AWS Bedrock AgentCore Memory

https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory-integrate-lang.html

AWS managed memory service for agents running on Bedrock AgentCore. Native integrations with LangChain/LangGraph and Strands. Drives long-running MCP servers + agent workloads.

At a glance

Type
Managed memory in Bedrock AgentCore
Tier
T2
Created
2025-07-16 (preview launch); 2025-10-13 (GA)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Pay-per-use
Funding
Amazon/AWS public (AMZN); market cap ~$2T

Taxonomy

storage
proprietary
retrieval
similarity
persistence
cross-session
update
extraction
unit
fact
governance
opaque
conflict
none

When to use

Optimised for: AWS Bedrock-native managed memory + IAM governance

Anti-fit: not for non-AWS stacks

Pros & cons

Pros

Native to Bedrock with deep integration into IAM, KMS, CloudWatch — enterprise compliance posture is built in.

Cons

AWS-only; pricing tied to Bedrock; cross-cloud portability requires rework.

Claims & capabilities

GA 2025-10-13; native integrations with LangChain/LangGraph and Strands; powers long-running MCP servers + agent workloads; SOC 2 / HIPAA / FedRAMP High / PCI-DSS / GDPR compliance; customers include Caylent / Epsilon / Cox Automotive / Thomson Reuters / Workday / NTT Data / MongoDB / PGA TOUR / Pulumi / Snorkel.ai

Technical surface

API surface
REST, SDK: AWS SDKs (boto3, etc.)
Backend storage
custom (AWS-managed)
Deployment
Managed-only
Embedding model
multiple supported
Multi-tenancy
hard-isolation
MCP
native (first-party) — AgentCore supports MCP
A2A
searched not found
OpenTelemetry
first-class — CloudWatch + OTel

Similar systems

Other platform-provider memory in the catalog, ranked by inbound references.

  • Anthropic Claude Memory T1

    Memory tool API + consumer "Memory" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.

  • Anthropic Managed Agents — Memory T3

    Mounts memory as files on a managed filesystem; Claude reads and writes via the same bash/code-execution tools used for agentic tasks. Unit of storage is a file — inspectable, editable, exportable by developers. Full audit log per session. Memory beta launched April 23, 2026, two weeks after Managed Agents itself launched April 8.

  • Cloudflare Agent Memory T2

    Managed persistent memory service for AI agents on Cloudflare's edge. Beta-launched April 2026. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.

  • Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) T1

    GA at Google Cloud Next 2026 (2026-04-22). Vertex AI rebranded as Gemini Enterprise Agent Platform; Memory Bank now "Agent Platform Memory Bank" with new continuous event-streaming + automated memory generation triggered by configurable criteria (event count or idle time). Backed by Agent Runtime that supports long-running agents that maintain state for days. Note: separate "Memory Profiles" feature reported in TheNextWeb but not surfaced in official Google Cloud release notes — treated here as unconfirmed.

  • Google Gemini Memory T1

    Personal Context setting + Personal Intelligence packing. Memory import from ChatGPT/Claude (Mar 2026).

  • Grok Memory (xAI) T1

    Extracts and persists facts from past conversations; applies them to future responses. Per-memory deletion UI; user can also clear all.

Related systems

References (3)

Referenced by (2)

  • Strands Agents (AWS) integrates with — d 2025; Apache-2.0; integrates with AWS Bedrock; used internally before OSS release.
  • Strands Agents Memory (AWS) integrates with — ource SDK from AWS; integrates with Amazon Bedrock AgentCore Memory (SEMANTIC, SUMMARIZATION, USER_PREFERENCE strategies); used

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.