{ "data": { "a": { "slug": "google-memory-bank", "name": "Agent Platform Memory Bank", "vendor": "Google Cloud", "vendorUrl": "https://cloud.google.com/products/gemini-enterprise-agent-platform", "kind": "http-api", "category": "agent-memory", "summary": "Agent Platform Memory Bank, formerly Vertex AI Agent Engine Memory Bank, is Google Cloud's managed long-term memory for agents. It generates, stores and retrieves user-scoped memories through the Agent Platform API, Python SDK and ADK.", "url": "https://www.anchorterminal.com/tools/google-memory-bank", "markdownUrl": "https://www.anchorterminal.com/tools/google-memory-bank.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/google-memory-bank.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/google-memory-bank.json", "dns": "google-memory-bank.grade.anchorterminal.com", "transports": [ "http" ], "remoteUrl": "https://aiplatform.googleapis.com/v1", "packages": [ { "registry": "pypi", "name": "google-cloud-agentplatform" }, { "registry": "pypi", "name": "google-adk" } ], "auth": "oauth", "authNotes": "OAuth 2.0 bearer tokens from a service account or gcloud on a Google Cloud project with billing and the API enabled. IAM roles and IAM Conditions control access to Memory Bank, down to memory scope per the IAM conditions guide.", "pricing": "usage", "pricingNotes": "Billed since 1 September 2026 at $0.30 per GiB-month of storage including revisions, and one Agent Compute vCPU-hour ($0.085) per 3 million reads or 1 million writes. Model tokens for generation and embeddings are billed under their model SKUs. No Memory Bank free tier found.", "priceSummary": "$0.0001 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the aiplatform API or in the Memory Bank docs and pricing (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/memory-bank", "openapi": "https://aiplatform.googleapis.com/$discovery/rest?version=v1", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "hosted", "usage-priced", "closed-source", "card-required", "enterprise", "python", "async-jobs", "google-cloud" ], "lastRelease": "2026-08-20", "graded": true, "anchor": { "graded": true, "score": 65.6, "grade": "B", "agentReady": false, "rank": 412, "ranked": true, "rankOf": 1486, "categoryRank": 7, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 62, "payments": 20, "reliability": 68, "schema": 75, "security": 72, "transparency": 81 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Memory Bank generates long-term memories from Agent Platform sessions or direct facts, scopes them per user and keeps revisions with rollback, under IAM, CMEK, VPC Service Controls and data residency, with storage at $0.30 per GiB-month. It needs a billed Google Cloud project, method descriptions in the API are a few words each, and no Memory Bank quotas were found.", "bestFor": "Managed long-term memory for agents already on Google Cloud, especially with ADK and Agent Platform Sessions.", "strengths": [ "Memories are scoped by fields such as user_id, retrieved by similarity search and kept with an immutable revision history that can be rolled back", "IngestEvents (GA on 20 August 2026) streams events and triggers generation by volume or time", "IAM Conditions, CMEK, VPC Service Controls, data residency at rest, HIPAA and Access Transparency are listed as supported", "Usage prices are published, $0.30 per GiB-month stored and $0.085 per 3 million reads or 1 million writes, plus model tokens", "Google Cloud's status dashboard shows no incident naming the platform in the 90 days to 6 November 2026" ], "weaknesses": [ "Needs a Google Cloud project with billing, set up by a person in the console", "Method descriptions in the discovery document are 13 to 39 characters long", "No Memory Bank quotas or rate limits were found in the pages read", "Generation runs an LLM over conversations, with no prompt-injection guidance found", "Renamed from Vertex AI Agent Engine Memory Bank on 22 April 2026, so docs, SDKs and the REST paths (`reasoningEngines`, `memoryBanks`) use different names" ], "agentNotes": [ "Run `memories.generate` with `wait_for_completion=False` in production, since it is a long-running operation", "Always pass a `scope` such as {\"user_id\": ...} so one user's memories never reach another", "Send the OAuth token in the Authorization header, never as `access_token` in the URL", "Expect a 404 when fetching a deleted memory and treat it as gone", "Treat retrieved memories as untrusted text extracted from earlier conversations" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.6 } ], "editorialScores": { "ergonomics": 75, "maintenance": 62, "payments": 20, "reliability": 68, "schema": 75, "security": 72, "transparency": 65 }, "provenanceScore": 97, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install google-cloud-agentplatform" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/google-memory-bank" }, "sameCompany": [ "gemini-api", "vertex-ai", "gemini-embedding", "vertex-ai-tuning", "cloud-run-gpus", "google-model-armor", "google-imagen", "google-veo", "google-lyria", "google-speech-to-text", "google-cloud-tts", "gemini-live", "google-adk", "google-secret-manager", "google-cloud-document-ai", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-cloud-storage", "google-drive-api", "gemini-enterprise", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api", "google-people-api" ], "area": "agent-runtime", "unitPrices": [ { "item": "Memory storage including revisions", "unit": "gb-month", "usd": 0.3, "note": "Billed as Agent Storage since 1 September 2026" }, { "item": "Memory writes", "unit": "1k-requests", "usd": 0.000085, "note": "$0.085 per 1 million writes; reads are $0.085 per 3 million" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "domainNote": "The endpoint is on googleapis.com, Google's API domain.", "endpointOnVendorDomain": true, "terms": "https://cloud.google.com/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://status.cloud.google.com", "changelog": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Entity, domain, terms, privacy policy and security.txt are those of the other Google Cloud listings (google-model-armor, vertex-ai-tuning), not looked up again.", "docs.cloud.google.com and cloud.google.com robots.txt allow the Memory Bank, release-notes and pricing paths read.", "The pricing page was read with curl because it is over 16 MB." ], "score": 97 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/google-memory-bank.json", "live": { "slug": "google-memory-bank", "probe": { "target": "https://aiplatform.googleapis.com/v1", "method": "get", "lastAt": "2026-11-07T18:20:27.725315811Z", "lastOk": true, "lastStatus": 