# Cognee vs Memary

**Leader by Vioscale score:** Cognee

| Attribute | Cognee | Memary |
|---|---|---|
| **Vioscale score** | 83 (37% (low)) | 58 (27% (low)) |
| adoption.dependent_repos | - | 0 |
| adoption.github_stars | - | 2,641 |
| deployment.options | `{"cloud":true,"on_prem":true,"air_gapped":true,"self_hosted":true}` | `{"self_hosted":true}` |
| description.long | Cognee is a graph-based memory engine for AI agents that captures information, organizes it as interconnected knowledge, and enables agents to recall context across conversations. It runs locally, on managed cloud infrastructure, or on-premises with full control over data. | A memory layer for autonomous agents built on knowledge graphs. It tracks entities, relationships, and events with timestamps, supports multi-agent setups with isolated memory contexts, and integrates with LangChain and LlamaIndex to help agents evolve their knowledge through interactions. |
| features.capabilities | `{"soc2_type_ii":false,"architecture_model":"open_source_self_hosted","mit_or_apache_permissive_oss_license":true,"multi_tenant_user_and_agent_isolation":true,"time_decay_and_recency_weighted_retrieval":true,"graph_based_entity_relationship_extraction":true,"zero_data_retention_and_pii_redaction_layer":false,"memory_conflict_resolution_and_fact_updating":true,"automatic_context_window_rolling_summarization":true,"native_langchain_and_llamaindex_memory_classes":false,"cross_session_and_multi_thread_user_persistence":true,"semantic_vs_episodic_event_chronological_memory":true}` | `{"pricing_model":"free_open_source","architecture_model":"open_source_self_hosted","multi_tenant_user_and_agent_isolation":true,"graph_based_entity_relationship_extraction":true,"native_langchain_and_llamaindex_memory_classes":true,"cross_session_and_multi_thread_user_persistence":true,"semantic_vs_episodic_event_chronological_memory":true}` |
| integrations.count | 27 | 3 |
| integrations.list | `[{"name":"Claude Code"},{"name":"Cursor"},{"name":"Codex"},{"name":"LangGraph"},{"name":"OpenClaw"},{"name":"CrewAI"},{"name":"n8n"},{"name":"Slack"},{"name":"Notion"},{"name":"Google Drive"},{"name":"Amazon Neptune"},{"name":"Weaviate"},{"name":"Qdrant"},{"name":"Pinecone"},{"name":"Redis"},{"name":"Azure AI Search"},{"name":"Milvus"},{"name":"OpenSearch"},{"name":"Valkey"},{"name":"Memgraph"},{"name":"NetworkX"},{"name":"Google Cloud Spanner"},{"name":"TuringDB"},{"name":"pgGraph"},{"name":"DuckDB"},{"name":"FalkorDB"},{"name":"ScrapeGraphAI"}]` | `[{"name":"FalkorDB"},{"name":"LangChain"},{"name":"LlamaIndex"}]` |
| language.primary | - | Jupyter Notebook |
| license.spdx | - | MIT |
| market.availability | `{"hqCountry":"DE","primaryMarkets":["EU","US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | - |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"hybrid","plans":[{"free":true,"name":"Free","summary":"Free, forever","features":["Graph-based memory","SDK and MCP access","Agentic integrations (Claude Code, Cursor, Codex)","Unlimited users and API calls"],"components":[{"kind":"fixed","amount":0,"period":"month","currency":"USD"}],"description":"Self-hosted open-source deployment","contactSales":false,"includedLimits":{"users":"unlimited","api_calls":"unlimited","workspaces":"1","tokens_monthly":"1M"}},{"free":false,"name":"Standard","summary":"$5 per workspace/month","features":["Unlimited workspaces","Data integrations: Slack, Notion, Google Drive","In-app support"],"commitment":"monthly","components":[{"kind":"per_unit","unit":"workspace","amount":5,"period":"month","currency":"USD"}],"description":"Managed cloud with data integrations","contactSales":false,"includedLimits":{"workspaces":"unlimited"}},{"free":false,"name":"Premium","summary":"Custom pricing with enterprise support","features":["Dedicated Slack channel","Dedicated support engineer","Bring-your-own cloud support","Support SLA"],"commitment":"monthly","components":[{"kind":"per_unit","unit":"workspace","amount":5,"period":"month","currency":"USD"}],"description":"Enterprise deployment with dedicated support","contactSales":false}],"summary":"Free tier (1M tokens/mo). Standard from $5/workspace/mo. Enterprise custom pricing.","currency":"USD","freeTier":true,"sourceUrl":"https://www.cognee.ai/pricing","retrievedAt":"2026-08-21T11:08:22.660Z","startingPrice":{"unit":"workspace","amount":5,"period":"month","currency":"USD"},"billingPeriods":["month"]}` | `{"type":"open_source","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-08-21T11:06:33.797Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | freemium |
| pricing.price_level | low | free |
| pricing.starting_price | `{"amount":5,"currency":"USD"}` | - |
| pricing.transparent | yes | yes |
| release.cadence_days | - | 11 |
| release.history | - | `[{"url":"https://github.com/kingjulio8238/Memary/releases/tag/v0.1.5","date":"2024-10-22T00:46:00Z","type":"stable","version":"v0.1.5"},{"url":"https://github.com/kingjulio8238/Memary/releases/tag/v0.1.4","date":"2024-09-09T19:15:36Z","type":"stable","version":"v0.1.4"},{"url":"https://github.com/kingjulio8238/Memary/releases/tag/v0.1.3","date":"2024-05-27T21:27:37Z","type":"stable","version":"v0.1.3"},{"url":"https://github.com/kingjulio8238/Memary/releases/tag/v0.1.2","date":"2024-05-21T05:33:23Z","type":"stable","version":"v0.1.2"},{"url":"https://github.com/kingjulio8238/Memary/releases/tag/v0.1.1","date":"2024-05-09T23:52:34Z","type":"stable","version":"v0.1.1"},{"url":"https://github.com/kingjulio8238/Memary/releases/tag/v0.1.0","date":"2024-05-02T13:20:10Z","type":"stable","version":"v0.1.0"}]` |
| security.gdpr | yes | - |
| security.vulnerabilities | - | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=memary&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (Agent Memory)

| Capability | Cognee | Memary |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Architecture model | Open source self hosted | Open source self hosted |
| Graph based entity relationship extraction | ✓ | ✓ |
| Automatic context window rolling summarization | ✓ | - |
| Semantic vs episodic event chronological memory | ✓ | ✓ |
| Cross session and multi thread user persistence | ✓ | ✓ |
| Memory conflict resolution and fact updating | ✓ | - |
| Multi tenant user and agent isolation | ✓ | ✓ |
| Native langchain and llamaindex memory classes | ✗ | ✓ |
| Time decay and recency weighted retrieval | ✓ | - |
| Zero data retention and pii redaction layer | ✗ | - |
| SOC2 type ii | ✗ | - |
| Mit or apache permissive oss license | ✓ | - |
| Pricing model | - | Free open source |

*Source: Vioscale. Generated 2026-09-01T16:44:31.691Z. "-" = undocumented, not absent.*