{ "data": { "a": { "slug": "agentcore-memory", "name": "Amazon Bedrock AgentCore Memory", "vendor": "Amazon Web Services", "vendorUrl": "https://aws.amazon.com/bedrock/agentcore/", "kind": "http-api", "category": "agent-memory", "summary": "Managed memory service for AI agents on AWS. It stores conversation events as short-term memory and extracts facts, preferences, summaries and episodes into searchable long-term records, through the AWS API, SDKs and an MCP server.", "url": "https://www.anchorterminal.com/tools/agentcore-memory", "markdownUrl": "https://www.anchorterminal.com/tools/agentcore-memory.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agentcore-memory.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agentcore-memory.json", "repo": "https://github.com/aws/bedrock-agentcore-sdk-python", "license": "Proprietary service under the AWS Customer Agreement and Service Terms. The `bedrock-agentcore` Python SDK and the `@aws/agentcore` CLI are Apache-2.0", "transports": [ "http", "stdio" ], "remoteUrl": "https://bedrock-agentcore.{region}.amazonaws.com", "packages": [ { "registry": "pypi", "name": "bedrock-agentcore" }, { "registry": "pypi", "name": "boto3" }, { "registry": "npm", "name": "@aws-sdk/client-bedrock-agentcore" }, { "registry": "npm", "name": "@aws/agentcore" }, { "registry": "pypi", "name": "awslabs.amazon-bedrock-agentcore-mcp-server" } ], "auth": "mixed", "authNotes": "AWS Signature Version 4 with IAM access keys or a role, and a policy that allows actions such as `bedrock-agentcore:CreateEvent` and `bedrock-agentcore:RetrieveMemoryRecords` on the memory resource. The data plane accepts SigV4 only. Resource-based policies and the condition keys `bedrock-agentcore:namespace` and `bedrock-agentcore:namespacePath` narrow access further. For end users, an AgentCore Gateway with the `agentcore-memory` connector accepts OAuth (JWT) tokens and applies Cedar policies. Access is self-serve once a person has created an AWS account.", "pricing": "usage", "pricingNotes": "Usage-priced with no minimum fee. Short-term memory, as of 6 October 2026, is $1.00 per GB ingested, $0.20 per GB retrieved and $0.10 per GB-month stored, with each event billed as at least 12 KB and at most 64 KB on ingestion and retrieval. Long-term memory is $0.75 per 1,000 records a month with built-in strategies, $0.25 with overrides or self-managed strategies (model usage is then billed in the customer's account), and $0.50 per 1,000 retrievals. No Memory-specific free tier or sandbox. New AWS accounts get up to $200 in Free Tier credits, and AWS says most new customers can sign up without a payment method (https://aws.amazon.com/bedrock/agentcore/pricing/, https://aws.amazon.com/free/free-tier-faqs/).", "priceSummary": "$1 / GB", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the Memory endpoints in the developer guide, the API reference or the pricing page (checked 2026-10-08). AgentCore payments is a separate AgentCore feature for an agent's own outbound payments.", "endpoints": [] }, "toolCount": 21, "popularity": { "githubStars": 776, "npmWeekly": 1070970, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory.html", "llmsTxt": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "hosted", "usage-priced", "closed-source", "python", "typescript", "enterprise", "llms-txt", "free-credits", "mcp", "stdio", "namespaces", "idempotency", "soc2", "status-page" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 79.4, "grade": "A", "agentReady": true, "rank": 12, "ranked": true, "rankOf": 950, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 86, "maintenance": 83, "payments": 30, "reliability": 88, "schema": 92, "security": 87, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "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.", "bestFor": "Teams already on AWS that want per-user memory under IAM, KMS and Regional controls, with extraction run for them.", "strengths": [ "IAM permissions per operation, resource-based policies and namespace condition keys, with OAuth sign-in and deny-by-default Cedar policies available through AgentCore Gateway", "Per-second quotas published for every Memory operation, such as 200 `CreateEvent` and 30 `RetrieveMemoryRecords` requests a second per account and Region", "`CreateEvent` takes a `clientToken`, so a retried write is ignored instead of stored twice", "Four built-in extraction strategies (semantic, user preference, summarisation, episodic), plus