404, "lastMs": 765, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 664, "p95ms24h": 752, "samples24h": 200, "samples30d": 200, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "versions": [ { "registry": "pypi", "name": "google-adk", "version": "2.13.0", "released": "2026-10-23", "seenAt": "2026-11-06T23:29:40.592483472Z" }, { "registry": "pypi", "name": "google-cloud-agentplatform", "version": "2.7.0", "released": "2026-10-28", "seenAt": "2026-11-06T23:29:40.399171204Z" } ], "pypiWeekly": 102081, "securityTxt": { "url": "https://google.com/.well-known/security.txt", "state": "valid", "expires": "2030-04-01T00:00:00z", "checkedAt": "2026-11-07T16:01:22.068349931Z" }, "pages": [ { "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:05:40.442097724Z", "changedAt": "2026-11-07T14:05:40.442097724Z", "fingerprint": "5aae3bc64910" } ], "updatedAt": "2026-11-07T18:20:27.725315811Z" } }, "answer": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments \u0026 pricing and maintenance \u0026 community.", "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", "dns": "memory-reference-server.grade.anchorterminal.com", "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": "2026-10-28", "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": 58.8, "grade": "C", "agentReady": false, "rank": 724, "ranked": true, "rankOf": 1486, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 75, "payments": 60, "reliability": 75, "schema": 70, "security": 39, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -6, "negativeNotes": [ "-3, a released fix of the server's own described flaw with no advisory. 1.0.0 (tag v1.0.0, 10 October 2026) fixed #4827, where the atomic save added in 2026.8.31 replaced a memory file 'the operator narrowed with chmod 600' with one at 0644, and the temporary file was 'briefly readable at 0644' (1b01ea6d, 819ae904, 463c402f). The changelog calls it keeping the file's permission bits and no GHSA id is cited. https://github.com/modelcontextprotocol/servers/blob/main/src/memory/CHANGELOG.md", "-3, published behaviour changed for existing clients with word only on release day. 1.0.0 (10 October 2026) makes a write to a read-only memory file fail with EACCES where 2026.8.31 replaced the file, and fails a write that can't take the new lock file within 60 seconds; 2.0.1 (tag v2.2.0, 28 October 2026) stops startup when the memory.json migration fails, where earlier versions started on an empty graph. Each was described only in that release's changelog. One folded term. https://github.com/modelcontextprotocol/servers/blob/main/src/memory/CHANGELOG.md" ], "verdict": "Nine tools with typed schemas and accurate read, destructive and idempotent annotations, and since 1.0.0 a lock file keeps two processes from losing each other's writes. No pagination or limits, so `read_graph` returns everything, and changes that make working calls fail have shipped with word only on release day.", "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", "Atomic writes, a per-process write queue and a cross-process lock file since 1.0.0", "Semver releases with a per-package changelog since 1.0.0, four releases since 6 August", "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", "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 with no guidance on untrusted content", "1.0.0 and 2.0.1 changed behaviour that made working calls fail, told only in the release's changelog" ], "agentNotes": [ "Set `MEMORY_FILE_PATH` to an absolute path in a writable directory. The default sits inside the npx cache, and the lock file needs the directory", "Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph holds a few hundred entities or more", "Read `skipped` in the `create_entities` result and use `add_observations` for names that already exist", "Create both entities before `create_relations`. A missing endpoint fails the whole batch", "Run on Node 24 or later since 2.0.0, and 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": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.8 } ], "editorialScores": { "ergonomics": 67, "maintenance": 75, "payments": 60, "reliability": 75, "schema": 70, "security": 39, "transparency": 78 }, "provenanceScore": 74, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "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": 74 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/memory-reference-server.json", "live": { "slug": "memory-reference-server", "versions": [ { "registry": "github", "name": "modelcontextprotocol/servers", "version": "v2.3.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:44:03.926181669Z" }, { "registry": "npm", "name": "@modelcontextprotocol/server-memory", "version": "2.1.0", "seenAt": "2026-11-06T23:44:03.713410969Z" } ], "githubStars": 91839, "npmWeekly": 297358, "securityTxt": { "url": "https://modelcontextprotocol.io/.well-known/security.txt", "state": "valid", "checkedAt": "2026-11-07T16:01:43.564896778Z" }, "domain": { "domain": "modelcontextprotocol.io", "checkedAt": "2026-11-01T14:07:30.038395054Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/modelcontextprotocol/servers/main/src/memory/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:21:57.904273443Z", "changedAt": "2026-11-05T13:06:00.440607386Z", "fingerprint": "7e1bf59fb9b7" } ], "github": { "repo": "modelcontextprotocol/servers", "checkedAt": "2026-11-02T09:08:15.395430974Z", "stars": 91747, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-29T05:27:40Z", "openIssues": 30, "openPRs": 8, "issuesOpened90d": 289, "issuesClosed90d": 487, "prsMerged90d": 276, "ci": { "branch": "main", "runs": 50, "success": 44, "failure": 0, "other": 6, "latest": "success", "latestAt": "2026-10-28T20:46:50Z" }, "advisories": [ { "ghsa": "GHSA-w766-5x43-whvw", "severity": "medium", "published": "2026-10-28T21:13:40Z" }, { "ghsa": "GHSA-mvf5-2qqv-rg3c", "severity": "medium", "published": "2026-10-25T00:19:52Z" }, { "ghsa": "GHSA-hhwq-wxfx-cj7g", "severity": "low", "published": "2026-10-25T00:19:37Z" }, { "ghsa": "GHSA-53mr-w429-c597", "severity": "low", "published": "2026-10-25T00:19:21Z" }, { "ghsa": "GHSA-v38p-wf49-hx2j", "severity": "medium", "published": "2026-10-25T00:19:06Z" }, { "ghsa": "GHSA-66qx-2266-pmj6", "severity": "low", "published": "2026-10-25T00:18:52Z" }, { "ghsa": "GHSA-7rgq-gccq-qphx", "severity": "medium", "published": "2026-10-25T00:18:38Z" }, { "ghsa": "GHSA-4gxg-m5jx-9j57", "severity": "medium", "published": "2026-10-25T00:18:21Z" }, { "ghsa": "GHSA-3jqg-r5pp-rmp2", "severity": "low", "published": "2026-10-25T00:15:37Z" }, { "ghsa": "GHSA-vjqx-cfc4-9h6v", "cve": "CVE-2026-27735", "severity": "medium", "published": "2026-02-25T23:21:57Z" }, { "ghsa": "GHSA-j22h-9j4x-23w5", "cve": "CVE-2025-68145", "severity": "medium", "published": "2025-12-17T16:04:43Z" }, { "ghsa": "GHSA-9xwc-hfwc-8w59", "cve": "CVE-2025-68144", "severity": "medium", "published": "2025-12-17T16:01:56Z" }, { "ghsa": "GHSA-5cgr-j3jf-jw3v", "cve": "CVE-2025-68143", "severity": "medium", "published": "2025-12-17T15:55:26Z" }, { "ghsa": "GHSA-hc55-p739-j48w", "cve": "CVE-2025-53110", "severity": "high", "published": "2025-07-01T18:39:04Z" }, { "ghsa": "GHSA-q66q-fx2p-7w4m", "cve": "CVE-2025-53109", "severity": "high", "published": "2025-07-01T18:38:24Z" } ], "replies": { "sampled": 