{ "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 LocalGhost's 55.7 (C), and leads in 5 of 7 scored categories. LocalGhost leads on payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "localghost", "name": "LocalGhost", "vendor": "LocalGhost", "vendorUrl": "https://www.localghost.ai", "kind": "platform", "category": "local-ai", "summary": "Open-source personal AI server that runs on a Debian machine its owner keeps, archiving photos, location, notes, voice and health data and reading them with local models, with its own Android app as the only client.", "url": "https://www.anchorterminal.com/tools/localghost", "markdownUrl": "https://www.anchorterminal.com/tools/localghost.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/localghost.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/localghost.json", "dns": "localghost.grade.anchorterminal.com", "repo": "https://github.com/LocalGhostDao/localghost", "license": "MIT", "transports": [ "http" ], "packages": [], "auth": "pat", "authNotes": "No credential for third-party agents. The companion app presents a client certificate issued by the box's own certificate authority (ECDSA P-256, no scopes, good for two weeks and renewed daily while the phone is in use since 0.0.6) and a session token of at most 48 hours from a PIN unlock, sent in a header. Enrolment is one animated QR code carrying a `localghost://enroll` link whose query string holds the device's certificate and private key. Since 2 October 2026 the box draws that QR only on an interactive terminal and never prints the link as text, and after the first unlock the phone swaps the QR's key for one it makes in the Android Keystore and the box retires the QR's certificate (https://github.com/LocalGhostDao/localghost/blob/main/server/internal/secd/rekey.go). A request without a valid certificate, from a retired phone or to a locked box gets the same 503. Since wisp 0.0.2 (2 October 2026) one phone can be retired by its key with ghost-cli ghost.secd retire or from another phone (POST /v1/devices/retire), and the retire button in the app isn't built yet. On a fresh box nginx terminates the phone's TLS and passes the device certificate to ghost.secd as an X-Client-Cert header that any local process on the box can forge, until the operator runs ghost-ctl edge-passthrough and writes tls to /etc/ghost/edge, after which ghost.secd checks the certificate itself (https://github.com/LocalGhostDao/localghost/blob/main/server/internal/secd/edge.go).", "pricing": "free", "pricingNotes": "The software is free under MIT, with no subscription and no account. Nothing is on sale yet. Pre-built boxes are planned as a one-time purchase at the cost of parts and assembly plus a 30% margin, price not set, and optional future daemons may be sold as one-time packages. The June 2026 reference build is about £1,130 in parts (https://www.localghost.ai/about).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No payments of any kind. The software is free and nothing is sold yet (checked 2026-10-02).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 16, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://github.com/LocalGhostDao/localghost/blob/main/server/tools/README.md", "llmsTxt": "https://www.localghost.ai/llms.txt", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "local", "self-hosted", "open-source", "free", "go", "llms-txt", "no-telemetry", "pre-1.0", "uk" ], "lastRelease": "2026-10-10", "graded": true, "own": true, "disclosure": "LocalGhost is built by Anchor Terminal's founder. Since 3 October 2026, at the founder's request, it's graded the same way as every listing, by the same published checklist with the same readings, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed. letme never picks it. Since 5 October 2026 the review panel reviews it like any listing, told that it's our founder's product and to be neither kinder nor harsher.", "anchor": { "graded": true, "score": 55.7, "grade": "C", "agentReady": false, "rank": 853, "ranked": true, "rankOf": 1486, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 39, "maintenance": 79, "payments": 60, "reliability": 67, "schema": 49, "security": 50, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": -2, "negativeNotes": [ "2026-10-02 to 2026-10-04. The 0.0.1 notes of 2 October said never a location leaves the box, and the 0.0.3 notes of 3 October called the Open-Meteo call the one position that ever left either device, while the phone sent its position, rounded to two decimals, to Open-Meteo for a weather question naming no place until 0.0.3, and handed its newest fix to Android's geocoder, which on phones with Google's services usually reaches Google, until 0.0.4. Both lookups are gone, and the privacy page and llms.txt list each with the release that ended it. A misleading claim, fixed and documented, so the minimum, -2. https://github.com/LocalGhostDao/localghost/blob/v0.0.4/server/releases/0.0.4.md; https://github.com/LocalGhostDao/localghost/blob/v0.0.3/server/releases/0.0.3.md; https://www.localghost.ai/privacy" ], "verdict": "LocalGhost keeps a person's photos, trail, notes, voice and health data on an encrypted volume on their own Debian machine and runs its models there, and its list of outbound requests matches the code. It's pre-1.0 at wisp 0.0.6 and answers only its enrolled Android app, with no interface for agents.", "bestFor": "One technical owner who wants a phone-first personal archive (photos, location trail, notes, voice, health, news and prices) kept and read by