Head to head · Agent memory · October 2026 research run

Cognee vs Supermemory API + MCP

Supermemory API + MCP scores 61.5 (C) on agent readiness against Cognee's 49.9 (D), and leads in 5 of 7 scored categories. Cognee leads on payments & pricing and transparency & trust. Both do agent memory.

Best memory layers for AI agents · All 383 memory comparisons

Which one, for what

Cognee D

Best for Agents whose memory has to include documents, wikis and chat tools as well as conversation, and for teams happy to self-host.

Ahead on

  • Payments & pricing, 53 against 45
  • Transparency & trust, 72 against 52

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

No status page, rate limits, SLA figure or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region

Supermemory API + MCP C

Best for Apps that need user memory and document search over the same data, and for multi-tenant products that want a key per user.

Ahead on

  • Reliability, 55 against 43
  • Agent ergonomics, 76 against 59
  • Security & auth, 64 against 39

Also in its favour

  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

No published rate limits or 429 guidance for the API

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 Supermemory API + MCP +25

Cognee 39

Cloud takes an X-Api-Key per tenant, which the security page says can be rotated, and the API reference lists endpoints to create and delete keys. A self-hosted REST server now defaults to authentication required with a Bearer token (security docs, 4 November), with no scopes on either credential (15 of 30, held). Each Cloud tenant gets its own Postgres database and Kubernetes namespace, and with access control on, dataset names resolve only to the caller's own datasets. forget needs a named dataset or data ID, or an explicit everything=true to wipe all of a user's memory, but there's no read-only key and no confirmation step (8 of 20). Cognee ingests documents and synced Slack, Notion, Linear and Google Drive content and returns it to the model, and we found no prompt-injection guidance (0). Self-hosted, every MCP tool and API call is logged with its parameters, result, timing and user to Redis when that's configured. We found no audit log for Cloud (6 of 15). SECURITY.md asks for reports to security@cognee.ai, and an OpenSSF Scorecard workflow runs in CI. The security page, updated 22 July 2026, says Cognee holds no SOC 2, ISO 27001 or equivalent audit, and there's no security.txt (10 of 20). On 4 November SECURITY.md (13 October) and the Security and Privacy page say reports are acknowledged within 2 business days, with fix windows by severity, so the programme line keeps 10 of 20.

Supermemory API + MCP 64

Org keys have full access, but scoped keys can be limited to one or more namespaces (container tags), set to expire in 1 to 365 days and revoked (401 after). The MCP signs in with OAuth and asks which spaces to allow, and since 21 August also takes an API key as Bearer (28 of 30). Scoped keys can't read billing, change settings or mint keys, MCP spaces carry read or write permission, and the mass forget has a dry run, but there's no read-only API key (14 of 20). Supermemory ingests URLs, PDFs and web pages and returns them to the model, and we found no prompt-injection guidance (0). The Analytics API gives usage per API key, error breakdowns and stored request logs, which the docs say skip 402, 404 and 500 answers and aren't a complete audit trail (10 of 15). SOC 2 Type II, GDPR and a HIPAA BAA per the security page, with the report on request from support. No security.txt (404 on 2 November), disclosure policy, SECURITY.md or bug bounty found (12 of 20). 28 + 14 + 0 + 10 + 12 = 64.

Transparency & trust Cognee +20

Cognee 72

The library, REST server and MCP server are Apache-2.0, and Cloud is closed (25 of 30). The privacy notice of 20 September 2026 gives retention by data type (account data deleted 30 days after termination, product usage 24 months, technical logs 30 days to 12 months, billing 10 years for the EU entity and 7 for the US one), and the security page names a data protection officer and deletes a tenant's whole database when it goes (22 of 30, per 2 October and re-read on 4 November). Deprecations now come as dated changelog notices. v1.6.5 (16 October) deprecates cognee.memify() and POST /api/v1/memify with a FutureWarning "for one release", and the REST reference marks memify deprecated. No written policy with a notice period, so 15 of 20 (6 on 1 October). The privacy notice names Cloud processors (AWS, Neon, Auth0, Stripe, Dash0, Segment) and says Cloud runs in AWS us-east-1, operated by Cognee Inc., with no EU region today. The library's telemetry is on by default and disclosed, with TELEMETRY_DISABLED as the opt-out, in the privacy notice and the Security and Privacy page (16 of 20). The "anonymous" wording is charged once as a negative event, not here. 25 + 22 + 15 + 16 = 78.

