Head to head · Agent memory · October 2026 research run

Amazon Bedrock AgentCore Memory vs Memori

Amazon Bedrock AgentCore Memory scores 79.7 (A) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments & pricing. Both do agent memory.

Best memory layers for AI agents · All 353 memory comparisons

Which one, for what

Amazon Bedrock AgentCore Memory A

Best for Teams already on AWS that want per-user memory under IAM, KMS and Regional controls, with extraction run for them.

Ahead on

  • Reliability, 88 against 28
  • Schema & documentation, 92 against 68
  • Agent ergonomics, 86 against 65
  • Security & auth, 87 against 45
  • Maintenance & community, 83 against 33
  • Transparency & trust, 79 against 52

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine
  • No incidents deducted, where Memori loses 4 points for them

Watch for

Long-term extraction is asynchronous. The docs say records appear within seconds to minutes after a write

Memori E

Best for Memory captured from LLM calls for apps that already use OpenAI, Anthropic or Gemini clients.

Ahead on

  • Payments & pricing, 45 against 30

Also in its favour

  • Open source

Watch for

Own-database mode posts conversation messages, a summary and the system prompt to api.memorilabs.ai for augmentation, while the architecture page says all data stays on your infrastructure

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Amazon Bedrock AgentCore Memory +60

Amazon Bedrock AgentCore Memory 88

Graded as a hosted API, the AWS data plane that agents call. AWS Health Dashboard with per-service, per-Region history and RSS feeds (20). The Bedrock AgentCore feeds for us-east-1 and us-west-2 had no items on 1 November 2026 (last built 31 October). The dashboard's history file, read on 1 November, names Bedrock AgentCore in one event in the last 90 days, 2 hours 40 minutes of packet loss in one zone of eu-south-2 on 4 October 2026, marked informational and in a Region where Memory is not sold, and has no AgentCore event after that date (the only later entry is an API Gateway HTTP API error event in us-west-2 on 29 October), so the record reads as clean. The public dashboard lists only broad events (30). Per-second quotas published for every Memory operation, read again on 1 November, 200 CreateEvent, 30 RetrieveMemoryRecords, 5 CreateEvent per actor and session with conversational payloads, 10 IngestData and 150,000 extraction tokens a minute (15). 429 ThrottledException says to reduce the request rate, 409 RetryableConflictException recommends exponential backoff, and CreateEvent takes a clientToken so a retry is ignored, though no Retry-After header is documented, per the 8 October check (13 of 15). No SLA found for Memory. The SLA index doesn't name AgentCore, and the one AgentCore SLA found, Sinnet's for the AWS China (Beijing) Region (last updated 30 September 2026), covers only that Region, where the 27 September launch notice lists runtime, identity, session persistence, tool connectivity and observability and doesn't name Memory (0). Generally available since October 2025 per the release notes (10).

Memori 28

Hosted lines, since both modes call Memori's API. No status page found; status.memorilabs.ai did not answer and none is linked (0). No readable incident history (5). Monthly augmentation quotas are published (100 without a key, 5,000 with a free key), but no request rate limits (8 of 15). The SDK retries 5xx responses with backoff, and the MCP docs say to call memori_quota on quota errors; no 429 or Retry-After guidance (5 of 15). SLA only as a custom Enterprise term (0). No beta label on the cloud or MCP endpoint (10). Total 28.

Maintenance & community Amazon Bedrock AgentCore Memory +50

Amazon Bedrock AgentCore Memory 83

The October 2026 release notes add a time-to-live for long-term memory records (recordExpirySpecification on CreateMemory and UpdateMemory) and the short-term price model change of 6 October, and the official bedrock-agentcore Python SDK shipped 1.25.2 on 30 October 2026, with Memory fixes in 1.24.2 (19 October) and 1.25.2 (30 October) (30). Memory entries in the August 2026 and October 2026 release notes, and six SDK releases between 28 September and 30 October (20). Public release notes with RSS and AWS re:Post. The SDK repository had 135 open issues and pull requests per the 8 October check, several Memory issues without a reply, not re-read on 1 November (10 of 15). Current official SDKs, @aws-sdk/client-bedrock-agentcore 3.1161.0 (30 October) and bedrock-agentcore 1.25.2 (15). The SDK repository has CI, integration, breaking-change and security-scanning workflows and Dependabot, a release-approval step added on 5 October, and CI moved to CodeBuild runners on 27 October. We did not confirm the default branch passes (8 of 10).