25, "unanswered": 8, "medianDays": 0.5 } }, "updatedAt": "2026-11-07T16:01:43.564896778Z" } }, "edges": [ { "by": 40, "category": "payments", "leads": "memory-reference-server", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Storage, read and write prices are published without a login (20). No Memory Bank free tier found (0). A person creates the project, enables billing and sets up IAM in the console (0). Total 20.", "b": "Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0)." }, "scores": { "a": 20, "b": 60 } }, { "by": 33, "category": "security", "leads": "google-memory-bank", "name": "Security \u0026 auth", "reasons": { "a": "OAuth 2.0 with IAM and service accounts (30), less 10, as for the other Google API listings, because the v1 discovery document lists `access_token`, `oauth_token` and `key` as query parameters (20 of 30). IAM Conditions can restrict access by memory scope; purge and delete have no confirmation (15 of 20). Memories are written by an LLM from conversation content and returned to agents, with no injection guidance found (5 of 15). Access Transparency and Access Approval are listed; Cloud Audit Logs coverage for Memory Bank wasn't read (12 of 15). Google's valid security.txt, vulnerability reward programme and certifications, with HIPAA listed for Memory Bank (20). Total 72.", "b": "No credentials, nothing to scope, so the middle band (20). No read-only mode. The three delete tools run without confirmation and annotations are the only signal a host gets. The file path is whatever `MEMORY_FILE_PATH` says (5). Everything stored comes back verbatim in later sessions, so an instruction an agent copied from a web page or document persists as memory. The README still has no guidance on this (2). No log of who changed what. Resource notifications say only that the graph changed (0). SECURITY.md was rewritten on 29 September 2026 and is on main since 1.0.0. It names this server in scope, takes private reports through GitHub, says fixes ship in the next release and publishes accepted advisories once a fixed release is out. modelcontextprotocol.io serves a security.txt with a contact and no Expires line. No bounty or certification. Graded as the sequential-thinking and filesystem servers and nanobot (12 of 20). OSV lists no advisory for the package on 4 November, and none of the GHSA-named branches merged in October touches this server. 20+5+2+0+12 = 39." }, "scores": { "a": 72, "b": 39 } }, { "by": 13, "category": "maintenance", "leads": "memory-reference-server", "name": "Maintenance \u0026 community", "reasons": { "a": "The newest Memory Bank release notes are of 20 August 2026 (IngestEvents GA, metadata, Gemini Embedding 2), 78 days before the check, and billing started on 1 September (20). Three Memory Bank entries in the 90 days, all on 20 August (10 of 20). Public release notes and Cloud Customer Care (12 of 15). `google-cloud-agentplatform` 2.7.0 on 28 October 2026, twelve releases in 90 days per its PyPI release feed, plus ADK (15). SDK test status not checked (5 of 10). Total 62.", "b": "Memory 2.0.1, released with the monorepo's v2.2.0 tag on 28 October 2026, 7 days before this check (30). Four releases of this package in the 90 days from 6 August, 2026.8.31 (31 August), 1.0.0 (tag v1.0.0, 10 October), 2.0.0 (tag v2.0.0, 19 October) and 2.0.1 (tag v2.2.0, 28 October), each with code changes; v2.1.0 (24 October) left it at 2.0.0 (package.json read at each tag). Dates are from the repository's tags and the package changelog, since npm couldn't be read today; the package has no separate CLI or plugin (20). Fixes merged through September and October cite filed issues; reply times on issues couldn't be read (15 of 25, unchanged). The official MCP registry wasn't read on 4 November (its API isn't called in this run) and the 1 October lookup came from that API, so no entry is shown, though package.json carries the mcpName io.github.modelcontextprotocol/server-memory (0). Current SDK (`@modelcontextprotocol/server` ^2.3.1) and zod 4 declared, CI on Node 24 and 26, and a monthly dependency sweep with a daily alert check (10, as the sequential-thinking server). 30+20+15+0+10 = 75." }, "scores": { "a": 62, "b": 75 } }, { "by": 8, "category": "ergonomics", "leads": "google-memory-bank", "name": "Agent ergonomics", "reasons": { "a": "Retrieval takes a scope and similarity search with a result limit (20 of 25). List methods page with page tokens and filters (16 of 20). Google's standard error model with status codes (15 of 20). Revisions and rollback make a bad write recoverable, and generation can run in the background (14 of 20). Python SDK and ADK integration, with REST for other languages (10 of 15). Total 75.", "b": "Nine tools with short descriptions, but the entity and relation schemas repeat in every output schema, so tools/list runs to about 10,700 characters or roughly 2,700 tokens by the 1 October count, with a `$schema` line on each schema since 2.0.0 (22). No pagination, limit or field selection anywhere. `read_graph` returns the whole graph and `search_nodes` returns every substring match (5). Since 1.0.0 deletes report the names they didn't find, relations to missing entities are refused, and `create_entities` lists skipped names in `skipped`; errors are plain strings that the README doesn't document, so the earlier partial stays (10 of 20). All nine tools carry `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint`, the three deletes marked destructive, and since 2.0.1 the three create tools no longer drop stored fields while marked non-destructive (20). At most one required parameter per tool. Node only, plus Docker (10). 