All comparisons
Heartwood Memory comparison

Heartwood vs Cognee — provable records vs graph/ontology memory

TL;DR

Cognee combines relational, vector, and graph stores to turn source data into searchable, connected memory, with tenant/dataset-level permissions and documented audit logging; it leads on graph and ontology depth and has a longer public history than Heartwood. Heartwood's difference is record-level cryptographic proof — signed memories, policy-before-ranking, key-destruction erasure — that you re-execute yourself.

At-a-glance table

Heartwood Memory compared with Cognee
AxisHeartwood MemoryCognee
Governance granularityPer individual memory recordTenant roles + direct dataset-level read/write/delete grants
Provenance signingPer-record Ed25519, re-verified at read (opt-in strict enforcement)Not evaluated in public docs (document-level metadata/provenance)
Tamper-evident auditHash-chained audit logNot evaluated in public docs (Cloud lists audit logging)
Policy-before-rankingYesNot evaluated in public docs (results limited to accessible datasets)
Erasure / RTBFCrypto-shred + key-destruction receiptItem/dataset/all deletion of graph/vector/relational data, with caveats (no cryptographic proof)
Tenant isolationYesYes — complete data isolation; workspace = tenant
InterfacePython library + governed MCP serverPython API, HTTP API, CLI, MCP tools
DeploymentSelf-hosted, embeddedLocal/embedded, self-hosted Docker, managed Cloud, Enterprise BYO cloud
LicenseSource-available (BSL 1.1); 0.1.x MITApache-2.0 OSS engine; Cloud + Enterprise separate
PricingFree / Team $349·mo / Pro $6,000·yr / Enterprise Let’s talkFree ($0, 1 workspace/1M tokens) / Standard $2.50 per 1M tokens + $5/workspace / Enterprise custom
Best-forRecord-level, re-executable proofGraph/ontology-centered memory pipelines

Competitor pricing verified 2026-08-07 against Cognee's primary pricing documentation; other Cognee facts verified 2026-07-15. “Not evaluated in public docs” = not found in Cognee's primary documentation on the date checked; it is not a claim the feature is absent. Each date is a point-in-time snapshot, not a continuing assurance.

Comparison by dimension

Governance

Cognee governs at the dataset level with access controls and telemetry, and it leads on the knowledge-graph and ontology model. Heartwood governs at the record level: per-memory signatures, policy-before-ranking, and crypto-shred erasure. If cognee is further along on graph depth, Heartwood's lane is record-level proof.

Deletion

Cognee deletion removes graph, vector, and relational data (with raw-file/shared-node caveats); Heartwood adds a per-subject key-destruction receipt.

Who Cognee is best for

Teams building graph/ontology-centered memory pipelines with OSS or managed deployment.

Who Heartwood is best for

Regulated teams that need per-record, re-executable proof.

Can Heartwood run underneath Cognee?

As the governed store behind shape-compatible memory calls (example contract, not an official integration).

See the governed-memory model

FAQ

Does Cognee have access control?

Yes — tenant roles plus direct dataset-level read/write/delete grants. Heartwood's difference is per-record, re-executable proof.

Is Cognee open source?

Cognee's engine is Apache-2.0; hosted Cloud and Enterprise are separate.