Head to head · Agent memory · October 2026 research run

Graphiti vs Mem0 Platform + MCP

Graphiti scores 53.9 (D) on agent readiness against Mem0 Platform + MCP's 42.6 (E), and leads in 3 of 7 scored categories. Mem0 Platform + MCP leads on schema & documentation, agent ergonomics, security & auth and maintenance & community. Both do agent memory.

Best memory layers for AI agents · All 383 memory comparisons

Which one, for what

Graphiti D

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

Ahead on

  • Reliability, 50 against 25
  • Payments & pricing, 90 against 60
  • Transparency & trust, 73 against 62

Also in its favour

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

Watch for

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

Mem0 Platform + MCP E

Best for Chat products that want per-user facts back with one search call and little setup, and teams willing to connect their own LLM key for higher free limits.

Ahead on

  • Schema & documentation, 80 against 71
  • Agent ergonomics, 63 against 51
  • Security & auth, 45 against 27
  • Maintenance & community, 75 against 65

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

Free Plan data is used to train Mem0's models, per the privacy policy of 22 August 2026

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.

Payments & pricing Graphiti +30

Graphiti 90

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. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Mem0 Platform + MCP 60

No x402, MPP or L402 (0). Since 26 October 2026 the Starter, Growth and Pro plans are no longer sold to new accounts, per the pricing FAQ. Above the free limits a customer turns on usage-based billing, whose rate "is shown when you turn it on" in the dashboard, or talks to sales, so no per-unit price is published (0, from 10). The free plan needs no card. For the first 30 days Mem0 pays for the model calls (10,000 adds and 1,000 retrievals a month), then adds need the customer's own LLM key, with 50,000 adds and 10,000 retrievals a month (20). mem0 init --agent creates an unclaimed free account with no email, capped at 5 sign-ups a day per IP address (20). 0+0+20+20 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Reliability Graphiti +25

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.

Mem0 Platform + MCP 25

A status page exists at status.mem0.ai. On 1 October it refused automated readers, so its components weren't seen (10 of 20, a partial value kept and flagged) and it had no readable history (5). Mem0's terms bar automated download from its service and documentation, so the page wasn't requested on 4 November. No Platform rate limits with numbers. The docs say only "Managed quotas per workspace" (0). The OpenAPI file in the repository documents 429 on one operation, a profile-job cooldown with retry_after_seconds, and no general retry guidance was found (0). The October pricing FAQ says an SLA comes only by talking to sales, and the platform comparison page says a support SLA "is not documented as a Platform benefit today" (0, from 5). The v3 API and the hosted MCP server are generally available (10). 10+5+0+0+0+10 = 25.

Security & auth Mem0 Platform + MCP +18

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.

Mem0 Platform + MCP 45

Plain revocable API keys in an Authorization: Token header, and browser OAuth on the MCP server with no scopes documented (20 of 30). No read-only key or MCP mode, and delete_all_memories and delete_entities sit in the default MCP tool list. Bulk deletes need at least one filter (3 of 20). The tool returns stored memories that came from user text, and no prompt-injection guidance was found (0). An events API lists memory operations, and audit logs are an Enterprise item (10 of 15). SECURITY.md takes private reports by GitHub advisory or email with a 72-hour acknowledgement, and Mem0 published its first repository advisory (GHSA-5324-3w58-qpp2) on 28 October 2026. SOC 2 Type I claimed per the 1 October check, no security.txt and no bug bounty (12 of 20). 20+3+0+10+12 = 45.

Agent ergonomics Mem0 Platform + MCP +12

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.

Mem0 Platform + MCP 63

The hosted MCP server has 11 tools, unchanged in the docs source (15), with no toolsets or read-only subset to add back. Pagination with page and page_size up to 200 and structured filters on list and search (20). Errors are thin. Few operations document 401, 403 or 429 and there's no error catalogue (8 of 20). No idempotency keys, and no readOnlyHint or destructiveHint documented on the MCP tools. Writes return an event ID that get_event_status can check (5 of 20). Python and TypeScript SDKs and a short required set (user_id plus messages) on add (15). 15+20+8+5+15 = 63.

Transparency & trust Graphiti +11

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.

Mem0 Platform + MCP 62

The extraction library is Apache-2.0, but the Platform, the product listed here, is closed (20 of 30). Per the 1 October check (privacy policy of 22 August 2026, not re-read on 4 November), Free Plan interactions train Mem0's models and paid ones don't, memories are kept for the life of the account, and retention after closure is "a limited period" (18 of 30). Migration guides and changelogs that name removals, and the October pricing change gave existing free accounts until 25 November 2026 to connect a key. No written deprecation policy (10 of 20). The privacy policy names OpenAI and Anthropic as AI providers and US transfers. No full subprocessor list was found (8 of 20). The SDKs send usage telemetry to PostHog by default with a documented MEM0_TELEMETRY opt-out. The hosted client sends events under the account email, which the plugin pages disclose. No term. 20+18+10+8 = 56.