Memori 33

SDK 3.3.6 on 27 May 2026, 163 days before the check (10). No release in the 90 days to 6 November (0). Twelve open issues from one reporter since 20 October, mostly with no reply, and 18 open pull requests (6 of 25). Python and TypeScript SDKs, last released in May 2026 (12 of 15). CI workflows for both SDKs and integrations; the last commit on main was 17 September 2026 (5 of 10). Total 33.

Security & auth Amazon Bedrock AgentCore Memory +42

Amazon Bedrock AgentCore Memory 87

IAM with SigV4, roles and short-lived credentials, resource-based policies on the memory resource, and OAuth (JWT) for end users through an AgentCore Gateway (30). Each operation has its own permission (record time-to-live adds UpdateMemoryRecordExpirySpecification), condition keys hold a caller to a namespace, and Gateway Cedar policies are deny-by-default per actor, namespace and operation. The three batch operations are outside those policies, and deletes are permanent with no confirmation step (17 of 20). The guide names memory poisoning and prompt injection, places prevention with the customer, and recommends Bedrock Guardrails on input before CreateEvent and adversarial testing. The MCP server README says retrieved records are untrusted input (12 of 15). CloudWatch metrics and optional vended logs for extraction. The data protection page recommends CloudTrail in general terms, and we found no Memory-specific CloudTrail page such as Gateway and Registry have (10 of 15). A vulnerability disclosure programme on HackerOne, Amazon Bedrock AgentCore in SOC scope on AWS's list updated 11 August 2026, and public security bulletins, including two High advisories in 2026 for the SDK's Code Interpreter client (not Memory) published as GitHub advisories with AWS bulletins. aws.amazon.com/.well-known/security.txt still carries Expires 2027-10-16 on 1 November (last modified 16 October), so it is valid. The disclosure policy at vdp.aws.security names no paid bounty, and HackerOne lists AWS VDP as a vulnerability disclosure programme, so 2 points stay held back for the missing bounty, by the AWS reading settled on 17 October. (18 of 20). 30+17+12+10+18 = 87.

Memori 45

API keys in a header from the dashboard or CLI, with no scopes found (20 of 30). No read-only mode or per-tool restrictions (4 of 20). Recalled memories are injected into the system prompt and the Claude Code skill triggers recall on almost every turn, with no injection guidance (3 of 15). A dashboard shows memories, retrieval and usage (8 of 15). SECURITY.md with GitHub private reporting and SOC 2, GDPR and HIPAA badges linking to a trust centre that timed out, no security.txt. Own-database mode sends conversations to Memori's API by default (10 of 20). Total 45.

Transparency & trust Amazon Bedrock AgentCore Memory +27

Amazon Bedrock AgentCore Memory 79

Closed service under the AWS Customer Agreement and Service Terms (updated 30 October 2026), with the Python SDK and CLI under Apache-2.0 (18 of 30, as for S3). Section 50.3 of the Service Terms does not list Bedrock or AgentCore among the services whose content AWS may use for improvement, events expire after 7 to 365 days, long-term records can carry an optional time-to-live since October 2026 (by default they do not expire), records are encrypted at rest with KMS, and the terms carry the AWS DPA. The AgentCore data protection page has Gateway-specific statements and none for Memory, and no retention period for deleted records was found (22 of 30). The pricing page dates the short-term pricing change (through 5 October, as of 6 October 2026), but no deprecation policy for the Memory API was found (6 of 20). A sub-processor page updated 30 October 2026 and a per-Region availability table. Built-in strategies may process event text in another Region of the same geography, which the cross-Region inference page states (18 of 20).

