Strands Agents Memory (AWS)

https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/strands-sdk-memory.html

AWS code-first agent framework. Multi-LLM (Bedrock, Anthropic, Gemini, OpenAI). Memory via Mem0 integration (ElastiCache for Valkey + Neptune Analytics) or Bedrock AgentCore Memory. Local default uses FAISS; OpenSearch for production.

Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 53 cited facts, 1 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Tier
T2
Latest release
not applicable — not OSS fix
License
Apache-2.0 repo fix
Freshness
2026-10-22 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
Maturity
ga registry fix
SDK languages
python, typescript vendor fix
Protocols
mcp-client vendor fix
Developer activity
OpenRank 13.81 (12-mo avg 32.14) — 2026-05 third-party fix

Memory taxonomy

storage
vector
retrieval
similarity
persistence
long-term
update
extraction
unit
fact
governance
opaque
conflict
llm-arbitrate

When to use

Optimised for: AWS Bedrock integration via code-first SDK

Anti-fit: not for non-AWS stacks

Pros & cons

Pros

AWS-native agent framework with first-class Mem0 integration — managed memory without extra ops.

Cons

AWS-only; tightly coupled to Bedrock/AgentCore; not portable to other clouds.

Claims & capabilities

Open-source SDK from AWS; integrates with Amazon Bedrock AgentCore Memory (SEMANTIC, SUMMARIZATION, USER_PREFERENCE strategies); used in production by Amazon Q Developer, AWS Glue, VPC Reachability Analyzer, and Smartsheet. AWS + Mem0 partnership brings persistent memory to next-gen Strands agents

Technical surface

API surface
SDK: Python (Agent + ConversationManager; Bedrock AgentCore Memory)
Backend storage
pluggable (AgentCore, Mem0)
Deployment
Both (OSS self-hosted; AWS Bedrock AgentCore managed cloud)
Embedding model
multiple supported
Multi-tenancy
namespace
MCP
native (first-party) — Strands MCP support
A2A
supported — Strands A2A server
OpenTelemetry
first-class — built-in OTel

Similar systems

Other framework-embedded memory in the catalog, ranked by inbound references.

  • Spring AI ChatMemory T3

    Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.

  • Flowise Memory T1

    Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by an internal chat_message DB table; Buffer Window kept the last K interactions, Summary Buffer compressed older turns while keeping recent ones verbatim.

  • LangGraph Persistence T2

    Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.

  • AutoGen Memory T2

    AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, bug and security fixes only), and Microsoft points new projects to Microsoft Agent Framework.

  • CrewAI Memory T2

    Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.

  • Hermes Agent memory (Nous Research) T3

    Nous Research's open-source self-improving agent keeps an agent-curated MEMORY.md/USER.md notebook injected at session start, full-text (FTS5) search over past sessions that returns raw messages without LLM summarisation, and optional Honcho user modelling. one of the most-starred agent projects of 2026.

Sources (52 cited facts, 1 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. 2026-10-23
    • Compliance “Inherits AWS/Bedrock compliance: SOC 1/2/3, ISO 27001, HIPAA, PCI DSS, GDPR, FedRAMP; VPC, PrivateLink, CloudFormat…” → “Inherits AWS/Bedrock compliance: SOC 1/2/3, ISO 27001, HIPAA, PCI DSS, GDPR, FedRAMP; VPC, PrivateLink” source
    #223
  2. 2026-10-22
    • License “not applicable — not OSS” → “Apache-2.0” source
    • Pricing “Strands SDK OSS free; memory via Bedrock AgentCore Memory: $0.25 per 1,000 short-term memory events; Runtime priced…” → “Strands SDK OSS free; AgentCore Memory: short-term $1.00/GB ingested from 2026-10-06 (was $0.25/1k events); long-term $0.75/1k records-mo, $0.50/1k retrievals” source
    #195

Related systems

References (5)

  • Amazon Neptune Analytics builds on — Memory via Mem0 integration (ElastiCache for Valkey + Neptune Analytics)
  • AWS Bedrock AgentCore Memory integrates with — integrates with Amazon Bedrock AgentCore Memory (SEMANTIC, SUMMARIZATION, USER_PREFERENCE strategies)
  • Bedrock AgentCore (AWS) depends on at runtime — adjacent-infrastructure cell: requires AWS; Bedrock + Mem0 / AgentCore Memory
  • Mem0 integrates with · depends on at runtime — Memory via Mem0 integration (ElastiCache for Valkey + Neptune Analytics) or Bedrock AgentCore Memory. AWS+Mem0 partnership.
  • OpenSearch builds on — OpenSearch for production