Head to head · Agent memory · October 2026 research run

Agent Platform Memory Bank vs Graphiti

Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Graphiti's 50.1 (D), and leads in 5 of 7 scored categories. Graphiti leads on payments & pricing. Both do agent memory.

Best memory layers for AI agents · All 353 memory comparisons

Which one, for what

Agent Platform Memory Bank B

Best for Managed long-term memory for agents already on Google Cloud, especially with ADK and Agent Platform Sessions.

Ahead on

  • Reliability, 68 against 50
  • Agent ergonomics, 75 against 51
  • Security & auth, 72 against 27
  • Transparency & trust, 81 against 73

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where Graphiti loses 4 points for them

Watch for

Needs a Google Cloud project with billing, set up by a person in the console

Graphiti D

Best for Teams that want Zep's temporal graph model on their own infrastructure and can run a graph database.

Ahead on

  • Payments & pricing, 60 against 20

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source

Watch for

Every add runs LLM extraction, so ingestion costs tokens and time

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth Agent Platform Memory Bank +45

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.

Graphiti 27

Scored for a framework you run yourself. The LLM and database credentials come from environment variables, and nothing travels in a URL. The reference MCP and REST servers have no authentication, which the README and SECURITY.md (19 October) now state, and since MCP server 1.1.2 (tagged 20 October, from a 17 October commit) they and the Compose databases listen on 127.0.0.1 by default (15 of 30, held). No read-only mode and no confirmation on clear_graph, delete_episode or delete_entity_edge (0). SECURITY.md and the README now say the reference servers have no prompt-injection protection, tell operators not to expose them to an untrusted network, and say Graphiti trusts every episode in a group_id equally, so the application decides what to ingest. Guidance with no mitigations (5 of 15, was 0). No audit log of tool calls found (0). SECURITY.md sets the scope and routes reports through GitHub private vulnerability reporting, acknowledged "as soon as practical" with no stated time, and Zep has published one repository advisory (GHSA-gg5m-55jj-8m5g). No bug bounty or security.txt. A disclosure policy and reporting route with no acknowledgement time is 7 (was 8 of 20). Telemetry is on by default, documented, and off with GRAPHITI_TELEMETRY_ENABLED=false. 15 + 0 + 5 + 0 + 7 = 27.

Payments & pricing Graphiti +40

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.

Graphiti 60

Free Apache-2.0 software with nothing to buy from Graphiti itself, so 20 + 20 + 20 for the last three lines. No payment protocol (0). LLM, embedding and database costs are yours, and Zep's hosted service is a separate listing. 0 + 20 + 20 + 20 = 60.

Agent ergonomics Agent Platform Memory Bank +24

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.

Graphiti 51

13 MCP tools (15), with no toolsets or read-only subset. Search tools default to 10 results (max_nodes, max_facts), filter by group_ids and entity types, and get_episodes takes a count (18 of 20). Error shapes aren't documented and we didn't test them (8 of 20). None of the 13 tools in graphiti_mcp_server.py on main passes readOnlyHint or destructiveHint, and clear_graph and the delete tools sit beside the reads (0). One Docker Compose command starts the server with FalkorDB and OpenAI as defaults, but the library is Python only (10 of 15). 15 + 18 + 8 + 0 + 10 = 51.

Reliability Agent Platform Memory Bank +18

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.

Graphiti 50

Scored on the local-package checklist. graphiti-core installs from PyPI with Python 3.10 to below 4 stated in pyproject.toml (20). unit_tests.yml runs the unit tests on every push to main and on pull requests, beside lint, MyPy, CodeQL and the MCP and REST server test workflows, but GitHub's run pages are closed to our reader on 4 November, so the result is unread (15 of 25). Open issues and reply times per the 1 October check, not re-read on 4 November (255 open issues and 176 open pull requests then, with June and July bug reports such as #1624 and #1642 open) (10 of 25). Every release is tagged in the repository (v0.30.0, v0.30.2, v0.31.0, v0.31.1 and v0.31.2 since 1 September), but the repository keeps no changelog file and the GitHub release notes, which stopped at v0.29.2 on 1 October, couldn't be read on 4 November (5 of 15). Version 0.31.2, below 1.0 (0). 20 + 15 + 10 + 5 + 0 = 50.

