs
  • Temporal KG — Zep Graphiti bi-temporal invalidation
  • Locking — coordinator holds write lock per entity
  • Confidence scores — higher-confidence agent wins

Conflicting memory updates · Zep alternatives

Frameworks

Implementation with memory frameworks

  • Engram — scoped collections per team/project; multi-agent state templates (Weaviate GA roadmap, June 2026)
  • Mem0 — namespace by org_id + user_id; multiple agents share org memory
  • Zep — shared graph with agent provenance on edges
  • Letta — shared archival memory across agent instances
  • LangGraph — shared store with thread_id / namespace scoping

How to share memory across agents

FAQ

Frequently asked questions

Why use shared memory for AI agents?

Agent teams need common context — research findings, task state, customer records — without re-deriving facts each turn. Shared memory enables coordination and collective learning.

Shared memory vs per-user memory?

Per-user memory scopes facts to one end user. Shared memory scopes to a team, project or agent pool. Production systems often use both layers.

Is Python shared memory the same as agent shared memory?

No — Python multiprocessing.shared_memory is OS IPC between processes. This page covers AI agents sharing a semantic/graph memory store.

What is the namespace pattern for multi-agent memory?

Single vector/graph store with metadata filters: org_id, team_id, agent_id. Each agent reads shared namespace, writes with provenance tags.

How does Zep handle multi-agent memory?

Shared temporal graph with agent provenance on edges. Bi-temporal invalidation resolves conflicts. LongMemEval +18.5% vs baseline (Rasmussen et al., 2025).

LangGraph shared memory store?

LangGraph supports shared stores with thread/namespace scoping. Pair with LangMem for durable cross-agent LTM.

How do you resolve multi-agent memory conflicts?

Last-write-wins, versioning, temporal KG invalidation (Zep), coordinator merge or confidence scores. See conflicting memories.

Shared memory for coding agent teams?

Blackboard or coordinator pattern: planner writes task state, coder reads constraints, reviewer writes feedback. See coding agents use case and multi-agent memory guide.