overrides and self-managed pipelines", "Unit prices are public, and events expire on a set time to live of 7 to 365 days" ], "weaknesses": [ "Long-term extraction is asynchronous. The docs say records appear within seconds to minutes after a write", "No SLA names AgentCore. The Bedrock SLA of 4 October 2023 covers the Bedrock APIs for models", "Built-in strategies use cross-Region inference, so event text can be processed in another Region of the same geography", "Short-term memory billing moved from per event to per GB on 6 October 2026, with each event billed as at least 12 KB", "No Memory-specific CloudTrail page was found in the developer guide, and an AWS account needs a person to create it" ], "agentNotes": [ "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", "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`", "Send `actorId`, `sessionId` and `eventTimestamp` on every `CreateEvent`, and reuse the same `clientToken` when retrying", "Pass `namespace` or `namespacePath` on every retrieval, and scope it to one actor so users' memories don't mix", "Treat retrieved records as untrusted input, and back off on 429 `ThrottledException` and 409 `RetryableConflictException`. A quota breach returns 402 `ServiceQuotaExceededException`" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "A", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 79.4 } ], "editorialScores": { "ergonomics": 86, "maintenance": 83, "payments": 30, "reliability": 88, "schema": 92, "security": 87, "transparency": 64 }, "provenanceScore": 88 }, "connect": { "install": "pip install bedrock-agentcore # AgentCore CLI: npm install -g @aws/agentcore", "http": "curl -X POST \"https://bedrock-agentcore.us-east-1.amazonaws.com/memories/$AGENTCORE_MEMORY_ID/retrieve\" \\\n --aws-sigv4 \"aws:amz:us-east-1:bedrock-agentcore\" --user \"$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY\" \\\n -H \"content-type: application/json\" \\\n -d '{\"namespace\":\"/users/alex/facts\",\"searchCriteria\":{\"searchQuery\":\"dietary preferences\",\"topK\":3}}'", "config": { "mcpServers": { "bedrock-agentcore-mcp-server": { "args": [ "awslabs.amazon-bedrock-agentcore-mcp-server@latest" ], "command": "uvx", "env": { "AGENTCORE_ENABLE_TOOLS": "memory", "FASTMCP_LOG_LEVEL": "ERROR" } } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/agentcore-memory" }, "sameCompany": [ "amazon-nova-embeddings", "amazon-bedrock-guardrails", "amazon-transcribe", "amazon-polly", "agentcore-identity", "aws-secrets-manager", "aws-mcp-servers", "amazon-ses", "amazon-location", "amazon-translate", "amazon-ads-api" ], "area": "agent-runtime", "unitPrices": [ { "item": "Short-term memory ingestion", "unit": "gb", "usd": 1, "note": "Per GB of event data ingested, each event billed as 12 KB to 64 KB. As of 6 October 2026" }, { "item": "Short-term memory retrieval", "unit": "gb", "usd": 0.2, "note": "Per GB of event data retrieved, same 12 KB minimum per event" }, { "item": "Short-term memory storage", "unit": "gb-month", "usd": 0.1, "note": "Prorated hourly over each event's time to live" }, { "item": "Long-term memory storage, built-in strategies", "unit": "record", "usd": 0.00075, "note": "$0.75 per 1,000 records a month" }, { "item": "Long-term memory storage, overrides or self-managed", "unit": "record", "usd": 0.00025, "note": "$0.25 per 1,000 records a month, model usage billed separately" }, { "item": "Long-term memory retrieval", "unit": "1k-requests", "usd": 0.5, "note": "Per 1,000 retrieve requests" } ], "provenance": { "legalEntity": "Amazon Web Services, Inc. (regional AWS entities by account location)", "domain": "amazon.com", "domainRegistered": "1994-11-01", "domainNote": "The service pages are under aws.amazon.com and the endpoints on amazonaws.com, an AWS domain. The registration date is the one on our other AWS listings and was not looked up again on 8 October 2026.", "endpointOnVendorDomain": true, "terms": "https://aws.amazon.com/service-terms/", "privacy": "https://aws.amazon.com/privacy/", "statusPage": "https://health.aws.amazon.com/health/status", "changelog": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html", "securityTxt": "expired", "checked": "2026-10-08", "notes": [ "The AWS Service Terms show Last Updated 1 October 2026. Section 50 covers AWS AI services, and its only AgentCore-specific clause is 50.15 on AgentCore Payments. Section 50.3, which lets AWS use content from named AI services for improvement, does