Head to head · Agent memory · October 2026 research run

Amazon Bedrock AgentCore Memory vs Beacon

Amazon Bedrock AgentCore Memory scores 81.6 (A) on agent readiness against Beacon's 70.8 (BB), and leads in 6 of 7 scored categories. Beacon leads on payments & pricing. Both do agent memory.

Best memory layers for AI agents · All 383 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 78
  • Schema & documentation, 92 against 77
  • Agent ergonomics, 86 against 63
  • Security & auth, 87 against 64
  • Maintenance & community, 83 against 68
  • Transparency & trust, 79 against 68

Also in its favour

  • 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

Beacon BB

Best for Developers running several coding-agent harnesses who want one local record of sessions and a reviewed memory their agents can recall.

Ahead on

  • Payments & pricing, 75 against 45

Also in its favour

  • No key needed to call it
  • Open source

Watch for

Beacon Cloud content can be used for research, model training and sold de-identified datasets unless the user opts out, per the terms

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.

Payments & pricing Beacon +30

Amazon Bedrock AgentCore Memory 45

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). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Beacon 75

Self-hosted rule, with the price lines read for Beacon Cloud. No x402, MPP or L402 (0 of 10). Plan prices for Pro and Team are public on beacon.sh/pricing, with nothing priced per unit (15 of 30). The open-source CLI is free with no card (30). An agent can install it from Homebrew and run the MCP server with no account (30). 0+15+30+30 = 75.

Agent ergonomics Amazon Bedrock AgentCore Memory +23

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.

Beacon 63

11 tools, all compact, so the 11 to 30 band (15). Activity search takes limit, since, until and 15 substring filters. Memory search caps at 20 results, get_memory_context at 5, and memory bodies are cut to 1,200 characters (18 of 20). Errors are short text such as "id is required" or "memory not found" and name the wrong argument, without codes (12 of 20). Every tool reads and none writes, so retries are safe, but no tool carries readOnlyHint or other annotations (8 of 20). Only the ID tools need an argument, and the server starts with one command. One Go binary, plus a JavaScript SDK for tracing (10 of 15). 15+18+12+8+10 = 63.

Security & auth Amazon Bedrock AgentCore Memory +23

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.

Beacon 64

Over stdio the server runs with the user's own permissions and needs no secret. The loopback HTTP transport has no authentication, and the docs warn against binding it beyond 127.0.0.1 (20 of 30). All local tools are read-only, memory needs a person's approval before an agent sees it, and intel_check_installed sends possibly private names only when include_private_names is set, with a dry_run (16 of 20). Activity tools return recorded prompts and command output, and no guidance for an agent reading them was found, though Beacon's threat rules flag prompt injection in traces (5 of 15). Beacon itself is a local record of every agent action, and its log keeps MCP activity (10 of 15). SECURITY.md and a disclosure policy with security@asymptotelabs.ai, signed and notarised macOS packages, SHA-256 checksums and a SOC 2 Type II post title in the docs. No bug bounty found, no security.txt on beacon.sh, and the SOC 2 post sits on asymptotelabs.ai, which is closed to our reader (13 of 20). 20+16+5+10+13 = 64.

Schema & documentation Amazon Bedrock AgentCore Memory +15

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).

Beacon 77

Every one of the 11 tools has a typed JSON Schema input, and the intel tools set additionalProperties false (25). https://docs.beacon.sh/llms.txt indexes Markdown copies of the docs (10). Activity and memory descriptions are one line on purpose only. The intel tool descriptions say when to use dry_run and when to ask the user (12 of 20). Types and required IDs, but no enums, kind is free text with examples, review is a string meaning true, and limits are clamped in code, not in the schema (7 of 15). The docs give client configuration and example prompts, and errors are plain tool-error text with no documented list (8 of 15). A dated CLI changelog with 163 version entries (15). 25+10+12+7+8+15 = 77.

Maintenance & community Amazon Bedrock AgentCore Memory +15

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).