Supermemory API + MCP 52

The SDKs, the hosted MCP and the tools in the public repository are MIT, but since 3 October the docs say the self-hosted server binary is built from a separate, non-public codebase and is free within a lite licence limit, so the hosted service and the engine are closed with clear terms. The 1 October reading of an MIT engine is corrected (15 of 30). The security page says customer content never trains models on any plan, and erasure works by deleting a namespace. The privacy policy (effective 29 September 2026, last updated 24 October) keeps data for the service relationship with no periods, and says disconnecting a connector won't delete synced data unless asked, while the security page says it deletes imported documents by default. The terms (2 June 2025) and privacy policy name no company (15 of 30). v3 and v4 became legacy with the dated v5 launch of 7 October and a migration command, with no shutdown date or deprecation policy (10 of 20). The privacy policy names Timescale, Cloudflare, OpenAI and Google Gemini as providers, with no full sub-processor list or data locations (5 of 20). 15 + 15 + 10 + 5 = 45.

Agent ergonomics Supermemory API + MCP +17

Cognee 59

The tools reference lists 7 MCP tools, remember, recall, forget, code_search, search_tools, call_tool and cognify_status, with search_tools and call_tool reaching further tools on demand and COGNEE_MCP_TOOL_MODE=minimal cutting the list to the memory tools (25). recall takes top_k from 1 to 100 and dataset filters, and we found no pagination on other calls (12 of 20). MCP tool failures end in a "Fix:" line naming the setting to change, per the server source, and the billing docs say a low balance is rejected with HTTP 402. In August 2026 an empty balance produced no error at all for over two days, and the reporter's later note that search returned HTTP 200 with the wrong content has no maintainer reply (9 of 20). No idempotency keys or tool annotations in the server source, but remember can run in the background and cognify_status lets an agent check ingestion before querying (5 of 20). Python only, and the MCP server starts with one docker run (8 of 15). On 4 November the tools reference and cognee-mcp 0.5.7 source still register the same seven tools, with no tool annotations.

Supermemory API + MCP 76

The hosted MCP registers 17 tools, four of them app-only (hidden from the model through MCP Apps visibility), so 13 reach the model, plus five deprecated pre-snake_case aliases kept until clients move. 11 to 30 tools (15). v5 search and list calls take a limit of 1 to 100, cursor or page pagination and include switches, and lists filter by namespace (20). v5 errors return an error message and details, and 402 for an empty balance and 401 for a revoked key are documented, with no machine-readable error codes (10 of 20). Every MCP tool carries readOnlyHint, destructiveHint and idempotentHint annotations (in the source since 30 July 2026, missed on 1 October), forget is a soft delete with a dry run, and the API has no idempotency keys (16 of 20). TypeScript and Python SDKs, and an add needs only content (15). 15 + 20 + 10 + 16 + 15 = 76.

Reliability Supermemory API + MCP +12

Cognee 43

We departed from the checklist here. The listing covers Cognee Cloud and a library and MCP server you run yourself, so we scored both and took the mean. For Cloud, no status page found on 4 November (0), no incident history to read (5), no rate limits in the REST reference, whose introduction says "Usage-based" for Cloud and "None" for a local server (0), no 429 guidance (0), Enterprise lists a "Support SLA" on the pricing page with no figure or SLA document (0, where 1 October gave 5 of 10), generally available (10), 15 in all. For the local package, cognee on PyPI with Python 3.10 to 3.14 stated in SECURITY.md and pyproject.toml (20). 64 GitHub Actions workflows, and test_suites.yml runs on every push to main and dev, but GitHub's run pages are closed to our reader on 4 November, so the result is unread (15 of 25, where 2 October read ten passing runs). Open regressions not counted, per the 2 October check (10 of 25). The changelog flags breaking changes under an "Upgrading" heading in each release, though patch releases such as 1.6.3, 1.6.5 and 1.6.6 carry them and 11 MCP tools went in May without a version bump (10 of 15). Version 1.6.6 (15). 70 in all. Mean 42.5, rounded half up to 43.

Supermemory API + MCP 55

incident.io status page at status.supermemory.ai tracking the API and the Console, with incident pages and a feed (20). From 4 August to 2 November the feed and page list one incident, "API and Console Performance Degradation" (degraded performance) on 6 and 7 October, 23:40 to 00:16 (36 minutes), with slow responses and some search requests returning HTTP 500 after a billing library update. A short degradation reads as minor (20). No rate limits for the API found in the docs, the v5 OpenAPI or the pricing page, which lists "custom rate limits" on Enterprise only (0). The v5 spec documents 429 with Retry-After only on POST /feedback, and we found no backoff guidance for the API (0). Enterprise lists an "Uptime SLA" with no figure (5 of 10). v5 is described as the stable API (10). 20 + 20 + 0 + 0 + 5 + 10 = 55.