local models on their own hardware.", "disclosure": "LocalGhost is built by Anchor Terminal's founder. Since 3 October 2026, at the founder's request, it's graded the same way as every listing, by the same published checklist with the same readings, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed. letme never picks it. Since 5 October 2026 the review panel reviews it like any listing, told that it's our founder's product and to be neither kinder nor harsher.", "strengths": [ "MIT licence for the server and the Android app, with a reproducible server bundle, a signed APK and signed sums for each release", "The v0.0.6 sums verify against the site key, which security.txt, SECURITY.md and the repository pin by the same fingerprint", "The privacy page and llms.txt list every outbound request, and the hosts in the v0.0.6 code match the list", "No telemetry, analytics or crash reporting in the server or the app", "Volume key sealed to the TPM, a wipe PIN, and phone certificates that last two weeks, renew daily and can be retired one at a time" ], "weaknesses": [ "No API, MCP server or credential for agents. The box answers only its enrolled phone", "The repository's checksum command finds no file, because SHA256SUMS lists the bundle under `server/`. The setup page's version strips the prefix and works", "Every API error reaches the phone as the same 503 page, so a client can't tell a bad request from a locked box", "Device certificates carry no scopes, so every enrolled phone has full owner rights, and a fresh box trusts a forgeable local header until the operator runs the edge passthrough", "The README's list of outbound requests still describes the weather pull of 0.0.5, three thousand places once a day, where the code and the privacy page say about six thousand, a hundred every two minutes" ], "agentNotes": [ "Don't look for an API or MCP server. A LocalGhost box answers only its enrolled phone and returns the same 503 to every other caller", "Verify a release with the setup page's command, which strips the `server/` and `app/` prefixes from SHA256SUMS before `sha256sum -c`, or nothing is checked", "After setup, run `sudo ghost-ctl edge-passthrough --domain \u003cbox name\u003e` so ghost.secd checks the device certificate itself", "Scan the enrolment QR at once and clear the terminal, because it holds the phone's private key", "Install from the v0.0.6 release, which main pins" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 3, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.7 } ], "editorialScores": { "ergonomics": 39, "maintenance": 79, "payments": 60, "reliability": 67, "schema": 49, "security": 50, "transparency": 81 }, "provenanceScore": 74, "checked": { "categories": { "ergonomics": "2026-10-10", "maintenance": "2026-10-10", "payments": "2026-10-10", "reliability": "2026-10-10", "schema": "2026-10-10", "security": "2026-10-10", "transparency": "2026-10-10" }, "last": "2026-10-10", "lastMoved": "2026-10-28", "oldest": "2026-10-10", "stale": false, "staleAfterDays": 90 } }, "letme": { "capability": "https://letme.dev/memory.store" }, "alsoIn": [ "personal-assistants" ], "area": "models", "provenance": { "legalEntity": "LocalGhost.ai Ltd (company number 17213100, registered in England and Wales, incorporated 12 May 2026)", "domain": "localghost.ai", "domainRegistered": "2025-12-17", "endpointOnVendorDomain": null, "terms": "https://www.localghost.ai/terms", "privacy": "https://www.localghost.ai/privacy", "statusPage": "https://www.localghost.ai/status", "changelog": "https://www.localghost.ai/changelog", "securityTxt": "valid", "checked": "2026-10-06", "notes": [ "LocalGhost.ai Ltd is active at Companies House (company number 17213100, incorporated 12 May 2026, registered office in London, checked 6 October 2026) and is named on the about, privacy and terms pages. The `LICENSE` copyright line reads LocalGhostDao, which the terms page also names as the copyright holder.", "Self-hosted software with no hosted endpoint. The privacy page (updated 5 October 2026) and the terms page (updated 3 October 2026) cover the website, the mirror and the software. The status page, updated by hand and last on 2 October 2026, covers the website, the mirror and the releases and records no incidents.", "www.localghost.ai/.well-known/security.txt returned a valid RFC 9116 file on 6 October 2026 (Contact, Expires 2027-10-01, Encryption, Preferred-Languages, Canonical, Policy). The key is the repository's server/tools/mirror-key.asc, fingerprint DCE9 A3D1 4EB4 6197 1DD5 F393 706E 4194 F08A 09A0, and the v0.0.6 SHA256SUMS.asc verified against it on 10 October 2026.", "The changelog page has a dated entry for each release from 0.0.1 to 0.0.6 and for mirror and page changes. RELEASES.md and server/releases/ in the code repository hold the notes per release.", "The privacy and mirror pages say the website and mirror keep no access logs. Whether the live server runs that configuration wasn't checked. The domain's registration date (17 December 2025, through Cloudflare, per the .ai RDAP record) is per the 3 October check." ], "score": 74 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/localghost.json", "live": { "slug": "localghost", "vendorStatus": { "page": "https://www.localghost.ai/status", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:48:00.567459109Z" }, "versions": [ { "registry": "github", "name": "LocalGhostDao/localghost", "version": "v0.0.7", "released": "2026-10-23", "seenAt": "2026-11-06T23:41:17.291874611Z" } ], "githubStars": 17, "securityTxt": { "url": "https://localghost.ai/.well-known/security.txt", "state": "valid", "expires": "2027-10-01T00:00:00Z", "checkedAt": "2026-11-07T16:00:33.069535961Z" }, "llmsTxt": { "url": "https://www.localghost.