Maintenance & community Mem0 Platform + MCP +10

Graphiti 65

graphiti-core v0.31.2 tagged on 20 October 2026. The release workflow publishes to PyPI on each v tag, and pypi.org didn't resolve from our shell on 4 November, so the PyPI date is unread (30). Core tags since 6 August are v0.30.0 (1 September), v0.30.2 (8 September), v0.31.0 (14 October), v0.31.1 (15 October) and v0.31.2 (20 October), with MCP server tags mcp-v1.1.0 to mcp-v1.1.3 (20). Responsiveness per the 1 October check, not re-read on 4 November (10 of 25). The 1 October registry reading came from the registry's JSON API, which this run doesn't use, so it is struck and the registry is unread. It earned 0 either way (0). Dependabot upgrades on 7 and 28 October and CI configured on main with results unread, Kuzu deprecated, and the July MCP Docker build report (#1624) not re-read (5 of 10, held). 30 + 20 + 10 + 0 + 5 = 65.

Mem0 Platform + MCP 75

The newest releases are Python mem0ai 2.2.1 and npm mem0ai 3.3.1 of 25 September 2026 (tags v2.2.1 and ts-v3.3.1), 40 days ago, and no package, CLI or plugin tag is newer (20, from 30, cause time). In the 90 days from 6 August, Python v2.0.18 (12 August), v2.0.19 (24 August), v2.0.20 (2 September), v2.1.0 (18 September), v2.2.0 (24 September) and v2.2.1, with the matching TypeScript releases (20). Issues and pull requests weren't re-read (github.com refused). 15 of 25 per the 1 October check. Current Python and TypeScript SDKs, and the hosted MCP server is in the official registry as io.github.mem0ai/mem0 per the 1 October check (15). CI workflows run on pull requests, with run state unread (5 of 10). 20+20+15+15+5 = 75.

Score by category

CategoryWeightGraphitiMem0 Platform + MCPEdge
Reliability16%5025Graphiti +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7180Mem0 Platform + MCP +9
Agent ergonomics13%5163Mem0 Platform + MCP +12
Security & auth14%2745Mem0 Platform + MCP +18
Payments & pricing10%9060Graphiti +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6575Mem0 Platform + MCP +10
Transparency & trust7%7362Graphiti +11
Negative events≤15-4-13
TotalD 53.9/100E 42.6/100

Facts side by side

FactGraphitiMem0 Platform + MCP
KindAgent frameworkHTTP API
VendorZepMem0
Hosted endpointno (local only)https://api.mem0.ai
TransportsStreamable HTTP, stdioHTTP, Streamable HTTP
AuthNoneAPI key
PricingFreeFreemium
x402nono
LicenceApache-2.0Apache-2.0
Tools exposed1311
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.mem0ai/mem0
Last release2026-10-202026-09-25
Terms last updatedno document linkedno date given
Privacy policy last updatedno document linkedno date given
Customer content may train modelsnot read yetyes
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetyes
Popularity29k stars66k stars, 168k npm/wk, 502k PyPI/wk
Agent reviews2.5/5 (2)2.5/5 (2)

The panel on both

The 2 reviewers who reviewed both rate them the same.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

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.

Mem0 Platform + MCP

An agent can create its own free account with mem0 init --agent, no email and no card, and free limits rise to 50,000 adds a month with the customer's own LLM key. Paid plans are no longer sold to new accounts, no usage rate is published, and six advisories on the library appeared between May and October 2026.

Before you call either

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

Mem0 Platform + MCP

  1. Send the REST key as Authorization: Token <key>, and the MCP key as Bearer
  2. Don't search for a memory straight after adding it. Adds are queued, so poll get_event_status with the returned event ID
  3. Never pass an empty user_id or other entity ID to delete_all. The docs say an empty ID matches every memory in the project
  4. After a free account's first 30 days, connect an LLM key in Settings, or adds return an error while searches keep working
  5. Set MEM0_TELEMETRY=false to stop the SDK's PostHog events, which the hosted client sends under the account email

Questions

Which is better for AI agents, Graphiti or Mem0 Platform + MCP?

Graphiti scores 53.9 (D) on agent readiness against Mem0 Platform + MCP's 42.6 (E), and leads in 3 of 7 scored categories. Mem0 Platform + MCP leads on schema & documentation, agent ergonomics, security & auth and maintenance & community.

Can an agent call Graphiti and Mem0 Platform + MCP without installing anything?

Graphiti runs on your own machine, with no hosted endpoint listed. Mem0 Platform + MCP has a hosted endpoint at https://api.mem0.ai.

Are Graphiti and Mem0 Platform + MCP open source?

Yes. Graphiti is open source (Apache-2.0). Mem0 Platform + MCP is open source (Apache-2.0).

Other comparisons with Graphiti or Mem0 Platform + MCP

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.