22+5+10+20+10 = 67." }, "scores": { "a": 75, "b": 67 } }, { "by": 7, "category": "reliability", "leads": "memory-reference-server", "name": "Reliability", "reasons": { "a": "Hosted lines. Google Cloud status dashboard with per-product history (20). Its incident feed, read on 6 November 2026, holds four incidents since 8 August (20 August, 27 products; 1 September, us-central1-b; 8 October, Cloud Storage; 20 October, europe-west2, 38 products), and none names Agent Platform, Vertex or Memory Bank (30). No Memory Bank quotas or rate limits were found; the platform quotas path guessed returned 404 (0, unchecked). Generation is a long-running operation with wait and cancel methods, and Google's retry guidance wasn't re-read for this API (8 of 15). No SLA for Memory Bank was found in the pages read (0, unchecked). Memory profiles, IngestEvents and multi-regional endpoints are GA (10). Total 68.", "b": "Scored as a local stdio package. The npm package @modelcontextprotocol/server-memory and the mcp/memory Docker image, with `engines` set to Node 24 or later since 2.0.0 and the README stating the same (20). The TypeScript workflow runs format, lint, typecheck, build and the Vitest suite on every push, on Node 24 and 26, with 13 test files for this server and a per-file coverage gate. Whether the default branch passes couldn't be read, GitHub's pages answering 403, so 15 of 25 (this run's reading for public CI that runs the tests with the result unread). The issue list wasn't readable. The eleven September fixes, the race in #4555 among them, shipped in 1.0.0 with fixes for #4797, #4827 and #4887, and 2.0.1 fixed #5058 and the failed-migration case (15 of 25). Since 1.0.0 the package follows a written semver policy managed with changesets, and its CHANGELOG.md lists 2.0.0's breaking changes under Major Changes (15). Version 2.0.1, but the repository README and SECURITY.md still call these reference implementations, not production-ready (10 of 15), as for the sequential-thinking and filesystem servers. 20+15+15+15+10 = 75." }, "scores": { "a": 68, "b": 75 } }, { "by": 5, "category": "schema", "leads": "google-memory-bank", "name": "Schema \u0026 documentation", "reasons": { "a": "Google's discovery document is a machine-readable contract for every memory method (25). No llms.txt or Markdown docs found (0). Method descriptions are 13 to 39 characters, one-line summaries, while the guides explain when to generate from sessions or from direct facts (12 of 20). Typed schemas with required fields in the discovery document (12 of 15). Python examples, a troubleshooting page and a documented 404 for deleted memories (11 of 15). v1 and v1beta1 and dated release notes (15). Total 75.", "b": "All nine tools take typed zod input schemas and declare output schemas, stated as JSON Schema 2020-12 since 2.0.0 (25). No llms.txt. The README is Markdown on GitHub with JSON examples (5). Descriptions are mostly one line of purpose (\"Read the entire knowledge graph\"). Since 1.0.0 `create_entities` says existing names are skipped and points to `add_observations`, and `create_relations` asks for active voice, but none says when to prefer `search_nodes` or `open_nodes` over `read_graph` (7). Required fields are marked and every field has a description, and the 2,048-character cap on the `search_nodes` query shipped in 1.0.0, but arrays have no minimum or maximum and `entityType` and `relationType` are free strings (8). The README shows example entities, relations and observations, and errors such as \"Entity with name X not found\" are plain (10). A per-package CHANGELOG.md with Major, Minor and Patch sections from 1.0.0, and dated release tags (15). 25+5+7+8+10+15 = 70." }, "scores": { "a": 75, "b": 70 } } ], "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Google Cloud", "b": "MCP project (reference servers)", "name": "Vendor" }, { "a": "https://aiplatform.googleapis.com/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "stdio", "name": "Transports" }, { "a": "OAuth", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "none", "b": "MIT and Apache-2.0", "name": "Licence" }, { "a": "none", "b": "9", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-08-20", "b": "2026-10-28", "name": "Last release" }, { "a": "2026-09-02", "b": "2021-09-08", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2023-03-15", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "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": "none", "b": "90k stars, 136k npm/wk", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Agent Platform Memory Bank or Memory (MCP reference server)?" }, { "answer": "Agent Platform Memory Bank uses an OAuth sign-in. Memory (MCP reference server) needs no key.", "question": "Do Agent Platform Memory Bank and Memory (MCP reference server) need an API key?" }, { "answer": "Agent Platform Memory Bank has a hosted endpoint at https://aiplatform.googleapis.com/v1. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Agent Platform Memory Bank and Memory (MCP reference server) without installing anything?" }, { "answer": "No open-source release is listed for Agent Platform Memory Bank. Memory (MCP reference server) is open source (MIT and Apache-2.0).", "question": "Are Agent Platform Memory Bank and Memory (MCP reference server) open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 75 against 70", "Agent ergonomics, 75 against 67", "Security \u0026 auth, 72 against 39", "Transparency \u0026 trust, 81 against 76" ], "also": [ "A hosted endpoint, with nothing to install", "No incidents deducted, where Memory (MCP reference server) loses 6 points for them" ], "goodFor": "Managed long-term memory for agents already on Google Cloud, especially with ADK and Agent Platform Sessions.", "slug": "google-memory-bank", "watchFor": "Needs a Google Cloud project with billing, set up by a person in the console" }, { "aheadOn": [ "Reliability, 75 against 68", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 75 against 62" ], "also": [ "No key needed to call it", "Runs on your own machine", "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" } ], "history": { "google-memory-bank": null, "memory-reference-server": [ { "causes": [ "security", "product", "event" ], "date": "2026-11-04", "delta": 4.4, "from": 54.4, "fromGrade": "C", "to": 58.8, "toGrade": "C" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 54.3, "fromGrade": "C", "to": 54.4, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 54.2, "fromGrade": "C", "to": 54.3, "toGrade": "C" } ] }, "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-google-memory-bank.json", "title": "Amazon Bedrock AgentCore Memory vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.json", "title": "Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-google-memory-bank.json", "title": "Basic Memory vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server.json", "title": "Basic Memory vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-google-memory-bank.json", "title": "claude-mem vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server.json", "title": "claude-mem vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank.json", "title": "Cognee vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank" }, { "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/everos-vs-google-memory-bank.json", "title": "EverOS vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.json", "title": "EverOS vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-graphicle.json", "title": "Agent Platform Memory Bank vs Graphicle", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-graphicle" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-graphiti.json", "title": "Agent Platform Memory Bank vs Graphiti", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-hindsight.json", "title": "Agent Platform Memory Bank vs Hindsight", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho.json", "title": "Agent Platform Memory Bank vs Honcho", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-hy-memory.json", "title": "Agent Platform Memory Bank vs Hy Memory", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-langmem.json", "title": "Agent Platform Memory Bank vs LangMem", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.json", "title": "Agent Platform Memory Bank vs LocalGhost", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-mem0.json", "title": "Agent Platform Memory Bank vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memmachine.json", "title": "Agent Platform Memory Bank vs MemMachine", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memori.json", "title": "Agent Platform Memory Bank vs Memori", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-mempalace.json", "title": "Agent Platform Memory Bank vs MemPalace", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-past-dev.json", "title": "Agent Platform Memory Bank vs past.dev", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-supermemory.json", "title": "Agent Platform Memory Bank vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory.json", "title": "Agent Platform Memory Bank vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-tokenrip.json", "title": "Agent Platform Memory Bank vs Tokenrip", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-zep.json", "title": "Agent Platform Memory Bank vs Zep", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-zep" }, { "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/hy-memory-vs-memory-reference-server.json", "title": "Hy Memory vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/hy-memory-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/memmachine-vs-memory-reference-server.json", "title": "MemMachine vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/memmachine-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-memory-reference-server.json", "title": "Memori vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/memori-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-mempalace.json", "title": "Memory (MCP reference server) vs MemPalace", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.json", "title": "Memory (MCP reference server) vs past.dev", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev" }, { "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-tencentdb-agent-memory.json", "title": "Memory (MCP reference server) vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip.json", "title": "Memory (MCP reference server) vs Tokenrip", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip" }, { "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" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank.json", "title": "AI Memory vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-google-memory-bank.json", "title": "Context Mode Engine vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/context-mode-vs-google-memory-bank" } ], "panel": null, "scores": [ { "by": 7, "edge": "memory-reference-server", "google-memory-bank": 68, "key": "reliability", "memory-reference-server": 75, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 5, "edge": "google-memory-bank", "google-memory-bank": 75, "key": "schema", "memory-reference-server": 70, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 8, "edge": "google-memory-bank", "google-memory-bank": 75, "key": "ergonomics", "memory-reference-server": 67, "name": "Agent ergonomics", "weight": 13 }, { "by": 33, "edge": "google-memory-bank", "google-memory-bank": 72, "key": "security", "memory-reference-server": 39, "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "edge": "memory-reference-server", "google-memory-bank": 20, "key": "payments", "memory-reference-server": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 13, "edge": "memory-reference-server", "google-memory-bank": 62, "key": "maintenance", "memory-reference-server": 75, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 5, "edge": "google-memory-bank", "google-memory-bank": 81, "key": "transparency", "memory-reference-server": 76, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments \u0026 pricing and maintenance \u0026 community. Both do agent memory.", "tasks": null, "tutorials": [], "verdicts": { "google-memory-bank": "Memory Bank generates long-term memories from Agent Platform sessions or direct facts, scopes them per user and keeps revisions with rollback, under IAM, CMEK, VPC Service Controls and data residency, with storage at $0.30 per GiB-month. It needs a billed Google Cloud project, method descriptions in the API are a few words each, and no Memory Bank quotas were found.", "memory-reference-server": "Nine tools with typed schemas and accurate read, destructive and idempotent annotations, and since 1.0.0 a lock file keeps two processes from losing each other's writes. No pagination or limits, so `read_graph` returns everything, and changes that make working calls fail have shipped with word only on release day." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server", "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.min.md" }, "markdown": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments \u0026 pricing and maintenance \u0026 community. Both do agent memory.\n\n- Agent Platform Memory Bank: grade B, 65.6/100, rank #412 of 1486. Markdown https://www.anchorterminal.com/tools/google-memory-bank.md · JSON https://www.anchorterminal.com/api/v1/tools/google-memory-bank.json\n- Memory (MCP reference server): grade C, 58.8/100, rank #724 of 1486. 