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:54.374669014Z" }, "domain": { "domain": "localghost.ai", "registered": "2025-12-17", "source": "https://rdap.identitydigital.services/rdap/domain/localghost.ai", "checkedAt": "2026-11-01T14:12:26.676825255Z" }, "pages": [ { "url": "https://www.localghost.ai/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:30:58.87482191Z", "changedAt": "2026-10-24T02:33:35.056983095Z", "fingerprint": "061f5343580e" }, { "url": "https://www.localghost.ai/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:31:00.879528436Z", "changedAt": "2026-10-24T02:33:37.068759386Z", "fingerprint": "f857f5ee0ba1" }, { "url": "https://www.localghost.ai/terms", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:31:02.879194941Z", "changedAt": "2026-10-14T21:14:28.658360477Z", "fingerprint": "4808f470d93a" } ], "github": { "repo": "localghostdao/localghost", "checkedAt": "2026-11-02T09:01:32.909025665Z", "stars": 17, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-01T22:42:18Z", "openIssues": 0, "openPRs": 0, "issuesOpened90d": 0, "issuesClosed90d": 1, "prsMerged90d": 1, "ci": { "branch": "main", "runs": 50, "success": 26, "failure": 23, "other": 1, "latest": "failure", "latestAt": "2026-11-01T22:43:54Z" }, "replies": { "sampled": 1, "unanswered": 0, "medianDays": 66.1 } }, "updatedAt": "2026-11-07T16:00:33.069535961Z" }, "vendorLinked": true }, "edges": [ { "by": 40, "category": "payments", "leads": "localghost", "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": "Read with the self-hosted rule, as the Khoj dossier did. Nothing is on sale. Pre-built boxes are planned at the cost of parts plus a 30 per cent margin with no price set, and the README's Ethereum donation address isn't a payment protocol on the tool's endpoints (0). Free under MIT with no account and no card, so 20, 20 and 20 on the last three lines." }, "scores": { "a": 20, "b": 60 } }, { "by": 36, "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": "Graded on the device API, as Schema is. `/v1/news` takes `since` and `limit`, the rate routes take `hours` or `days` and the Wikipedia route takes `n`, while `/v1/home` and `/v1/rates` return whole screens and nothing selects fields (12 of 25). `/v1/days` pages with `before` and `limit`, and `/v1/wiki` searches with `q` (12 of 20). edge.go folds every 400, 401, 403, 404 and 5xx a verified phone could get into the same 503 page, and the nginx path does the same with error_page, so the handlers' messages never reach the client and it can't tell a bad request from a locked box. Only a few statuses such as 409 pass through (2 of 20). Voice uploads are idempotent by id, `/v1/lock` is safe to repeat and trail deletion has a dry run, with no idempotency keys or retry guidance (10 of 20). The project's own Kotlin app is the only client, with no SDK and no documented way to enrol another (3 of 15)." }, "scores": { "a": 75, "b": 39 } }, { "by": 26, "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": "Graded on the HTTPS API that ghost.secd serves to enrolled phones under /v1, the only programmatic interface, as the Khoj and Open WebUI dossiers graded their HTTP APIs. There's no public API or MCP server, and the README and llms.txt say the box answers every other caller, an agent included, as if it were down. ghost.secd builds an OpenAPI 3.0 document from a route table and serves it at /v1/openapi.json only to enrolled devices. At v0.0.6 the table holds 49 paths while server.go registers 109 by hand (46 and 105 at v0.0.5), although the code comment says no route can exist outside the spec (8 of 25). llms.txt on www.localghost.ai and Markdown docs throughout the repository (10). Route summaries say what each call does and some say when to use it, and there's no API reference beyond them (8 of 20). Request and response shapes come from Go structs by reflection, but several shapes are marked loose with additionalProperties, request bodies among them, and query formats sit in summaries and handlers rather than in the spec (6 of 15). No API examples, and error statuses are folded into one 503 page by design, so no error responses are documented (3 of 15). /v1 prefixes, dated notes per release in server/releases/ and a dated changelog page (14 of 15)." }, "scores": { "a": 75, "b": 49 } }, { "by": 22, "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": "Graded with the tool lines on how the phone reaches the box. Each phone holds a client certificate from the box's own CA (ECDSA P-256, no scopes) and a session token of at most 48 hours from a PIN unlock, sent in a header. Since 0.0.6 a certificate is good for two weeks and the phone renews it once a day while it talks to the box, re-signing the same key, and the QR's own certificate is good for an hour. One phone can be retired by its key since 0.0.2, and after the first unlock the phone swaps the QR's key for one it makes in the Android Keystore and the box retires the QR's certificate. That's 20 for revocable credentials with rotation and no scopes. The `localghost://enroll` link carries the device's certificate and private key in its query string, and we didn't take the 10 off. The Screenpipe dossier took it for a key documented as a `token` parameter on HTTP requests, and the Khoj dossier didn't for a key in a query string that wasn't