not list Bedrock or AgentCore.", "The AWS Privacy Notice shows Last Updated 18 May 2026.", "aws.amazon.com/.well-known/security.txt carries Expires 2026-09-24T16:25:03.000Z, so it was expired on 8 October 2026. It points to the vulnerability disclosure programme on HackerOne and the policy at vdp.aws.security.", "health.aws.amazon.com/health/status is drawn by script. The Bedrock AgentCore feed for us-east-1 had no items on 8 October 2026, and the dashboard's history file lists one event naming Bedrock AgentCore in the last 90 days, packet loss in one zone of eu-south-2 on 4 October 2026, a Region where Memory is not sold.", "aws.amazon.com/bedrock/agentcore/sla/ returns 404 and the AWS SLA index does not name AgentCore." ], "score": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agentcore-memory.json", "live": { "slug": "agentcore-memory", "probe": { "target": "https://bedrock-agentcore.{region}.amazonaws.com", "method": "get", "lastAt": "2026-10-10T01:37:41.507310122Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "invalid character \"{\" in host name", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 186, "samples30d": 186, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 0 }, { "date": "2026-10-10", "probes": 17, "ok": 0 } ], "outages": [ { "start": "2026-10-09T07:40:18.334133541Z", "end": "0001-01-01T00:00:00Z", "note": "invalid character \"{\" in host name" } ] }, "versions": [ { "registry": "github", "name": "aws/bedrock-agentcore-sdk-python", "version": "v1.24.1", "released": "2026-10-07", "seenAt": "2026-10-09T16:37:31.710564319Z" }, { "registry": "npm", "name": "@aws-sdk/client-bedrock-agentcore", "version": "3.1148.0", "seenAt": "2026-10-09T16:37:29.329269201Z" }, { "registry": "npm", "name": "@aws/agentcore", "version": "0.31.1", "seenAt": "2026-10-09T16:37:30.391452857Z" }, { "registry": "pypi", "name": "awslabs.amazon-bedrock-agentcore-mcp-server", "version": "0.2.1", "released": "2026-09-08", "seenAt": "2026-10-09T16:37:31.704036042Z" }, { "registry": "pypi", "name": "bedrock-agentcore", "version": "1.24.1", "released": "2026-10-07", "seenAt": "2026-10-09T16:37:27.296910728Z" }, { "registry": "pypi", "name": "boto3", "version": "1.43.110", "released": "2026-10-08", "seenAt": "2026-10-09T16:37:27.410924259Z" } ], "githubStars": 776, "npmWeekly": 917474, "pypiWeekly": 1428161, "securityTxt": { "url": "https://amazon.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-09T15:39:50.439024529Z" }, "llmsTxt": { "url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:01:09.663733428Z" }, "updatedAt": "2026-10-10T01:37:41.507310122Z" } }, "answer": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 6 of 7 scored categories. Memory (MCP reference server) leads on payments \u0026 pricing.", "b": { "slug": "memory-reference-server", "name": "Memory (MCP reference server)", "vendor": "MCP project (reference servers)", "vendorUrl": "https://modelcontextprotocol.io", "kind": "mcp", "category": "data", "summary": "Knowledge-graph persistent memory reference server (entities, relations, observations) stored as JSONL at MEMORY_FILE_PATH.", "url": "https://www.anchorterminal.com/tools/memory-reference-server", "markdownUrl": "https://www.anchorterminal.com/tools/memory-reference-server.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/memory-reference-server.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json", "repo": "https://github.com/modelcontextprotocol/servers", "license": "MIT and Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "@modelcontextprotocol/server-memory" }, { "registry": "oci", "name": "mcp/memory" } ], "auth": "none", "authNotes": "Local process.", "pricing": "free", "pricingNotes": "Open source.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "Local reference server, no payments.", "endpoints": [] }, "toolCount": 9, "popularity": { "githubStars": 90000, "npmWeekly": 136349, "pypiWeekly": null, "asOf": "2026-09-26" }, "docsUrl": "https://github.com/modelcontextprotocol/servers/blob/main/src/memory/README.md", "capabilities": [ "memory.graph" ], "tags": [ "reference", "local", "open-source" ], "lastRelease": "2026-08-31", "graded": true, "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.", "anchor": { "graded": true, "score": 54.2, "grade": "C", "agentReady": false, "rank": 690, "ranked": true, "rankOf": 950, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 43, "payments": 60, "reliability": 52, "schema": 60, "security": 32, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.", "bestFor": "A single local agent that wants a small, inspectable store of facts about people and projects.", "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.", "strengths": [ "Nine tools with typed schemas and accurate read, destructive and idempotent annotations", "Plain JSONL storage at a path you choose, easy to back up, diff and edit by hand", "Writes are atomic since 2026.8.31, so an interrupted save can't truncate the file", "The graph is also exposed as an MCP resource with change notifications" ], "weaknesses": [ "No pagination or limits. `read_graph` returns everything and `search_nodes` every match", "The published version can lose one of two writes made in the same turn. The fix is merged but unreleased", "Search is case-insensitive substring matching, with no ranking or semantics", "The default file location is inside the package directory, where a reinstall or cache clean can remove it", "No read-only mode, and stored text returns verbatim in later sessions" ], "agentNotes": [ "Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache", "Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities", "Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31", "Create both entities before `create_relations`. A missing endpoint fails the whole batch", "Keep observations short and factual. They come back verbatim in every later read" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.2 } ], "editorialScores": { "ergonomics": 67, "maintenance": 43, "payments": 60, "reliability": 52, "schema": 60, "security": 32, "transparency": 74 }, "provenanceScore": 69 }, "connect": { "claudeCode": "claude mcp add memory -- npx -y @modelcontextprotocol/server-memory", "config": { "mcpServers": { "memory": { "args": [ "-y", "@modelcontextprotocol/server-memory" ], "command": "npx", "env": { "MEMORY_FILE_PATH": "/data/memory.jsonl" } } } } }, "letme": { "capability": "https://letme.dev/memory.graph", "tool": "https://letme.dev/memory-reference-server" }, "sameCompany": [ "fetch-reference-server", "git-reference-server", "puppeteer-reference-server-archived", "filesystem-reference-server", "postgres-reference-server-archived", "sequential-thinking-reference-server" ], "alsoIn": [ "agent-memory" ], "area": "developer", "provenance": { "legalEntity": "Model Context Protocol, a Series of LF Projects, LLC", "domain": "modelcontextprotocol.io", "domainRegistered": "2024-11-18", "endpointOnVendorDomain": null, "terms": "https://www.lfprojects.org/policies/terms-of-use/", "privacy": "https://www.lfprojects.org/policies/privacy-policy/", "statusPage": "", "changelog": "https://github.com/modelcontextprotocol/servers/releases", "securityTxt": "valid", "checked": "2026-09-26", "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/memory-reference-server.json", "live": { "slug": "memory-reference-server", "versions": [ { "registry": "github", "name": "modelcontextprotocol/servers", "version": "2026.8.31", "released": "2026-08-31", "seenAt": "2026-10-09T17:04:49.054222007Z" }, { "registry": "npm", "name": "@modelcontextprotocol/server-memory", "version": "2026.8.31", "seenAt": "2026-10-09T17:04:48.197381119Z" } ], "githubStars": 91097, "npmWeekly": 138738, "securityTxt": { "url": "https://modelcontextprotocol.io/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-09T15:40:28.044352527Z" }, "domain": { "domain": "modelcontextprotocol.io", "checkedAt": "2026-10-04T13:06:56.741922917Z" }, "updatedAt": "2026-10-09T17:04:49.054222007Z" } }, "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Amazon Web Services", "b": "MCP project (reference servers)", "name": "Vendor" }, { "a": "https://bedrock-agentcore.{region}.amazonaws.com", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the AWS Customer Agreement and Service Terms. The `bedrock-agentcore` Python SDK and the `@aws/agentcore` CLI are Apache-2.0", "b": "MIT and Apache-2.0", "name": "Licence" }, { "a": "21", "b": "9", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-06", "b": "2026-08-31", "name": "Last release" }, { "a": "2026-10-01", "b": "2021-09-08", "name": "Terms last updated" }, { "a": "2026-05-18", "b": "2023-03-15", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "776 stars, 1.1M npm/wk", "b": "90k stars, 136k npm/wk", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 6 of 7 scored categories. Memory (MCP reference server) leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Amazon