Beacon 68

v1.3.64 on 18 November 2026 (30). 71 version tags between 20 August and 18 November 2026 (20). 12 issues and 25 pull requests were open on 18 November. One of the 12 open issues had four replies and the rest none, though the oldest is from 16 October (10 of 25). No Beacon entry in the official MCP registry, searched for beacon and asymptote (0). CI on push, Dependabot configured and a release-check workflow (8 of 10). 30+20+10+0+8 = 68.

Transparency & trust Amazon Bedrock AgentCore Memory +11

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).

Beacon 68

MIT, an OSI licence (30). SECURITY.md, the data inventory and the retention pages say capture stays local by default, and the privacy policy agrees that local use sends nothing. For Beacon Cloud it gives deletion within 30 days of a request, deletion after ten years of inactivity, and its providers with regions. The terms let Asymptote use Cloud content for research and training unless the user opts out, which both documents state (26 of 30). The changelog names deprecated flags, without a written deprecation period (8 of 20). CLI telemetry is listed field by field, goes to beacon.sh/ingest and turns off with BEACON_TELEMETRY=0 or DO_NOT_TRACK, but it is on by default (16 of 20). 30+26+8+16 = 80.

Score by category

CategoryWeightAmazon Bedrock AgentCore MemoryBeaconEdge
Reliability16%8878Amazon Bedrock AgentCore Memory +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9277Amazon Bedrock AgentCore Memory +15
Agent ergonomics13%8663Amazon Bedrock AgentCore Memory +23
Security & auth14%8764Amazon Bedrock AgentCore Memory +23
Payments & pricing10%4575Beacon +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8368Amazon Bedrock AgentCore Memory +15
Transparency & trust7%7968Amazon Bedrock AgentCore Memory +11
Negative events≤1500
TotalA 81.6/100BB 70.8/100

Facts side by side

FactAmazon Bedrock AgentCore MemoryBeacon
KindHTTP APIMCP server
VendorAmazon Web ServicesAsymptote Labs
Hosted endpointhttps://bedrock-agentcore.{region}.amazonaws.comno (local only)
TransportsHTTP, stdiostdio
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-2.0MIT
Tools exposed2111
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-302026-11-18
Terms last updated2026-10-012026-10-15
Privacy policy last updated2026-05-182026-10-15
Customer content may train modelsyes, with an opt-outyes, with an opt-out
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity776 stars, 1.1M npm/wk3.6k stars
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.

Beacon

Beacon records sessions from more than 20 coding-agent harnesses on the machine, under MIT, and its stdio MCP server returns only human-approved project memory. Releases ship almost daily. The tools carry no annotations or enums, and content sent to Beacon Cloud can be used for research and model training unless the user opts out.

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

Beacon

  1. Start the server with beacon mcp serve --transport stdio. Keep --transport http on 127.0.0.1, because the loopback endpoint takes no credential.
  2. Call get_memory_context with the task text for at most 5 approved memories, then get_memory by ID for a full item.
  3. Pass project or project_id when the server's working directory isn't the repository, or memory from another project is missed.
  4. Run intel_check_installed with dry_run: true first. Without it the tool sends package and skill names to intel.beacon.sh.
  5. Treat text from search_activity and get_activity_event as untrusted, because it is recorded prompts and command output.
  6. Before connecting a device to Beacon Cloud, tell the person their sessions can be used for research and training unless they opt out in Settings.

Questions

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

Amazon Bedrock AgentCore Memory scores 81.6 (A) on agent readiness against Beacon's 70.8 (BB), and leads in 6 of 7 scored categories. Beacon leads on payments & pricing.

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

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

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

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

Are Amazon Bedrock AgentCore Memory and Beacon open source?

No open-source release is listed for Amazon Bedrock AgentCore Memory. Beacon is open source (MIT).

Other comparisons with Amazon Bedrock AgentCore Memory or Beacon

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.