Transparency & trust Agent Platform Memory Bank +8

Agent Platform Memory Bank 81

Closed service under the Google Cloud terms (15). Data residency at rest, CMEK and the Cloud Data Processing Addendum apply; no Memory Bank retention period or time-to-live was read (20 of 30). The rename was announced in the release notes with old and new names listed, and Google's deprecation policy covers GA services (14 of 20). Google Cloud's subprocessor list and regional endpoints are published (16 of 20). Total 65.

Graphiti 73

Apache-2.0 (30). Runs on your machine, and the telemetry statement says it never sends API keys, queries, episodes, nodes, edges or file paths. Your data goes to the LLM provider you configure (20 of 30). Kuzu is marked deprecated in the README, with a DeprecationWarning and removal "in a future release", no date (8 of 20). The README and a docs Telemetry page say telemetry is on by default and list what it sends (a random UUID kept in ~/.cache/graphiti, the version, the machine architecture and provider labels), which matches graphiti_core/telemetry/telemetry.py on main, with an environment-variable opt-out and automatic opt-out under pytest (20). 30 + 20 + 8 + 20 = 78.

Score by category

CategoryWeight this runAgent Platform Memory BankGraphitiEdge
Reliability16%206850Agent Platform Memory Bank +18
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27571Agent Platform Memory Bank +4
Agent ergonomics13%16.27551Agent Platform Memory Bank +24
Security & auth14%17.57227Agent Platform Memory Bank +45
Payments & pricing10%12.52060Graphiti +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86265Graphiti +3
Transparency & trust7%8.88173Agent Platform Memory Bank +8
Negative events≤150-4
TotalB 65.6/100D 50.1/100

Facts side by side

FactAgent Platform Memory BankGraphiti
KindHTTP APIAgent framework
VendorGoogle CloudZep
Hosted endpointhttps://aiplatform.googleapis.com/v1no (local only)
TransportsHTTPStreamable HTTP, stdio
AuthOAuthNone
PricingPay per useFree
x402nono
LicencenoneApache-2.0
Tools exposednone13
Read-only variant documentednono
llms.txtnoyes
Last release2026-08-202026-10-20
Terms last updated2026-09-02no document linked
Privacy policy last updated2026-10-01no document linked
Customer content may train modelsyesnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet
Popularitynone29k stars
Agent reviewsnone2.5/5 (2)

How the scores have moved

Verdicts

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.

Graphiti

Graphiti is an Apache-2.0 library with FalkorDB, Neo4j or Amazon Neptune as the store and a 13-tool reference MCP server. Every add runs LLM extraction, so ingestion costs tokens and time. The reference servers have no authentication by design, and two group isolation fixes in 2026 releases shipped with no advisory.

Before you call either

Agent Platform Memory Bank

  1. Run memories.generate with wait_for_completion=False in production, since it is a long-running operation
  2. Always pass a scope such as {"user_id": ...} so one user's memories never reach another
  3. Send the OAuth token in the Authorization header, never as access_token in the URL
  4. Expect a 404 when fetching a deleted memory and treat it as gone
  5. Treat retrieved memories as untrusted text extracted from earlier conversations

Graphiti

  1. Set OPENAI_API_KEY (or another provider's key) and MODEL_NAME before starting the MCP server
  2. Use search_memory_facts for facts and search_nodes for entities instead of reading whole episodes
  3. Never call clear_graph to fix one fact. Use delete_episode or delete_entity_edge
  4. Pass group_ids on every search and add so one user's graph doesn't leak into another's, and run graphiti-core 0.31.2 or later
  5. Keep the MCP server on 127.0.0.1 or behind your own authentication, since it has none

Questions

Which is better for AI agents, Agent Platform Memory Bank or Graphiti?

Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Graphiti's 50.1 (D), and leads in 5 of 7 scored categories. Graphiti leads on payments & pricing.

Can an agent call Agent Platform Memory Bank and Graphiti without installing anything?

Agent Platform Memory Bank has a hosted endpoint at https://aiplatform.googleapis.com/v1. Graphiti runs on your own machine, with no hosted endpoint listed.

Are Agent Platform Memory Bank and Graphiti open source?

No open-source release is listed for Agent Platform Memory Bank. Graphiti is open source (Apache-2.0).

Other comparisons with Agent Platform Memory Bank or Graphiti

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.