Catalog Systems Platform-provider memory AWS Bedrock AgentCore Memory

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.

Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 40 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Type
Managed memory in Bedrock AgentCore vendor fix
Tier
T2
Section
Platform-provider memory
Created
2025-07-16 (preview launch); 2025-10-13 (GA) vendor fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Pricing
Pay-per-use: short-term $1.00/GB ingested (was $0.25/1k events until 2026-10-05) + $0.10/GB-mo storage; long-term $0.75/1k records-mo (built-in) and $0.50/1k retrievals vendor fix
Funding
Amazon/AWS public (AMZN); market cap ~$2T vendor fix
Freshness
2026-10-22 fix
Layer
agent-infra repo fix
Licensing
commercial vendor fix
Deployment locus
cloud vendor fix
Platform vs product
platform vendor fix
SDK languages
python, rest, typescript registry fix
Compliance
csa-star, fedramp, hipaa, iso27001, iso27017, iso27018, iso27701 vendor fix

Memory 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

Alternatives to AWS Bedrock AgentCore Memory → live options ranked by shared design, licence, hosting and MCP support

Similar systems

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

  • Vertex AI Memory Bank (now Agent Platform Memory Bank) T2

    Google Cloud managed memory service, now 'Agent Platform Memory Bank' in Gemini Enterprise Agent Platform. LLM-based memory extraction/consolidation from sessions (background, multimodal, custom topics), per-identity isolation, similarity search, TTL, revisions; used from ADK via VertexAiMemoryBankService.

  • 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

    Public-beta memory stores for Claude Managed Agents: workspace-scoped collections of text documents mounted into the session sandbox as a directory the agent reads and writes with its file tools; every change is versioned for audit and point-in-time restore, and memories can also be managed via API/Console.

  • Cloudflare Agent Memory T2

    Managed persistent memory service for AI agents on Cloudflare's edge. Private beta announced 2026-04-17. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.

  • Google Gemini Memory T1

    Gemini app learns from past chats via the Personal context setting (on by default, can be disabled; temporary chats excluded). Users can import memories and full chat history from ChatGPT, Claude and other assistants (18+, personal accounts, not EEA/CH/UK).

  • 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. Announced by xAI's official Grok account on 2025-04-17 ('Grok now remembers your conversations').

Sources (39 cited facts, 0 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-22
    • Pricing “Pay-per-use” → “Pay-per-use: short-term $1.00/GB ingested (was $0.25/1k events until 2026-10-05) + $0.10/GB-mo storage; long-term $0.75/1k records-mo (built-in) and $0.50/1k retrievals” source
    #195

Related systems

References (3)

Referenced by (3)

  • LlamaIndex (framework) integrates with — LlamaIndex has an official memory integration package llama-index-memory-bedrock-agentcore in its repo. (verified 2026-10-29)
  • Strands Agents (AWS) integrates with — Strands Agents docs have an AgentCore Memory session manager integration page. (verified 2026-10-29)
  • Strands Agents Memory (AWS) integrates with — integrates with Amazon Bedrock AgentCore Memory (SEMANTIC, SUMMARIZATION, USER_PREFERENCE strategies)