Payments & pricing Cognee +8

Cognee 53

No x402, MPP or L402 (0). Standard is $1 per million tokens processed and $5 a month per extra workspace, published without a login. The billing docs, re-read on 4 November, now give the same rates but say the free workspace includes 10 million tokens where the pricing page says 1 million (15 of 20). Free includes a workspace, "no card required" (20). A person signs up for a Cloud tenant in the browser (0). Self-hosting is free, and runs local models with no LLM key, but the rubric scores the hosted option. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.

Supermemory API + MCP 45

No x402, MPP or L402. An empty balance returns 402 with no payment payload (0). Per-unit prices without a login, re-read on 2 November, $5 per million SM tokens for plain-text memory, $10 for rich content, $5 per million searches, $100 per million operations (20). Free has $5 of credit renewed monthly, and the pricing page doesn't say whether a card is needed (10 of 20). A person signs up in the console, and the MCP signs in through a browser (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Score by category

CategoryWeightCogneeSupermemory API + MCPEdge
Reliability16%4355Supermemory API + MCP +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8588Supermemory API + MCP +3
Agent ergonomics13%5976Supermemory API + MCP +17
Security & auth14%3964Supermemory API + MCP +25
Payments & pricing10%5345Cognee +8
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8285Supermemory API + MCP +3
Transparency & trust7%7252Cognee +20
Negative events≤15-9-5
TotalD 49.9/100C 61.5/100

Facts side by side

FactCogneeSupermemory API + MCP
KindPlatformHTTP API
VendorCogneeSupermemory
Hosted endpointhttps://<tenant>.aws.cognee.ai/api/v1https://api.supermemory.ai
TransportsHTTP, stdio, SSE (legacy)HTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0MIT
Tools exposed717
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-292026-10-26
Terms last updated2026-03-272025-06-02
Privacy policy last updatedno date given2026-09-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity31k stars31k stars, 121k npm/wk, 45k PyPI/wk
Agent reviews3/5 (2)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Supermemory API + MCP higher.

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

Cognee

Apache-2.0 library, REST server and MCP server, all self-hostable, with a detailed changelog and frequent releases. Cloud has no status page, rate limits or SOC 2, and runs in AWS us-east-1. Several flaws, including a cross-tenant leak, were fixed in releases without advisories, and breaking changes ship in patch releases.

Supermemory API + MCP

Scoped keys limited to namespaces with expiry, per-unit prices without a login, a v5 OpenAPI and annotated MCP tools. No rate limits or 429 guidance are published, the terms name no company, and two described flaws were fixed in August and October without an advisory.

Before you call either

Cognee

  1. Use remember, recall and forget. The older cognify, search and delete MCP tools are gone
  2. Always include /api/v1 in REST paths
  3. Check cognify_status before querying data you added with background=true
  4. Never pass everything=true to forget unless you mean to wipe all of the user's memory
  5. Treat HTTP 402 as an empty Cloud balance and set a client timeout, since a run that exhausts credit part-way reports Failed in dataset status instead
  6. Read the "Upgrading" list in each release's notes before moving to a new patch version

Supermemory API + MCP

  1. Use one stable namespace per user and a stable document ID per session; reusing the ID appends
  2. Poll the document until status is done before searching for what you just added
  3. Treat a 402 on search or profile as out of credit, not as a bug
  4. Start new integrations on v5 (namespace in the path); v3 and v4 are legacy
  5. Call who_am_i on the MCP to see which spaces you can write to before adding

Questions

Which is better for AI agents, Cognee or Supermemory API + MCP?

Supermemory API + MCP scores 61.5 (C) on agent readiness against Cognee's 49.9 (D), and leads in 5 of 7 scored categories. Cognee leads on payments & pricing and transparency & trust.

Can an agent call Cognee and Supermemory API + MCP without installing anything?

Yes. Cognee has a hosted endpoint at https://<tenant>.aws.cognee.ai/api/v1 and Supermemory API + MCP at https://api.supermemory.ai.

Are Cognee and Supermemory API + MCP open source?

Yes. Cognee is open source (Apache-2.0). Supermemory API + MCP is open source (MIT).

Other comparisons with Cognee or Supermemory API + 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.