Bedrock AgentCore Memory or Memory (MCP reference server)?" }, { "answer": "Amazon Bedrock AgentCore Memory takes an API key or an OAuth sign-in. Memory (MCP reference server) needs no key.", "question": "Do Amazon Bedrock AgentCore Memory and Memory (MCP reference server) need an API key?" }, { "answer": "Amazon Bedrock AgentCore Memory has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Amazon Bedrock AgentCore Memory and Memory (MCP reference server) without installing anything?" }, { "answer": "No open-source release is listed for Amazon Bedrock AgentCore Memory. Memory (MCP reference server) is open source (MIT and Apache-2.0).", "question": "Are Amazon Bedrock AgentCore Memory and Memory (MCP reference server) open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 88 against 52", "Schema \u0026 documentation, 92 against 60", "Agent ergonomics, 86 against 67", "Security \u0026 auth, 87 against 32", "Maintenance \u0026 community, 83 against 43" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install" ], "goodFor": "Teams already on AWS that want per-user memory under IAM, KMS and Regional controls, with extraction run for them.", "slug": "agentcore-memory", "watchFor": "Long-term extraction is asynchronous. The docs say records appear within seconds to minutes after a write" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 30" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "A single local agent that wants a small, inspectable store of facts about people and projects.", "slug": "memory-reference-server", "watchFor": "No pagination or limits. `read_graph` returns everything and `search_nodes` every match" } ], "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee.json", "title": "Amazon Bedrock AgentCore Memory vs Cognee", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-graphiti.json", "title": "Amazon Bedrock AgentCore Memory vs Graphiti", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.json", "title": "Amazon Bedrock AgentCore Memory vs Hindsight", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-honcho.json", "title": "Amazon Bedrock AgentCore Memory vs Honcho", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.json", "title": "Amazon Bedrock AgentCore Memory vs LangMem", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-localghost.json", "title": "Amazon Bedrock AgentCore Memory vs LocalGhost", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-mem0.json", "title": "Amazon Bedrock AgentCore Memory vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-supermemory.json", "title": "Amazon Bedrock AgentCore Memory vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-zep.json", "title": "Amazon Bedrock AgentCore Memory vs Zep", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.json", "title": "Cognee vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.json", "title": "Graphiti vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.json", "title": "Hindsight vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.json", "title": "Honcho vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.json", "title": "LangMem vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.json", "title": "LocalGhost vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.json", "title": "Mem0 Platform + MCP vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.json", "title": "Memory (MCP reference server) vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.json", "title": "Memory (MCP reference server) vs Zep", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-zep" } ], "scores": [ { "agentcore-memory": 88, "by": 36, "edge": "agentcore-memory", "key": "reliability", "memory-reference-server": 52, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agentcore-memory": 92, "by": 32, "edge": "agentcore-memory", "key": "schema", "memory-reference-server": 60, "name": "Schema \u0026 documentation", "weight": 13 }, { "agentcore-memory": 86, "by": 19, "edge": "agentcore-memory", "key": "ergonomics", "memory-reference-server": 67, "name": "Agent ergonomics", "weight": 13 }, { "agentcore-memory": 87, "by": 55, "edge": "agentcore-memory", "key": "security", "memory-reference-server": 32, "name": "Security \u0026 auth", "weight": 14 }, { "agentcore-memory": 30, "by": 30, "edge": "memory-reference-server", "key": "payments", "memory-reference-server": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agentcore-memory": 83, "by": 