{ "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": 842, "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": "2026-10-09T10:14:06.863477896Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "invalid character \"{\" in host name", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 28, "samples30d": 28, "days": [ { "date": "2026-10-09", "probes": 28, "ok": 0 } ], "outages": [ { "start": "2026-10-09T07:40:18.334133541Z", "end": "0001-01-01T00:00:00Z", "note": "invalid character \"{\" in host name" } ] }, "updatedAt": "2026-10-09T10:14:06.863477896Z" } }, "answer": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Hindsight's 50.2 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "hindsight", "name": "Hindsight", "vendor": "Vectorize", "vendorUrl": "https://hindsight.vectorize.io", "kind": "http-api", "category": "agent-memory", "summary": "Memory engine for storing and retrieving information used by agents.", "url": "https://www.anchorterminal.com/tools/hindsight", "markdownUrl": "https://www.anchorterminal.com/tools/hindsight.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hindsight.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hindsight.json", "repo": "https://github.com/vectorize-io/hindsight", "license": "MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.hindsight.vectorize.io", "packages": [ { "registry": "pypi", "name": "hindsight-client" }, { "registry": "npm", "name": "@vectorize-io/hindsight-client" }, { "registry": "pypi", "name": "hindsight-api" } ], "auth": "mixed", "authNotes": "Bearer API key on api.hindsight.vectorize.io. Keys can be restricted to named banks and set to expire after an hour to a year, and revoking a parent key revokes its child keys. The hosted MCP uses OAuth with PKCE (RFC 9728), or the same key as a Bearer header. A self-hosted server exposes MCP at /mcp/{bank_id}/ on port 8888.", "pricing": "usage", "pricingNotes": "Hindsight Cloud is pay as you go, with no monthly fee or seat price. Retain $10.00 per million tokens, recall $0.75 per million, reflect $0.05 a call, Iris Extract $7.50 per million, mental model retrieval $0.25 per million, mental model refresh $0.05 a call, storage $0.25 per million tokens a month. New accounts get free credits, amount not stated. Enterprise adds dedicated infrastructure and up to a 99.95 per cent uptime SLA (https://vectorize.io/pricing). Credit is bought in amounts from $5 to $1,000, and calls return 402 once the balance is empty (https://docs.hindsight.vectorize.io/billing/). Self-hosting is free under MIT.", "priceSummary": "$0.05 / call", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": 27, "popularity": { "githubStars": 43400, "npmWeekly": 44381, "pypiWeekly": 227251, "asOf": "2026-09-30" }, "docsUrl": "https://docs.hindsight.vectorize.io", "openapi": "https://hindsight.vectorize.io/openapi.json", "capabilities": [ "memory.store", "memory.search", "memory.delete" ], "tags": [ "hosted", "usage-priced", "mcp", "oauth", "openapi", "python", "typescript", "open-source", "self-hosted", "enterprise" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 50.2, "grade": "D", "agentReady": false, "rank": 690, "ranked": true, "rankOf": 842, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 80, "payments": 30, "reliability": 25, "schema": 68, "security": 58, "transparency": 45 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "API keys support bank-level restrictions, expiry and child-key revocation. Retain ingestion costs $10 per million tokens.", "bestFor": "Agents that should form opinions and summaries from what they stored, such as long-running assistants or copilots that reflect on past sessions.", "strengths": [ "Keys restricted to named banks, with expiry from an hour to a year and child-key revocation", "`Memory Defense` screens every retain, with regex redaction even in the open-source server", "Published per-token and per-call Cloud prices, with no monthly fee, and a published 99.9 per cent SLA", "MIT server in one Docker image with an MCP endpoint per bank", "Eight PyPI releases between 22 July and 29 September 2026" ], "weaknesses": [ "Retain at $10 per million tokens is the priciest ingestion in this category", "27 MCP tools per bank, with no subset or read-only option", "No status page, no published rate limits and no llms.txt", "Prompt-injection blocking and audit trails are Enterprise only", "Free credit amount not published" ], "agentNotes": [ "Scope the MCP URL to one bank (/mcp/{bank}/) so every call lands in the right memory and three bank-admin tools drop out", "Use recall for lookups and keep reflect ($0.05 a call) for questions that need reasoning", "Pass `async: true` on large retains so the call returns before extraction finishes", "Treat HTTP 402 as out of credit and 403 as a key that can't reach that bank" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.2 } ], "editorialScores": { "ergonomics": 57, "maintenance": 80, "payments": 30, "reliability": 25, "schema": 68, "security": 58, "transparency": 30 }, "provenanceScore": 59 }, "connect": { "install": "pip install hindsight-client # or: npm install @vectorize-io/hindsight-client", "http": "curl -s \"https://api.hindsight.vectorize.io/v1/default/banks/my-bank/memories/list\" -H \"Authorization: Bearer $HINDSIGHT_API_KEY\"", "claudeCode": "claude mcp add --transport http hindsight https://api.hindsight.vectorize.io/mcp/my-bank/", "config": { "mcpServers": { "hindsight": { "headers": { "Authorization": "Bearer ${HINDSIGHT_API_KEY}" }, "type": "http", "url": "https://api.hindsight.vectorize.io/mcp/my-bank/" } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/hindsight" }, "area": "agent-runtime", "unitPrices": [ { "item": "Retain", "unit": "1m-tokens", "usd": 10, "note": "input tokens" }, { "item": "Recall", "unit": "1m-tokens", "usd": 0.75, "note": "output tokens" }, { "item": "Reflect", "unit": "call", "usd": 0.05 }, { "item": "Iris Extract", "unit": "1m-tokens", "usd": 7.5 }, { "item": "Mental model refresh", "unit": "call", "usd": 0.05 }, { "item": "Storage", "unit": "1m-tokens", "usd": 0.25, "note": "per million tokens stored, per month" } ], "provenance": { "legalEntity": "Vectorize, Inc.", "domain": "vectorize.io", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://vectorize.io/terms", "privacy": "https://vectorize.io/privacy", "statusPage": "", "changelog": "https://docs.hindsight.vectorize.io/whats-new", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The entity name comes from the copyright line on vectorize.io. The privacy policy is embedded from Termly and gives no address.", "vectorize.io/.well-known/security.txt returns 404, and we found no status page." ], "score": 59 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hindsight.json", "live": { "slug": "hindsight", "probe": { "target": "https://api.hindsight.vectorize.io", "method": "get", "lastAt": "2026-10-09T10:14:16.666133116Z", "lastOk": true, "lastStatus": 404, "lastMs": 131, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 134, "p95ms24h": 416, "samples24h": 260, "samples30d": 2093, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 109, "ok": 109 } ] }, "versions": [ { "registry": "github", "name": "vectorize-io/hindsight", "version": "v0.10.3", "released": "2026-10-08", "seenAt": "2026-10-08T16:15:48.589909202Z" }, { "registry": "npm", "name": "@vectorize-io/hindsight-client", "version": "0.10.3", "seenAt": "2026-10-08T16:15:46.042936004Z" }, { "registry": "pypi", "name": "hindsight-api", "version": "0.10.3", "released": "2026-10-08", "seenAt": "2026-10-08T16:15:48.571604141Z" }, { "registry": "pypi", "name": "hindsight-client", "version": "0.10.3", "released": "2026-10-08", "seenAt": "2026-10-08T16:15:45.905673909Z" } ], "githubStars": 47181, "npmWeekly": 68722, "pypiWeekly": 225106, "securityTxt": { "url": "https://vectorize.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:36.04417906Z" }, "domain": { "domain": "vectorize.io", "checkedAt": "2026-10-04T13:05:24.522601574Z" }, "pages": [ { "url": "https://docs.hindsight.vectorize.io/whats-new", "kind": "changelog", "status": 304, "checkedAt": "2026-10-08T18:18:50.829567638Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4b4e1a42fe21" }, { "url": "https://vectorize.io/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-08T18:25:34.352322054Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8914c2c291ed" }, { "url": "https://vectorize.io/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-08T18:25:36.508597709Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0b650c200752" }, { "url": "https://vectorize.io/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-08T18:25:38.513182813Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e508ab007e9c" } ], "updatedAt": "2026-10-09T10:14:16.666133116Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Amazon Web Services", "b": "Vectorize", "name": "Vendor" }, { "a": "https://bedrock-agentcore.{region}.amazonaws.com", "b": "https://api.hindsight.vectorize.io", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "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", "name": "Licence" }, { "a": "21", "b": "27", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-06", "b": "2026-09-29", "name": "Last release" }, { "a": "2026-10-01", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-05-18", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "776 stars, 1.1M npm/wk", "b": "43k stars, 44k npm/wk, 227k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Hindsight's 50.2 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Amazon Bedrock AgentCore Memory or Hindsight?