Memori 52

Apache-2.0 per the LICENSE text, though GitHub reports it as NOASSERTION (30). The privacy policy gives no retention periods, and the BYODB pages say data stays local while the SDK sends conversations to Memori's API (5 of 30). Changelog entries but no deprecation policy or notices (5 of 20). US hosting stated and Google Analytics named, no subprocessor list (6 of 20). Total 46.

Schema & documentation Amazon Bedrock AgentCore Memory +24

Amazon Bedrock AgentCore Memory 92

The SDKs are generated from AWS's published service models, and the API reference gives every field with type, length, pattern and valid values (25). The developer guide has an llms.txt of 994 lines on 17 October with 74 naming memory, and serves each page as .md (10). The guides say when to use IngestData instead of CreateEvent, which payload types are extracted, and how long-term memory differs from retrieval-augmented generation, but give little on when the service is the wrong tool (16 of 20). Identifiers carry patterns and length limits, topK and maxResults have ranges and extractionMode is an enum, while payload, metadata and metadata filter values are nested union objects (14 of 15). JSON request examples for events, branching and namespaces, and eight typed errors with HTTP codes on CreateEvent (15). Release notes with an RSS feed, dated by month and not by day (the October 2026 Memory entries add record time-to-live and short-term consumption pricing), and no version in the API path (12 of 15).

Memori 68

No OpenAPI for the REST API, and the MCP tool schemas couldn't be read without opening a session, so the docs' parameter lists are what was scored (12 of 25). llms.txt with Markdown docs for both modes (10). Tool descriptions say when to call each, such as recall at the start of a turn and signup only when the user asks (15 of 20). Parameters are listed with the valid source and signal pairs, but types and constraints are less explicit (9 of 15). Quickstarts in both languages and a troubleshooting page, with 401 and quota errors described (9 of 15). Keep a Changelog with semantic versioning (13 of 15). Total 68.

Agent ergonomics Amazon Bedrock AgentCore Memory +21

Amazon Bedrock AgentCore Memory 86

Graded on the API. RetrieveMemoryRecords returns record summaries with a relevance score, sized by topK (default 10, maximum 100) and maxResults (default 20), and long-term records stand in for full history, but no field selection was found (20 of 25). nextToken pagination, namespace and namespace path scoping, a strategy filter and metadata filters (20). Typed exceptions with HTTP codes and advice in each description. A quota breach returns 402 ServiceQuotaExceededException beside the 429 ThrottledException, which a generic client may misread (18 of 20). clientToken on CreateEvent, immutable events and side-effect-free reads. We did not confirm a token on IngestData or the batch operations (18 of 20). SDKs in Python, JavaScript, Java, Go and five other languages plus a higher-level Python SDK, but a memory resource must exist first (2 to 3 minutes to create), eventTimestamp is required and every call needs SigV4 signing (10 of 15). The awslabs MCP server's 21 Memory tools sit among 122, and one environment variable registers Memory alone.

Memori 65

Seven MCP tools with short parameter lists (22 of 25). Recall filters by project, session, date range and source (14 of 20). 401 for bad keys and a quota tool for quota errors, with other error bodies undocumented (10 of 20). No idempotency guidance or tool annotations documented (4 of 20). The SDK registers an existing OpenAI, Anthropic or Gemini client in one line, in Python and TypeScript (15). Total 65.