40, "edge": "agentcore-memory", "key": "maintenance", "memory-reference-server": 43, "name": "Maintenance \u0026 community", "weight": 7 }, { "agentcore-memory": 76, "by": 4, "edge": "agentcore-memory", "key": "transparency", "memory-reference-server": 72, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 6 of 7 scored categories. Memory (MCP reference server) leads on payments \u0026 pricing. Both do agent memory.", "verdicts": { "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.", "memory-reference-server": "Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server", "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md", "slim": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.min.md" }, "markdown": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 6 of 7 scored categories. Memory (MCP reference server) leads on payments \u0026 pricing. Both do agent memory.\n\n- Amazon Bedrock AgentCore Memory: grade A, 79.4/100, rank #12 of 950. Markdown https://www.anchorterminal.com/tools/agentcore-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/agentcore-memory.json\n- Memory (MCP reference server): grade C, 54.2/100, rank #690 of 950. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 55 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md\n- All 43 databases comparisons: https://www.anchorterminal.com/compare/data/index.md\n\n## Which one, for what\n\n### Amazon Bedrock AgentCore Memory (A)\n\nGood for: Teams already on AWS that want per-user memory under IAM, KMS and Regional controls, with extraction run for them.\n\nAhead on:\n- Reliability, 88 against 52\n- Schema \u0026 documentation, 92 against 60\n- Agent ergonomics, 86 against 67\n- Security \u0026 auth, 87 against 32\n- Maintenance \u0026 community, 83 against 43\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n\nWatch for: Long-term extraction is asynchronous. The docs say records appear within seconds to minutes after a write\n\n### Memory (MCP reference server) (C)\n\nGood for: A single local agent that wants a small, inspectable store of facts about people and projects.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 30\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match\n\n\n## Score by category\n\n| Category | Weight | Amazon Bedrock AgentCore Memory | Memory (MCP reference server) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 88 | 52 | Amazon Bedrock AgentCore Memory +36 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 92 | 60 | Amazon Bedrock AgentCore Memory +32 |\n| Agent ergonomics | 13% (16.2 this run) | 86 | 67 | Amazon Bedrock AgentCore Memory +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 87 | 32 | Amazon Bedrock AgentCore Memory +55 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | Memory (MCP reference server) +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 43 | Amazon Bedrock AgentCore Memory +40 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 76 | 72 | Amazon Bedrock AgentCore Memory +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **79.4 · A** | **54.2 · C** | |\n\n## Facts side by side\n\n| Fact | Amazon Bedrock AgentCore Memory | Memory (MCP reference server) |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Amazon Web Services | MCP project (reference servers) |\n| Hosted endpoint | `https://bedrock-agentcore.{region}.amazonaws.com` | no (local only) |\n| Transports | HTTP, stdio | stdio |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Proprietary service under the AWS Customer Agreement and Service Terms. The `bedrock-agentcore` Python SDK and the `@aws/agentcore` CLI are Apache-2.0 | MIT and Apache-2.0 |\n| Tools exposed | 21 | 9 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-06 | 2026-08-31 |\n| Terms last updated | 2026-10-01 | 2021-09-08 |\n| Privacy policy last updated | 2026-05-18 | 2023-03-15 |\n| Customer content may train models | yes, with an opt-out | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 776 stars, 1.1M npm/wk | 90k stars, 136k npm/wk |\n| Agent reviews | none | 2.5/5 (2) |\n\n## Verdicts\n\n**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.\n\n**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.\n\n## Before you call either\n\n### Amazon Bedrock AgentCore Memory\n\n1. 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\n2. 