a documented way to authenticate, so the line covers secrets in request URLs that pass through servers, proxies and logs. This link is drawn only as a QR on an interactive terminal and never printed as text (internal/pair/command.go), the app has no intent filter for the scheme and reads the QR with its own scanner, and the link never becomes a network request (20 of 30). Every enrolled phone has full owner rights, with no read-only device. Since 0.0.6 DEPLOY, ROLL BACK and LOCK BOX NOW ask for confirmation first and deleting a model, a notification, a connector or a chat takes a second tap, trail deletion has a dry run and a deploy runs on trial with automatic rollback, while the API's deletes run without a confirmation step (8 of 20). The box and phone pass news feeds, web search results, coin websites and Wikipedia text to the model, and we found no injection guidance. The daemons own the control flow, the model calls no tools, and some writers drop text carrying names or numbers not in their facts (6 of 15). Requests are logged at debug level only, and `ghost-cli ghost.secd devices` and Box Status show the enrolled phones and the daemons, with no per-call audit trail (5 of 15). security.txt valid to 1 October 2027, SECURITY.md with a 72-hour acknowledgement, a 14-day response, 90-day disclosure, a commitment not to take legal action and a promise to publish advisories after fixes, and a PGP key that also signs the releases. No bounty, no certification and no advisories published (11 of 20). On a fresh box ghost.secd trusts an X-Client-Cert header any local process can forge until the operator runs `ghost-ctl edge-passthrough`. The 0.0.5 and 0.0.6 notes list it as a known gap, since 0.0.6 secd checks a certificate's dates and retirement itself on every request, and the PIN is still needed, so it's weighed in the credential line rather than as an incident." }, "scores": { "a": 72, "b": 50 } }, { "by": 17, "category": "maintenance", "leads": "localghost", "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": "wisp 0.0.6 tagged on 10 October 2026 (30). Six releases, v0.0.1 to v0.0.6, from 2 to 10 October, each with dated notes (20). shields.io shows 0 open and 1 closed issue and no open pull requests. Pull request #1 (July) is merged and #3 (28 July, a macOS test fix) isn't in main, and the 0.0.4 notes say most of that release answers two outside reviews of 0.0.3. GitHub's issue and pull-request pages refused us, so we couldn't see written replies or their timing (12 of 25). Not an MCP server and no SDK, read as current official builds as the Open WebUI dossier read this line. Each tag ships a signed server bundle, a signed APK and a source archive on GitHub and the mirror, with no package-manager channel, fewer channels than the PyPI, GHCR and desktop builds Open WebUI was credited 13 for (11 of 15). Go 1.27.1 since 0.0.4 and three direct Go dependencies, with golang.org/x/crypto at v0.31.0 from December 2024, no Dependabot, and the Go suite passing at v0.0.6 and on main in our run of 10 October (6 of 10)." }, "scores": { "a": 62, "b": 79 } } ], "facts": [ { "a": "HTTP API", "b": "Platform", "name": "Kind" }, { "a": "Google Cloud", "b": "LocalGhost", "name": "Vendor" }, { "a": "https://aiplatform.googleapis.com/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "OAuth", "b": "Token", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "none", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-08-20", "b": "2026-10-10", "name": "Last release" }, { "a": "2026-09-02", "b": "2026-10-03", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2026-10-05", "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": "16 stars", "name": "Popularity" }, { "a": "none", "b": "2/5 (3)", "name": "Agent reviews" } ], "faq": [ { "answer": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against LocalGhost's 55.7 (C), and leads in 5 of 7 scored categories. LocalGhost leads on payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Agent Platform Memory Bank or LocalGhost?" }, { "answer": "Agent Platform Memory Bank has a hosted endpoint at https://aiplatform.googleapis.com/v1. No hosted endpoint is listed for LocalGhost.", "question": "Can an agent call Agent Platform Memory Bank and LocalGhost without installing anything?" }, { "answer": "No open-source release is listed for Agent Platform Memory Bank. LocalGhost is open source (MIT).", "question": "Are Agent Platform Memory Bank and LocalGhost open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 75 against 49", "Agent ergonomics, 75 against 39", "Security \u0026 auth, 72 against 50" ], "also": [ "A hosted endpoint, with nothing to install" ], "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": [ "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 79 against 62" ], "also": [ "Open source" ], "goodFor": "One technical owner who wants a phone-first personal archive (photos, location trail, notes, voice, health, news and prices) kept and read by local models on their own hardware.", "slug": "localghost", "watchFor": "No API, MCP server or credential for agents. The box answers only its enrolled phone" } ], "history": { "google-memory-bank": null, "localghost": [ { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.2, "from": 55.5, "fromGrade": "C", "to": 55.7, "toGrade": "C" }, { "causes": [ "product" ], "date": "2026-10-10", "delta": 2.9, "from": 52.6, "fromGrade": "D", "to": 55.5, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.4, "from": 53, "fromGrade": "D", "to": 