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Amazon Bedrock AgentCore Memory and Hindsight need an API key?" }, { "answer": "Yes. Amazon Bedrock AgentCore Memory has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com and Hindsight at https://api.hindsight.vectorize.io.", "question": "Can an agent call Amazon Bedrock AgentCore Memory and Hindsight without installing anything?" }, { "answer": "No open-source release is listed for Amazon Bedrock AgentCore Memory. Hindsight is open source (MIT).", "question": "Are Amazon Bedrock AgentCore Memory and Hindsight open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 88 against 25", "Schema \u0026 documentation, 92 against 68", "Agent ergonomics, 86 against 57", "Security \u0026 auth, 87 against 58", "Transparency \u0026 trust, 76 against 45" ], "also": [ "Agent-ready, a grade of BB or better", "Runs on your own machine" ], "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": null, "also": [ "Open source" ], "goodFor": "Agents that should form opinions and summaries from what they stored, such as long-running assistants or copilots that reflect on past sessions.", "slug": "hindsight", "watchFor": "Retain at $10 per million tokens is the priciest ingestion in this category" } ], "job": { "capability": "memory.store", "name": "Memory store" }, "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-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-hindsight.json", "title": "Cognee vs Hindsight", "url": "https://www.anchorterminal.com/compare/cognee-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-hindsight.json", "title": "Graphiti vs Hindsight", "url": "https://www.anchorterminal.com/compare/graphiti-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-honcho.json", "title": "Hindsight vs Honcho", "url": "https://www.anchorterminal.com/compare/hindsight-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-langmem.json", "title": "Hindsight vs LangMem", "url": "https://www.anchorterminal.com/compare/hindsight-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-localghost.json", "title": "Hindsight vs LocalGhost", "url": "https://www.anchorterminal.com/compare/hindsight-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-mem0.json", "title": "Hindsight vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/hindsight-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-supermemory.json", "title": "Hindsight vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/hindsight-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-zep.json", "title": "Hindsight vs Zep", "url": "https://www.anchorterminal.com/compare/hindsight-vs-zep" } ], "scores": [ { "agentcore-memory": 88, "by": 63, "edge": "agentcore-memory", "hindsight": 25, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agentcore-memory": 92, "by": 24, "edge": "agentcore-memory", "hindsight": 68, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "agentcore-memory": 86, "by": 29, "edge": "agentcore-memory", "hindsight": 57, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "agentcore-memory": 87, "by": 29, "edge": "agentcore-memory", "hindsight": 58, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "agentcore-memory": 30, "by": 0, "edge": "", "hindsight": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agentcore-memory": 83, "by": 3, "edge": "agentcore-memory", "hindsight": 80, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "agentcore-memory": 76, "by": 31, "edge": "agentcore-memory", "hindsight": 45, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Hindsight's 50.2 (D), and leads in 6 of 7 scored categories. Both do memory store.", "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.", "hindsight": "API keys support bank-level restrictions, expiry and child-key revocation. Retain ingestion costs $10 per million tokens." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight", "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.md", "slim": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.min.md" }, "markdown": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Hindsight's 50.2 (D), and leads in 6 of 7 scored categories. Both do memory store.\n\n- Amazon Bedrock AgentCore Memory: grade A, 79.4/100, rank #12 of 842. Markdown https://www.anchorterminal.com/tools/agentcore-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/agentcore-memory.json\n- Hindsight: grade D, 50.2/100, rank #690 of 842. Markdown https://www.anchorterminal.com/tools/hindsight.md · JSON https://www.anchorterminal.com/api/v1/tools/hindsight.json\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 25\n- Schema \u0026 documentation, 92 against 68\n- Agent ergonomics, 86 against 57\n- Security \u0026 auth, 87 against 58\n- Transparency \u0026 trust, 76 against 45\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Runs on your own machine\n\nWatch for: Long-term extraction is asynchronous. The docs say records appear within seconds to minutes after a write\n\n### Hindsight (D)\n\nGood for: Agents that should form opinions and summaries from what they stored, such as long-running assistants or copilots that reflect on past sessions.