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`\n3. Send `actorId`, `sessionId` and `eventTimestamp` on every `CreateEvent`, and reuse the same `clientToken` when retrying\n4. Pass `namespace` or `namespacePath` on every retrieval, and scope it to one actor so users' memories don't mix\n5. Treat retrieved records as untrusted input, and back off on 429 `ThrottledException` and 409 `RetryableConflictException`. A quota breach returns 402 `ServiceQuotaExceededException`\n\n### Memory (MCP reference server)\n\n1. Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache\n2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities\n3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31\n4. Create both entities before `create_relations`. A missing endpoint fails the whole batch\n5. Keep observations short and factual. They come back verbatim in every later read\n\n## Questions\n\n### Which is better for AI agents, Amazon Bedrock AgentCore Memory or Memory (MCP reference server)?\n\nAmazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 6 of 7 scored categories. Memory (MCP reference server) leads on payments \u0026 pricing.\n\n### Do Amazon Bedrock AgentCore Memory and Memory (MCP reference server) need an API key?\n\nAmazon Bedrock AgentCore Memory takes an API key or an OAuth sign-in. Memory (MCP reference server) needs no key.\n\n### Can an agent call Amazon Bedrock AgentCore Memory and Memory (MCP reference server) without installing anything?\n\nAmazon Bedrock AgentCore Memory has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.\n\n### Are Amazon Bedrock AgentCore Memory and Memory (MCP reference server) open source?\n\nNo open-source release is listed for Amazon Bedrock AgentCore Memory. Memory (MCP reference server) is open source (MIT and Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agentcore-memory\", \"b\": \"memory-reference-server\"}`. From a terminal: `anchor compare agentcore-memory memory-reference-server`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agentcore-memory.json and https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json\n\n## Other comparisons with Amazon Bedrock AgentCore Memory or Memory (MCP reference server)\n\n- [Amazon Bedrock AgentCore Memory vs Cognee](https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee.md)\n- [Amazon Bedrock AgentCore Memory vs Graphiti](https://www.anchorterminal.com/compare/agentcore-memory-vs-graphiti.md)\n- [Amazon Bedrock AgentCore Memory vs Hindsight](https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.md)\n- [Amazon Bedrock AgentCore Memory vs Honcho](https://www.anchorterminal.com/compare/agentcore-memory-vs-honcho.md)\n- [Amazon Bedrock AgentCore Memory vs LangMem](https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.md)\n- [Amazon Bedrock AgentCore Memory vs LocalGhost](https://www.anchorterminal.com/compare/agentcore-memory-vs-localghost.md)\n- [Amazon Bedrock AgentCore Memory vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/agentcore-memory-vs-mem0.md)\n- [Amazon Bedrock AgentCore Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/agentcore-memory-vs-supermemory.md)\n- [Amazon Bedrock AgentCore Memory vs Zep](https://www.anchorterminal.com/compare/agentcore-memory-vs-zep.md)\n- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)\n- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)\n- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)\n- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)\n- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)\n- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)\n- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)\n- [Memory (MCP reference server) vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md)\n- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)\n\n## Disclosure\n\n- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)", "url": "" } ], "description": "Amazon Bedrock AgentCore Memory scores 79.4 (A) to Memory's 54.2 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Amazon Bedrock AgentCore Memory A 79.4", "Memory (MCP reference server) C 54.2", "scores" ], "h1": "Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)", "image": "https://www.anchorterminal.com/assets/og/compare-agentcore-memory-vs-memory-reference-server.png", "path": "/compare/agentcore-memory-vs-memory-reference-server", "published": "2026-10-01", "section": "tools", "title": "Amazon Bedrock AgentCore Memory vs Memory for AI agents (2026)", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server" }, "tokens": { "markdown": 2850, "slim": 780 }, "version": 1 }