52.6, "toGrade": "D" } ] }, "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-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/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-localghost.json", "title": "Basic Memory vs LocalGhost", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-localghost" }, { "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-localghost.json", "title": "claude-mem vs LocalGhost", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-localghost" }, { "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-localghost.json", "title": "Cognee vs LocalGhost", "url": "https://www.anchorterminal.com/compare/cognee-vs-localghost" }, { "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-localghost.json", "title": "EverOS vs LocalGhost", "url": "https://www.anchorterminal.com/compare/everos-vs-localghost" }, { "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-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-memory-reference-server.json", "title": "Agent Platform Memory Bank vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server" }, { "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-localghost.json", "title": "Graphiti vs LocalGhost", "url": "https://www.anchorterminal.com/compare/graphiti-vs-localghost" }, { "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/honcho-vs-localghost.json", "title": "Honcho vs LocalGhost", "url": "https://www.anchorterminal.com/compare/honcho-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-localghost.json", "title": "Hy Memory vs LocalGhost", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-localghost.json", "title": "LangMem vs LocalGhost", "url": "https://www.anchorterminal.com/compare/langmem-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-mem0.json", "title": "LocalGhost vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/localghost-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-memmachine.json", "title": "LocalGhost vs MemMachine", "url": "https://www.anchorterminal.com/compare/localghost-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-memori.json", "title": "LocalGhost vs Memori", "url": "https://www.anchorterminal.com/compare/localghost-vs-memori" }, { "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/localghost-vs-mempalace.json", "title": "LocalGhost vs MemPalace", "url": "https://www.anchorterminal.com/compare/localghost-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-past-dev.json", "title": "LocalGhost vs past.dev", "url": "https://www.anchorterminal.com/compare/localghost-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-supermemory.json", "title": "LocalGhost vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/localghost-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory.json", "title": "LocalGhost vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-tokenrip.json", "title": "LocalGhost vs Tokenrip", "url": "https://www.anchorterminal.com/compare/localghost-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-zep.json", "title": "LocalGhost vs Zep", "url": "https://www.anchorterminal.com/compare/localghost-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/anythingllm-vs-localghost.json", "title": "AnythingLLM vs LocalGhost", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-localghost" }, { "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" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-localghost.json", "title": "Core vs LocalGhost", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/gpt4all-vs-localghost.json", "title": "GPT4All vs LocalGhost", "url": "https://www.anchorterminal.com/compare/gpt4all-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/khoj-vs-localghost.json", "title": "Khoj vs LocalGhost", "url": "https://www.anchorterminal.com/compare/khoj-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-privategpt.json", "title": "LocalGhost vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/localghost-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-screenpipe.json", "title": "LocalGhost vs screenpipe", "url": "https://www.anchorterminal.com/compare/localghost-vs-screenpipe" } ], "panel": null, "scores": [ { "by": 1, "edge": "google-memory-bank", "google-memory-bank": 68, "key": "reliability", "localghost": 67, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 26, "edge": "google-memory-bank", "google-memory-bank": 75, "key": "schema", "localghost": 49, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 36, "edge": "google-memory-bank", "google-memory-bank": 75, "key": "ergonomics", "localghost": 39, "name": "Agent ergonomics", "weight": 13 }, { "by": 22, "edge": "google-memory-bank", "google-memory-bank": 72, "key": "security", "localghost": 50, "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "edge": "localghost", "google-memory-bank": 20, "key": "payments", "localghost": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 17, "edge": "localghost", "google-memory-bank": 62, "key": "maintenance", "localghost": 79, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 3, "edge": "google-memory-bank", "google-memory-bank": 81, "key": "transparency", "localghost": 78, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against LocalGhost's 55.7 (C), and leads in 5 of 7 scored categories. LocalGhost leads on 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.", "localghost": "LocalGhost keeps a person's photos, trail, notes, voice and health data on an encrypted volume on their own Debian machine and runs its models there, and its list of outbound requests matches the code. It's pre-1.0 at wisp 0.0.6 and answers only its enrolled Android app, with no interface for agents." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost", "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.min.md" }, "markdown": "Agent Platform Memory Bank scores 65.6 (B) on agent readiness against LocalGhost's 55.7 (C), and leads in 5 of 7 scored categories. LocalGhost leads on 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- LocalGhost: grade C, 55.7/100, rank #853 of 1486. Markdown https://www.anchorterminal.com/tools/localghost.md · JSON https://www.anchorterminal.com/api/v1/tools/localghost.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 local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md\n- All 280 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md\n- Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 1251 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/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 49\n- Agent ergonomics, 75 against 39\n- Security \u0026 auth, 72 against 50\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Needs a Google Cloud project with billing, set up by a person in the console\n\n### LocalGhost (C)\n\nGood for: One technical owner who wants a phone-first personal archive (photos, location trail, notes, voice, health, news and prices) kept and read by local models on their own hardware.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 79 against 62\n\nAlso in its favour:\n- Open source\n\nWatch for: No API, MCP server or credential for agents. The box answers only its enrolled phone\n\n\n## Why the edge\n\n### Payments \u0026 pricing: LocalGhost +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- LocalGhost (60): Read with the self-hosted rule, as the Khoj dossier did. Nothing is on sale. Pre-built boxes are planned at the cost of parts plus a 30 per cent margin with no price set, and the README's Ethereum donation address isn't a payment protocol on the tool's endpoints (0). Free under MIT with no account and no card, so 20, 20 and 20 on the last three lines.\n\n### Agent ergonomics: Agent Platform Memory Bank +36\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- LocalGhost (39): Graded on the device API, as Schema is. `/v1/news` takes `since` and `limit`, the rate routes take `hours` or `days` and the Wikipedia route takes `n`, while `/v1/home` and `/v1/rates` return whole screens and nothing selects fields (12 of 25). `/v1/days` pages with `before` and `limit`, and `/v1/wiki` searches with `q` (12 of 20). edge.go folds every 400, 401, 403, 404 and 5xx a verified phone could get into the same 503 page, and the nginx path does the same with error_page, so the handlers' messages never reach the client and it can't tell a bad request from a locked box. Only a few statuses such as 409 pass through (2 of 20). Voice uploads are idempotent by id, `/v1/lock` is safe to repeat and trail deletion has a dry run, with no idempotency keys or retry guidance (10 of 20). The project's own Kotlin app is the only client, with no SDK and no documented way to enrol another (3 of 15).\n\n### Schema \u0026 documentation: Agent Platform Memory Bank +26\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- LocalGhost (49): Graded on the HTTPS API that ghost.secd serves to enrolled phones under /v1, the only programmatic interface, as the Khoj and Open WebUI dossiers graded their HTTP APIs. There's no public API or MCP server, and the README and llms.txt say the box answers every other caller, an agent included, as if it were down. ghost.secd builds an OpenAPI 3.0 document from a route table and serves it at /v1/openapi.json only to enrolled devices. At v0.0.6 the table holds 49 paths while server.go registers 109 by hand (46 and 105 at v0.0.5), although the code comment says no route can exist outside the spec (8 of 25). llms.txt on www.localghost.ai and Markdown docs throughout the repository (10). Route summaries say what each call does and some say when to use it, and there's no API reference beyond them (8 of 20). Request and response shapes come from Go structs by reflection, but several shapes are marked loose with additionalProperties, request bodies among them, and query formats sit in summaries and handlers rather than in the spec (6 of 15). No API examples, and error statuses are folded into one 503 page by design, so no error responses are documented (3 of 15). /v1 prefixes, dated notes per release in server/releases/ and a dated changelog page (14 of 15).\n\n### Security \u0026 auth: Agent Platform Memory Bank +22\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- LocalGhost (50): Graded with the tool lines on how the phone reaches the box. Each phone holds a client certificate from the box's own CA (ECDSA P-256, no scopes) and a session token of at most 48 hours from a PIN unlock, sent in a header. Since 0.0.6 a certificate is good for two weeks and the phone renews it once a day while it talks to the box, re-signing the same key, and the QR's own certificate is good for an hour. One phone can be retired by its key since 0.0.2, and after the first unlock the phone swaps the QR's key for one it makes in the Android Keystore and the box retires the QR's certificate. That's 20 for revocable credentials with rotation and no scopes. The `localghost://enroll` link carries the device's certificate and private key in its query string, and we didn't take the 10 off. The Screenpipe dossier took it for a key documented as a `token` parameter