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 353 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 97 databases comparisons: https://www.anchorterminal.com/compare/data/index.md\n\n## Which one, for what\n\n### Agent Platform Memory Bank (B)\n\nGood for: Managed long-term memory for agents already on Google Cloud, especially with ADK and Agent Platform Sessions.\n\nAhead on:\n- Schema \u0026 documentation, 75 against 70\n- Agent ergonomics, 75 against 67\n- Security \u0026 auth, 72 against 39\n- Transparency \u0026 trust, 81 against 76\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- No incidents deducted, where Memory (MCP reference server) loses 6 points for them\n\nWatch for: Needs a Google Cloud project with billing, set up by a person in the console\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- Reliability, 75 against 68\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 75 against 62\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- Open source\n\nWatch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Memory (MCP reference server) +40\n\n- Agent Platform Memory Bank (20): No x402, MPP or L402 (0). Storage, read and write prices are published without a login (20). No Memory Bank free tier found (0). A person creates the project, enables billing and sets up IAM in the console (0). Total 20.\n- Memory (MCP reference server) (60): Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0).\n\n### Security \u0026 auth: Agent Platform Memory Bank +33\n\n- Agent Platform Memory Bank (72): OAuth 2.0 with IAM and service accounts (30), less 10, as for the other Google API listings, because the v1 discovery document lists `access_token`, `oauth_token` and `key` as query parameters (20 of 30). IAM Conditions can restrict access by memory scope; purge and delete have no confirmation (15 of 20). Memories are written by an LLM from conversation content and returned to agents, with no injection guidance found (5 of 15). Access Transparency and Access Approval are listed; Cloud Audit Logs coverage for Memory Bank wasn't read (12 of 15). Google's valid security.txt, vulnerability reward programme and certifications, with HIPAA listed for Memory Bank (20). Total 72.\n- Memory (MCP reference server) (39): No credentials, nothing to scope, so the middle band (20). No read-only mode. The three delete tools run without confirmation and annotations are the only signal a host gets. The file path is whatever `MEMORY_FILE_PATH` says (5). Everything stored comes back verbatim in later sessions, so an instruction an agent copied from a web page or document persists as memory. The README still has no guidance on this (2). No log of who changed what. Resource notifications say only that the graph changed (0). SECURITY.md was rewritten on 29 September 2026 and is on main since 1.0.0. It names this server in scope, takes private reports through GitHub, says fixes ship in the next release and publishes accepted advisories once a fixed release is out. modelcontextprotocol.io serves a security.txt with a contact and no Expires line. No bounty or certification. Graded as the sequential-thinking and filesystem servers and nanobot (12 of 20). OSV lists no advisory for the package on 4 November, and none of the GHSA-named branches merged in October touches this server. 20+5+2+0+12 = 39.\n\n### Maintenance \u0026 community: Memory (MCP reference server) +13\n\n- Agent Platform Memory Bank (62): The newest Memory Bank release notes are of 20 August 2026 (IngestEvents GA, metadata, Gemini Embedding 2), 78 days before the check, and billing started on 1 September (20). Three Memory Bank entries in the 90 days, all on 20 August (10 of 20). Public release notes and Cloud Customer Care (12 of 15). `google-cloud-agentplatform` 2.7.0 on 28 October 2026, twelve releases in 90 days per its PyPI release feed, plus ADK (15). SDK test status not checked (5 of 10). Total 62.\n- Memory (MCP reference server) (75): Memory 2.0.1, released with the monorepo's v2.2.0 tag on 28 October 2026, 7 days before this check (30). Four releases of this package in the 90 days from 6 August, 2026.8.31 (31 August), 1.0.0 (tag v1.0.0, 10 October), 2.0.0 (tag v2.0.0, 19 October) and 2.0.1 (tag v2.2.0, 28 October), each with code changes; v2.1.0 (24 October) left it at 2.0.0 (package.json read at each tag). Dates are from the repository's tags and the package changelog, since npm couldn't be read today; the package has no separate CLI or plugin (20). Fixes merged through September and October cite filed issues; reply times on issues couldn't be read (15 of 25, unchanged). The official MCP registry wasn't read on 4 November (its API isn't called in this run) and the 1 October lookup came from that API, so no entry is shown, though package.json carries the mcpName io.github.modelcontextprotocol/server-memory (0). Current SDK (`@modelcontextprotocol/server` ^2.3.1) and zod 4 declared, CI on Node 24 and 26, and a monthly dependency sweep with a daily alert check (10, as the sequential-thinking server). 30+20+15+0+10 = 75.\n\n### Agent ergonomics: Agent Platform Memory Bank +8\n\n- Agent Platform Memory Bank (75): Retrieval takes a scope and similarity search with a result limit (20 of 25). List methods page with page tokens and filters (16 of 20). Google's standard error model with status codes (15 of 20). Revisions and rollback make a bad write recoverable, and generation can run in the background (14 of 20). Python SDK and ADK integration, with REST for other languages (10 of 15). Total 75.\n- Memory (MCP reference server) (67): Nine tools with short descriptions, but the entity and relation schemas repeat in every output schema, so tools/list runs to about 10,700 characters or roughly 2,700 tokens by the 1 October count, with a `$schema` line on each schema since 2.0.0 (22). No pagination, limit or field selection anywhere. `read_graph` returns the whole graph and `search_nodes` returns every substring match (5). Since 1.0.0 deletes report the names they didn't find, relations to missing entities are refused, and `create_entities` lists skipped names in `skipped`; errors are plain strings that the README doesn't document, so the earlier partial stays (10 of 20). All nine tools carry `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint`, the three deletes marked destructive, and since 2.0.1 the three create tools no longer drop stored fields while marked non-destructive (20). At most one required parameter per tool. Node only, plus Docker (10). 22+5+10+20+10 = 67.