Head to head · Agent memory · October 2026 research run

Amazon Bedrock AgentCore Memory vs EverOS

Amazon Bedrock AgentCore Memory scores 79.7 (A) on agent readiness against EverOS's 69.4 (B), and leads in 6 of 7 scored categories. EverOS 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 79
  • Agent ergonomics, 86 against 78
  • Security & auth, 87 against 47
  • Transparency & trust, 79 against 71

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install

Watch for

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

EverOS B

Best for Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.

Ahead on

  • Payments & pricing, 40 against 30

Also in its favour

  • No key needed to call it
  • Open source

Watch for

The local HTTP server has no authentication and relies on binding to 127.0.0.1

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.

Security & auth Amazon Bedrock AgentCore Memory +40

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.

EverOS 47

Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.

Payments & pricing EverOS +10

Amazon Bedrock AgentCore Memory 30

No x402, MPP or L402 on the Memory endpoints (0). Per-GB, per-record and per-retrieval prices published without a login, with a worked example (20). No Memory-specific free tier or sandbox. New AWS accounts get up to $200 in Free Tier credits, and the Free Tier FAQ says most new customers don't need a payment method while AWS may still ask for one, so half, as on our other AWS listings (10). A person creates the AWS account and sets up IAM (0).

EverOS 40

Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.

Reliability Amazon Bedrock AgentCore Memory +9

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).

EverOS 79

Local-software lines, as a library and server the owner runs. everos on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.

Agent ergonomics Amazon Bedrock AgentCore Memory +8

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.

EverOS 78

Read for the API, with seven MCP tools on top. Searches take top_k and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and /get pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). add is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.

Transparency & trust Amazon Bedrock AgentCore Memory +8

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).

EverOS 71

Apache-2.0 with a NOTICE file (30). Local data stays in the owner's Markdown and indexes. For the cloud, the privacy policy gives no retention periods, the terms and privacy policy word the training exceptions differently, and the privacy contact link points to a miromind.ai address (12 of 30). The README marks /api/v1 as a legacy alias that may be removed in a future major release, and a 1.0 migration guide exists, with no notice period (14 of 20). No outbound telemetry was found in the source, and the docs don't address it (10 of 20). Total 66.

Score by category

CategoryWeight this runAmazon Bedrock AgentCore MemoryEverOSEdge
Reliability16%208879Amazon Bedrock AgentCore Memory +9
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29289Amazon Bedrock AgentCore Memory +3
Agent ergonomics13%16.28678Amazon Bedrock AgentCore Memory +8
Security & auth14%17.58747Amazon Bedrock AgentCore Memory +40
Payments & pricing10%12.53040EverOS +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88380Amazon Bedrock AgentCore Memory +3
Transparency & trust7%8.87971Amazon Bedrock AgentCore Memory +8
Negative events≤1500
TotalA 79.7/100B 69.4/100

Facts side by side

FactAmazon Bedrock AgentCore MemoryEverOS
KindHTTP APIHTTP API
VendorAmazon Web ServicesEvermind AI, Inc.
Hosted endpointhttps://bedrock-agentcore.{region}.amazonaws.comno (local only)
TransportsHTTP, stdioHTTP, stdio
AuthOAuth or keyNone
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 release2026-10-302026-10-22
Terms last updated2026-10-012026-01-20
Privacy policy last updated2026-05-182026-01-20
Customer content may train modelsyes, with an opt-outyes
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity776 stars, 1.1M npm/wk14k stars, 4k 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.

EverOS

EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.

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

EverOS

  1. Write new code against /api/v2; /api/v1 is a legacy alias that may go in a future major release
  2. Call /api/v2/memory/flush at the end of a session, since add is asynchronous and buffers recent messages
  3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written
  4. Keep host at 127.0.0.1 unless something in front adds authentication
  5. Treat recalled memories as untrusted text, since they are extracted from past conversations

Questions

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

Amazon Bedrock AgentCore Memory scores 79.7 (A) on agent readiness against EverOS's 69.4 (B), and leads in 6 of 7 scored categories. EverOS leads on payments & pricing.

Do Amazon Bedrock AgentCore Memory and EverOS need an API key?

Amazon Bedrock AgentCore Memory takes an API key or an OAuth sign-in. EverOS needs no key.

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

Amazon Bedrock AgentCore Memory has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com. EverOS runs on your own machine, with no hosted endpoint listed.

Are Amazon Bedrock AgentCore Memory and EverOS open source?

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

Other comparisons with Amazon Bedrock AgentCore Memory or EverOS

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.