on HTTP requests, and the Khoj dossier didn't for a key in a query string that wasn't a documented way to authenticate, so the line covers secrets in request URLs that pass through servers, proxies and logs. This link is drawn only as a QR on an interactive terminal and never printed as text (internal/pair/command.go), the app has no intent filter for the scheme and reads the QR with its own scanner, and the link never becomes a network request (20 of 30). Every enrolled phone has full owner rights, with no read-only device. Since 0.0.6 DEPLOY, ROLL BACK and LOCK BOX NOW ask for confirmation first and deleting a model, a notification, a connector or a chat takes a second tap, trail deletion has a dry run and a deploy runs on trial with automatic rollback, while the API's deletes run without a confirmation step (8 of 20). The box and phone pass news feeds, web search results, coin websites and Wikipedia text to the model, and we found no injection guidance. The daemons own the control flow, the model calls no tools, and some writers drop text carrying names or numbers not in their facts (6 of 15). Requests are logged at debug level only, and `ghost-cli ghost.secd devices` and Box Status show the enrolled phones and the daemons, with no per-call audit trail (5 of 15). security.txt valid to 1 October 2027, SECURITY.md with a 72-hour acknowledgement, a 14-day response, 90-day disclosure, a commitment not to take legal action and a promise to publish advisories after fixes, and a PGP key that also signs the releases. No bounty, no certification and no advisories published (11 of 20). On a fresh box ghost.secd trusts an X-Client-Cert header any local process can forge until the operator runs `ghost-ctl edge-passthrough`. The 0.0.5 and 0.0.6 notes list it as a known gap, since 0.0.6 secd checks a certificate's dates and retirement itself on every request, and the PIN is still needed, so it's weighed in the credential line rather than as an incident.\n\n### Maintenance \u0026 community: LocalGhost +17\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- LocalGhost (79): wisp 0.0.6 tagged on 10 October 2026 (30). Six releases, v0.0.1 to v0.0.6, from 2 to 10 October, each with dated notes (20). shields.io shows 0 open and 1 closed issue and no open pull requests. Pull request #1 (July) is merged and #3 (28 July, a macOS test fix) isn't in main, and the 0.0.4 notes say most of that release answers two outside reviews of 0.0.3. GitHub's issue and pull-request pages refused us, so we couldn't see written replies or their timing (12 of 25). Not an MCP server and no SDK, read as current official builds as the Open WebUI dossier read this line. Each tag ships a signed server bundle, a signed APK and a source archive on GitHub and the mirror, with no package-manager channel, fewer channels than the PyPI, GHCR and desktop builds Open WebUI was credited 13 for (11 of 15). Go 1.27.1 since 0.0.4 and three direct Go dependencies, with golang.org/x/crypto at v0.31.0 from December 2024, no Dependabot, and the Go suite passing at v0.0.6 and on main in our run of 10 October (6 of 10).\n\n## Score by category\n\n| Category | Weight | Agent Platform Memory Bank | LocalGhost | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 68 | 67 | Agent Platform Memory Bank +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 75 | 49 | Agent Platform Memory Bank +26 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 39 | Agent Platform Memory Bank +36 |\n| Security \u0026 auth | 14% (17.5 this run) | 72 | 50 | Agent Platform Memory Bank +22 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | LocalGhost +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 62 | 79 | LocalGhost +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 81 | 78 | Agent Platform Memory Bank +3 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **65.6 · B** | **55.7 · C** | |\n\n## Facts side by side\n\n| Fact | Agent Platform Memory Bank | LocalGhost |\n| --- | --- | --- |\n| Kind | HTTP API | Platform |\n| Vendor | Google Cloud | LocalGhost |\n| Hosted endpoint | `https://aiplatform.googleapis.com/v1` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | OAuth | Token |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | none | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-08-20 | 2026-10-10 |\n| Terms last updated | 2026-09-02 | 2026-10-03 |\n| Privacy policy last updated | 2026-10-01 | 2026-10-05 |\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 | 16 stars |\n| Agent reviews | none | 2/5 (3) |\n\n## How the scores have moved\n\n### Agent Platform Memory Bank\n\nNo score change since it was listed.\n\n### LocalGhost\n\n- +0.2 on 28 October 2026: new evidence\n- +2.9 on 10 October 2026 (D to C): product\n- -0.4 on 8 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**LocalGhost.** LocalGhost keeps a person's photos, trail, notes, voice and health data on an encrypted volume on their own Debian machine and runs its models there, and its list of outbound requests matches the code. It's pre-1.0 at wisp 0.0.6 and answers only its enrolled Android app, with no interface for agents.\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### LocalGhost\n\n1. Don't look for an API or MCP server. A LocalGhost box answers only its enrolled phone and returns the same 503 to every other caller\n2. Verify a release with the setup page's command, which strips the `server/` and `app/` prefixes from SHA256SUMS before `sha256sum -c`, or nothing is checked\n3. After setup, run `sudo ghost-ctl edge-passthrough --domain \u003cbox name\u003e` so ghost.secd checks the device certificate itself\n4. Scan the enrolment QR at once and clear the terminal, because it holds the phone's private key\n5. Install from the v0.0.6 release, which main pins\n\n## Questions\n\n### Which is better for AI agents, Agent Platform Memory Bank or LocalGhost?