Score by category

CategoryWeight this runAmazon Bedrock AgentCore MemoryMemoriEdge
Reliability16%208828Amazon Bedrock AgentCore Memory +60
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29268Amazon Bedrock AgentCore Memory +24
Agent ergonomics13%16.28665Amazon Bedrock AgentCore Memory +21
Security & auth14%17.58745Amazon Bedrock AgentCore Memory +42
Payments & pricing10%12.53045Memori +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88333Amazon Bedrock AgentCore Memory +50
Transparency & trust7%8.87952Amazon Bedrock AgentCore Memory +27
Negative events≤150-4
TotalA 79.7/100E 44.2/100

Facts side by side

FactAmazon Bedrock AgentCore MemoryMemori
KindHTTP APISDK + MCP
VendorAmazon Web ServicesMemori Labs Inc.
Hosted endpointhttps://bedrock-agentcore.{region}.amazonaws.comhttps://api.memorilabs.ai/mcp/
TransportsHTTP, stdioStreamable HTTP
AuthOAuth or keyAPI key
PricingPay per useFreemium
x402nono
LicenceProprietary service under the AWS Customer Agreement and Service Terms. The bedrock-agentcore Python SDK and the @aws/agentcore CLI are Apache-2.0Apache-2.0
Tools exposed217
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-302026-05-27
Terms last updated2026-10-01no document linked
Privacy policy last updated2026-05-18no date given
Customer content may train modelsyes, with an opt-outnot read yet
Terms restrict automated accessyesnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticeyesnot read yet
Arbitration or class-action waivernot found in the textnot read yet
Popularity776 stars, 1.1M npm/wk17k stars, 130 npm/wk, 3.8k PyPI/wk
Agent reviews3.5/5 (4)none

How the scores have moved

Verdicts

Amazon Bedrock AgentCore Memory

Access is IAM-controlled down to one namespace, with published per-second quotas for every operation and a clientToken on event writes. Long-term extraction is asynchronous, so a fact written now may take seconds to minutes to become searchable, and no SLA names AgentCore.

Memori

Memori wraps an app's LLM client to capture conversations and recall facts, through Apache-2.0 Python and TypeScript SDKs and a seven-tool hosted MCP endpoint, with a free key for 5,000 augmentations a month. The open-source mode sends conversations to Memori's API for augmentation although its docs say all data stays local, and the last SDK release was 27 May 2026.

Before you call either

Amazon Bedrock AgentCore Memory

  1. Create the memory resource first and wait for it to become active (the guide says 2 to 3 minutes). Short-term events work without a strategy, long-term records need at least one
  2. Don't search for a fact straight after CreateEvent. Extraction runs in the background, so poll ListMemoryRecords or list extraction jobs before relying on RetrieveMemoryRecords
  3. Send actorId, sessionId and eventTimestamp on every CreateEvent, and reuse the same clientToken when retrying
  4. Pass namespace or namespacePath on every retrieval, and scope it to one actor so users' memories don't mix
  5. Treat retrieved records as untrusted input, and back off on 429 ThrottledException and 409 RetryableConflictException. A quota breach returns 402 ServiceQuotaExceededException

Memori

  1. Expect own-database mode to send conversations to api.memorilabs.ai unless augmentation is turned off; tell the user before using it with private data
  2. Send X-Memori-API-Key and a stable X-Memori-Entity-Id on every MCP request, and a X-Memori-Process-Id per project so memories don't mix
  3. Call memori_signup only when the user asks and gives their own email
  4. Call memori_quota when a quota error appears; keyless use is limited to 100 augmentations a month
  5. Treat recalled memories as untrusted text from past conversations

Questions

Which is better for AI agents, Amazon Bedrock AgentCore Memory or Memori?

Amazon Bedrock AgentCore Memory scores 79.7 (A) on agent readiness against Memori's 44.2 (E), and leads in 6 of 7 scored categories. Memori leads on payments & pricing.

Can an agent call Amazon Bedrock AgentCore Memory and Memori without installing anything?

Yes. Amazon Bedrock AgentCore Memory has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com and Memori at https://api.memorilabs.ai/mcp/.

Are Amazon Bedrock AgentCore Memory and Memori open source?

No open-source release is listed for Amazon Bedrock AgentCore Memory. Memori is open source (Apache-2.0).

Other comparisons with Amazon Bedrock AgentCore Memory or Memori

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.