\n\n### Reliability: Memory (MCP reference server) +7\n\n- Agent Platform Memory Bank (68): Hosted lines. Google Cloud status dashboard with per-product history (20). Its incident feed, read on 6 November 2026, holds four incidents since 8 August (20 August, 27 products; 1 September, us-central1-b; 8 October, Cloud Storage; 20 October, europe-west2, 38 products), and none names Agent Platform, Vertex or Memory Bank (30). No Memory Bank quotas or rate limits were found; the platform quotas path guessed returned 404 (0, unchecked). Generation is a long-running operation with wait and cancel methods, and Google's retry guidance wasn't re-read for this API (8 of 15). No SLA for Memory Bank was found in the pages read (0, unchecked). Memory profiles, IngestEvents and multi-regional endpoints are GA (10). Total 68.\n- Memory (MCP reference server) (75): Scored as a local stdio package. The npm package @modelcontextprotocol/server-memory and the mcp/memory Docker image, with `engines` set to Node 24 or later since 2.0.0 and the README stating the same (20). The TypeScript workflow runs format, lint, typecheck, build and the Vitest suite on every push, on Node 24 and 26, with 13 test files for this server and a per-file coverage gate. Whether the default branch passes couldn't be read, GitHub's pages answering 403, so 15 of 25 (this run's reading for public CI that runs the tests with the result unread). The issue list wasn't readable. The eleven September fixes, the race in #4555 among them, shipped in 1.0.0 with fixes for #4797, #4827 and #4887, and 2.0.1 fixed #5058 and the failed-migration case (15 of 25). Since 1.0.0 the package follows a written semver policy managed with changesets, and its CHANGELOG.md lists 2.0.0's breaking changes under Major Changes (15). Version 2.0.1, but the repository README and SECURITY.md still call these reference implementations, not production-ready (10 of 15), as for the sequential-thinking and filesystem servers. 20+15+15+15+10 = 75.\n\n### Schema \u0026 documentation: Agent Platform Memory Bank +5\n\n- Agent Platform Memory Bank (75): Google's discovery document is a machine-readable contract for every memory method (25). No llms.txt or Markdown docs found (0). Method descriptions are 13 to 39 characters, one-line summaries, while the guides explain when to generate from sessions or from direct facts (12 of 20). Typed schemas with required fields in the discovery document (12 of 15). Python examples, a troubleshooting page and a documented 404 for deleted memories (11 of 15). v1 and v1beta1 and dated release notes (15). Total 75.\n- Memory (MCP reference server) (70): All nine tools take typed zod input schemas and declare output schemas, stated as JSON Schema 2020-12 since 2.0.0 (25). No llms.txt. The README is Markdown on GitHub with JSON examples (5). Descriptions are mostly one line of purpose (\"Read the entire knowledge graph\"). Since 1.0.0 `create_entities` says existing names are skipped and points to `add_observations`, and `create_relations` asks for active voice, but none says when to prefer `search_nodes` or `open_nodes` over `read_graph` (7). Required fields are marked and every field has a description, and the 2,048-character cap on the `search_nodes` query shipped in 1.0.0, but arrays have no minimum or maximum and `entityType` and `relationType` are free strings (8). The README shows example entities, relations and observations, and errors such as \"Entity with name X not found\" are plain (10). A per-package CHANGELOG.md with Major, Minor and Patch sections from 1.0.0, and dated release tags (15). 25+5+7+8+10+15 = 70.\n\n## Score by category\n\n| Category | Weight | Agent Platform Memory Bank | Memory (MCP reference server) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 68 | 75 | Memory (MCP reference server) +7 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 75 | 70 | Agent Platform Memory Bank +5 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 67 | Agent Platform Memory Bank +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 72 | 39 | Agent Platform Memory Bank +33 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | Memory (MCP reference server) +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 62 | 75 | Memory (MCP reference server) +13 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 81 | 76 | Agent Platform Memory Bank +5 |\n| Negative events | ≤15 | 0 | -6 | |\n| **Total** | | **65.6 · B** | **58.8 · C** | |\n\n## Facts side by side\n\n| Fact | Agent Platform Memory Bank | Memory (MCP reference server) |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Google Cloud | MCP project (reference servers) |\n| Hosted endpoint | `https://aiplatform.googleapis.com/v1` | no (local only) |\n| Transports | HTTP | stdio |\n| Auth | OAuth | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | none | MIT and Apache-2.0 |\n| Tools exposed | none | 9 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-08-20 | 2026-10-28 |\n| Terms last updated | 2026-09-02 | 2021-09-08 |\n| Privacy policy last updated | 2026-10-01 | 2023-03-15 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | none | 90k stars, 136k npm/wk |\n| Agent reviews | none | 2.5/5 (2) |\n\n## How the scores have moved\n\n### Agent Platform Memory Bank\n\nNo score change since it was listed.\n\n### Memory (MCP reference server)\n\n- +4.4 on 4 November 2026: security, product, negative event\n- +0.1 on 28 October 2026: new evidence\n- +0.1 on 27 October 2026: checklist\n\n## Verdicts\n\n**Agent Platform Memory Bank.** Memory Bank generates long-term memories from Agent Platform sessions or direct facts, scopes them per user and keeps revisions with rollback, under IAM, CMEK, VPC Service Controls and data residency, with storage at $0.30 per GiB-month. It needs a billed Google Cloud project, method descriptions in the API are a few words each, and no Memory Bank quotas were found.\n\n**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations, and since 1.0.0 a lock file keeps two processes from losing each other's writes. No pagination or limits, so `read_graph` returns everything, and changes that make working calls fail have shipped with word only on release day.\n\n## Before you call either\n\n### Agent Platform Memory Bank\n\n1. Run `memories.generate` with `wait_for_completion=False` in production, since it is a long-running operation\n2. Always pass a `scope` such as {\"user_id\": ...