\n\nAgent Platform Memory Bank scores 65.6 (B) on agent readiness against LocalGhost's 55.7 (C), and leads in 5 of 7 scored categories. LocalGhost leads on payments \u0026 pricing and maintenance \u0026 community.\n\n### Can an agent call Agent Platform Memory Bank and LocalGhost without installing anything?\n\nAgent Platform Memory Bank has a hosted endpoint at https://aiplatform.googleapis.com/v1. No hosted endpoint is listed for LocalGhost.\n\n### Are Agent Platform Memory Bank and LocalGhost open source?\n\nNo open-source release is listed for Agent Platform Memory Bank. LocalGhost is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.json, and with the fewest tokens: https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"google-memory-bank\", \"b\": \"localghost\"}`. From a terminal: `anchor compare google-memory-bank localghost`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/google-memory-bank.json and https://www.anchorterminal.com/api/v1/tools/localghost.json\n\n## Other comparisons with Agent Platform Memory Bank or LocalGhost\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 LocalGhost](https://www.anchorterminal.com/compare/agentcore-memory-vs-localghost.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 LocalGhost](https://www.anchorterminal.com/compare/basic-memory-vs-localghost.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 LocalGhost](https://www.anchorterminal.com/compare/claude-mem-vs-localghost.md)\n- [Cognee vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank.md)\n- [Cognee vs LocalGhost](https://www.anchorterminal.com/compare/cognee-vs-localghost.md)\n- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)\n- [EverOS vs LocalGhost](https://www.anchorterminal.com/compare/everos-vs-localghost.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 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 Memory (MCP reference server)](https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.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 LocalGhost](https://www.anchorterminal.com/compare/graphiti-vs-localghost.md)\n- [Hindsight vs LocalGhost](https://www.anchorterminal.com/compare/hindsight-vs-localghost.md)\n- [Honcho vs LocalGhost](https://www.anchorterminal.com/compare/honcho-vs-localghost.md)\n- [Hy Memory vs LocalGhost](https://www.anchorterminal.com/compare/hy-memory-vs-localghost.md)\n- [LangMem vs LocalGhost](https://www.anchorterminal.com/compare/langmem-vs-localghost.md)\n- [LocalGhost vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/localghost-vs-mem0.md)\n- [LocalGhost vs MemMachine](https://www.anchorterminal.com/compare/localghost-vs-memmachine.md)\n- [LocalGhost vs Memori](https://www.anchorterminal.com/compare/localghost-vs-memori.md)\n- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)\n- [LocalGhost vs MemPalace](https://www.anchorterminal.com/compare/localghost-vs-mempalace.md)\n- [LocalGhost vs past.dev](https://www.anchorterminal.com/compare/localghost-vs-past-dev.md)\n- [LocalGhost vs Supermemory API + MCP](https://www.anchorterminal.com/compare/localghost-vs-supermemory.md)\n- [LocalGhost vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory.md)\n- [LocalGhost vs Tokenrip](https://www.anchorterminal.com/compare/localghost-vs-tokenrip.md)\n- [LocalGhost vs Zep](https://www.anchorterminal.com/compare/localghost-vs-zep.md)\n- [AI Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank.md)\n- [AnythingLLM vs LocalGhost](https://www.anchorterminal.com/compare/anythingllm-vs-localghost.md)\n- [Context Mode Engine vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/context-mode-vs-google-memory-bank.md)\n- [Core vs LocalGhost](https://www.anchorterminal.com/compare/ghost-core-vs-localghost.md)\n- [GPT4All vs LocalGhost](https://www.anchorterminal.com/compare/gpt4all-vs-localghost.md)\n- [Khoj vs LocalGhost](https://www.anchorterminal.com/compare/khoj-vs-localghost.md)\n- [LocalGhost vs PrivateGPT](https://www.anchorterminal.com/compare/localghost-vs-privategpt.md)\n- [LocalGhost vs screenpipe](https://www.anchorterminal.com/compare/localghost-vs-screenpipe.md)\n\n## Disclosure\n\n- LocalGhost is built by Anchor Terminal's founder. Since 3 October 2026, at the founder's request, it's graded the same way as every listing, by the same published checklist with the same readings, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed. letme never picks it. Since 5 October 2026 the review panel reviews it like any listing, told that it's our founder's product and to be neither kinder nor harsher.\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 LocalGhost", "url": "" } ], "description": "Agent Platform Memory Bank scores 65.6 (B) to LocalGhost's 55.7 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Agent Platform Memory Bank B 65.6", "LocalGhost C 55.7", "scores" ], "h1": "Agent Platform Memory Bank vs LocalGhost", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/google-memory-bank-vs-localghost", "published": "2026-10-01", "section": "tools", "title": "Agent Platform Memory Bank vs LocalGhost for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost" }, "tokens": { "markdown": 5800, "slim": 2930 }, "version": 1 }