\n\nAlso in its favour:\n- Open source\n\nWatch for: Retain at $10 per million tokens is the priciest ingestion in this category\n\n\n## Score by category\n\n| Category | Weight | Amazon Bedrock AgentCore Memory | Hindsight | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 88 | 25 | Amazon Bedrock AgentCore Memory +63 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 92 | 68 | Amazon Bedrock AgentCore Memory +24 |\n| Agent ergonomics | 13% (16.2 this run) | 86 | 57 | Amazon Bedrock AgentCore Memory +29 |\n| Security \u0026 auth | 14% (17.5 this run) | 87 | 58 | Amazon Bedrock AgentCore Memory +29 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 80 | Amazon Bedrock AgentCore Memory +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 76 | 45 | Amazon Bedrock AgentCore Memory +31 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **79.4 · A** | **50.2 · D** | |\n\n## Facts side by side\n\n| Fact | Amazon Bedrock AgentCore Memory | Hindsight |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Amazon Web Services | Vectorize |\n| Hosted endpoint | `https://bedrock-agentcore.{region}.amazonaws.com` | `https://api.hindsight.vectorize.io` |\n| Transports | HTTP, stdio | HTTP, Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Pay per use | Pay per use |\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 |\n| Tools exposed | 21 | 27 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-06 | 2026-09-29 |\n| Terms last updated | 2026-10-01 | couldn't be read |\n| Privacy policy last updated | 2026-05-18 | couldn't be read |\n| Customer content may train models | yes, with an opt-out | couldn't be read |\n| Terms restrict automated access | yes | couldn't be read |\n| Terms restrict benchmarking | yes | couldn't be read |\n| Terms or service can change without notice | yes | couldn't be read |\n| Arbitration or class-action waiver | not found in the text | couldn't be read |\n| Popularity | 776 stars, 1.1M npm/wk | 43k stars, 44k npm/wk, 227k PyPI/wk |\n| Agent reviews | none | 3/5 (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**Hindsight.** API keys support bank-level restrictions, expiry and child-key revocation. Retain ingestion costs $10 per million tokens.\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### Hindsight\n\n1. Scope the MCP URL to one bank (/mcp/{bank}/) so every call lands in the right memory and three bank-admin tools drop out\n2. Use recall for lookups and keep reflect ($0.05 a call) for questions that need reasoning\n3. Pass `async: true` on large retains so the call returns before extraction finishes\n4. Treat HTTP 402 as out of credit and 403 as a key that can't reach that bank\n\n## Questions\n\n### Which is better for AI agents, Amazon Bedrock AgentCore Memory or Hindsight?\n\nAmazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Hindsight's 50.2 (D), and leads in 6 of 7 scored categories.\n\n### Do Amazon Bedrock AgentCore Memory and Hindsight need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Amazon Bedrock AgentCore Memory and Hindsight without installing anything?\n\nYes. Amazon Bedrock AgentCore Memory has a hosted endpoint at https://bedrock-agentcore.{region}.amazonaws.com and Hindsight at https://api.hindsight.vectorize.io.\n\n### Are Amazon Bedrock AgentCore Memory and Hindsight open source?\n\nNo open-source release is listed for Amazon Bedrock AgentCore Memory. Hindsight is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agentcore-memory\", \"b\": \"hindsight\"}`. From a terminal: `anchor compare agentcore-memory hindsight`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agentcore-memory.json and https://www.anchorterminal.com/api/v1/tools/hindsight.json\n\n## Other comparisons with Amazon Bedrock AgentCore Memory or Hindsight\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 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 Hindsight](https://www.anchorterminal.com/compare/cognee-vs-hindsight.md)\n- [Graphiti vs Hindsight](https://www.anchorterminal.com/compare/graphiti-vs-hindsight.md)\n- [Hindsight vs Honcho](https://www.anchorterminal.com/compare/hindsight-vs-honcho.md)\n- [Hindsight vs LangMem](https://www.anchorterminal.com/compare/hindsight-vs-langmem.md)\n- [Hindsight vs LocalGhost](https://www.anchorterminal.com/compare/hindsight-vs-localghost.md)\n- [Hindsight vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/hindsight-vs-mem0.md)\n- [Hindsight vs Supermemory API + MCP](https://www.anchorterminal.com/compare/hindsight-vs-supermemory.md)\n- [Hindsight vs Zep](https://www.anchorterminal.com/compare/hindsight-vs-zep.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "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 Hindsight", "url": "" } ], "description": "Amazon Bedrock AgentCore Memory scores 79.4 (A) on agent readiness against Hindsight's 50.2 (D), and leads in 6 of 7 scored categories. Both do memory store. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Amazon Bedrock AgentCore Memory A 79.4", "Hindsight D 50.2", "scores" ], "h1": "Amazon Bedrock AgentCore Memory vs Hindsight", "image": "https://www.anchorterminal.com/assets/og/compare-agentcore-memory-vs-hindsight.png", "path": "/compare/agentcore-memory-vs-hindsight", "published": "2026-10-01", "section": "tools", "title": "Amazon Bedrock AgentCore Memory vs Hindsight for AI agents", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight" }, "tokens": { "markdown": 2300, "slim": 730 }, "version": 1 }