} so one user's memories never reach another\n3. Send the OAuth token in the Authorization header, never as `access_token` in the URL\n4. Expect a 404 when fetching a deleted memory and treat it as gone\n5. Treat retrieved memories as untrusted text extracted from earlier conversations\n\n### Memory (MCP reference server)\n\n1. Set `MEMORY_FILE_PATH` to an absolute path in a writable directory. The default sits inside the npx cache, and the lock file needs the directory\n2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph holds a few hundred entities or more\n3. Read `skipped` in the `create_entities` result and use `add_observations` for names that already exist\n4. Create both entities before `create_relations`. A missing endpoint fails the whole batch\n5. Run on Node 24 or later since 2.0.0, and keep observations short and factual. They come back verbatim in every later read\n\n## Questions\n\n### Which is better for AI agents, Agent Platform Memory Bank or Memory (MCP reference server)?\n\nAgent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments \u0026 pricing and maintenance \u0026 community.\n\n### Do Agent Platform Memory Bank and Memory (MCP reference server) need an API key?\n\nAgent Platform Memory Bank uses an OAuth sign-in. Memory (MCP reference server) needs no key.\n\n### Can an agent call Agent Platform Memory Bank and Memory (MCP reference server) without installing anything?\n\nAgent Platform Memory Bank has a hosted endpoint at https://aiplatform.googleapis.com/v1. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.\n\n### Are Agent Platform Memory Bank and Memory (MCP reference server) open source?\n\nNo open-source release is listed for Agent Platform Memory Bank. 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/google-memory-bank-vs-memory-reference-server.json, and with the fewest tokens: https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"google-memory-bank\", \"b\": \"memory-reference-server\"}`. From a terminal: `anchor compare google-memory-bank memory-reference-server`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/google-memory-bank.json and https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json\n\n## Other comparisons with Agent Platform Memory Bank or Memory (MCP reference server)\n\n- [Amazon Bedrock AgentCore Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/agentcore-memory-vs-google-memory-bank.md)\n- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)\n- [Basic Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/basic-memory-vs-google-memory-bank.md)\n- [Basic Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server.md)\n- [claude-mem vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/claude-mem-vs-google-memory-bank.md)\n- [claude-mem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server.md)\n- [Cognee vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank.md)\n- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)\n- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)\n- [EverOS vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.md)\n- [Agent Platform Memory Bank vs Graphicle](https://www.anchorterminal.com/compare/google-memory-bank-vs-graphicle.md)\n- [Agent Platform Memory Bank vs Graphiti](https://www.anchorterminal.com/compare/google-memory-bank-vs-graphiti.md)\n- [Agent Platform Memory Bank vs Hindsight](https://www.anchorterminal.com/compare/google-memory-bank-vs-hindsight.md)\n- [Agent Platform Memory Bank vs Honcho](https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho.md)\n- [Agent Platform Memory Bank vs Hy Memory](https://www.anchorterminal.com/compare/google-memory-bank-vs-hy-memory.md)\n- [Agent Platform Memory Bank vs LangMem](https://www.anchorterminal.com/compare/google-memory-bank-vs-langmem.md)\n- [Agent Platform Memory Bank vs LocalGhost](https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.md)\n- [Agent Platform Memory Bank vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/google-memory-bank-vs-mem0.md)\n- [Agent Platform Memory Bank vs MemMachine](https://www.anchorterminal.com/compare/google-memory-bank-vs-memmachine.md)\n- [Agent Platform Memory Bank vs Memori](https://www.anchorterminal.com/compare/google-memory-bank-vs-memori.md)\n- [Agent Platform Memory Bank vs MemPalace](https://www.anchorterminal.com/compare/google-memory-bank-vs-mempalace.md)\n- [Agent Platform Memory Bank vs past.dev](https://www.anchorterminal.com/compare/google-memory-bank-vs-past-dev.md)\n- [Agent Platform Memory Bank vs Supermemory API + MCP](https://www.anchorterminal.com/compare/google-memory-bank-vs-supermemory.md)\n- [Agent Platform Memory Bank vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory.md)\n- [Agent Platform Memory Bank vs Tokenrip](https://www.anchorterminal.com/compare/google-memory-bank-vs-tokenrip.md)\n- [Agent Platform Memory Bank vs Zep](https://www.anchorterminal.com/compare/google-memory-bank-vs-zep.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- [Hy Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hy-memory-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- [MemMachine vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/memmachine-vs-memory-reference-server.md)\n- [Memori vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/memori-vs-memory-reference-server.md)\n- [Memory (MCP reference server) vs MemPalace](https://www.anchorterminal.com/compare/memory-reference-server-vs-mempalace.md)\n- [Memory (MCP reference server) vs past.dev](https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.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 TencentDB Agent Memory](https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory.md)\n- [Memory (MCP reference server) vs Tokenrip](https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip.md)\n- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)\n- [AI Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank.md)\n- [Context Mode Engine vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/context-mode-vs-google-memory-bank.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)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Agent Platform Memory Bank vs Memory (MCP reference server)", "url": "" } ], "description": "Agent Platform Memory Bank scores 65.6 (B) to Memory's 58.8 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Agent Platform Memory Bank B 65.6", "Memory (MCP reference server) C 58.8", "scores" ], "h1": "Agent Platform Memory Bank vs Memory (MCP reference server)", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/google-memory-bank-vs-memory-reference-server", "published": "2026-10-01", "section": "tools", "title": "Agent Platform Memory Bank vs Memory for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server" }, "tokens": { "markdown": 5950, "slim": 2980 }, "version": 1 }