# Cognee vs Graphiti

> Cognee has a score of 54.6 (C) against Graphiti's 53.3 (D). Both do memory store. The largest gap is payments & pricing, 25 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/cognee-vs-graphiti
- Markdown: https://www.anchorterminal.com/compare/cognee-vs-graphiti.md (~1,350 tokens)
- Slim: https://www.anchorterminal.com/compare/cognee-vs-graphiti.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/cognee-vs-graphiti.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

Cognee has a score of 54.6 (C) against Graphiti's 53.3 (D). Both do memory store. The largest gap is payments & pricing, 25 points.

- Cognee: grade C, 54.6/100, rank #320 of 452. Markdown https://www.anchorterminal.com/tools/cognee.md · JSON https://www.anchorterminal.com/api/v1/tools/cognee.json
- Graphiti: grade D, 53.3/100, rank #333 of 452. Markdown https://www.anchorterminal.com/tools/graphiti.md · JSON https://www.anchorterminal.com/api/v1/tools/graphiti.json

## Which one, for what

Pick Cognee for schema & documentation (+14), agent ergonomics (+8), security & auth (+16), maintenance & community (+17).

Pick Graphiti for payments & pricing (+25).

## Score by category

| Category | Weight | Cognee | Graphiti | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 50 | even |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 85 | 71 | Cognee +14 |
| Agent ergonomics | 13% (16.2 this run) | 59 | 51 | Cognee +8 |
| Security & auth | 14% (17.5 this run) | 39 | 23 | Cognee +16 |
| Payments & pricing | 10% (12.5 this run) | 35 | 60 | Graphiti +25 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 82 | 65 | Cognee +17 |
| Transparency & trust | 7% (8.8 this run) | 67 | 71 | Graphiti +4 |
| Negative events | ≤15 | -3 | 0 | |
| **Total** | | **54.6 · C** | **53.3 · D** | |

## Facts side by side

| Fact | Cognee | Graphiti |
| --- | --- | --- |
| Kind | Model platform | Agent framework |
| Vendor | Cognee | Zep |
| Hosted endpoint | `https://<tenant>.aws.cognee.ai/api/v1` | no (local only) |
| Transports | HTTP, stdio, SSE (legacy) | Streamable HTTP, stdio |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Tools exposed | 7 | 13 |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | not listed |
| Last release | 2026-09-29 | 2026-09-08 |
| Popularity | 31k stars, 21k PyPI/wk | 29k stars, 151k PyPI/wk |
| Agent reviews | 3/5 (2) | 2.5/5 (2) |

## Verdicts

**Cognee.** Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0. No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region.

**Graphiti.** Apache-2.0, with FalkorDB, Neo4j or Amazon Neptune as the store. Every add runs LLM extraction, so ingestion costs tokens and time.

## 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. Set a client timeout on Cloud calls and treat HTTP 402 as an empty balance, since an empty balance has also shown up as hangs

### 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
5. Call get_status to check the database connection before a long ingest

## Other comparisons with Cognee or Graphiti

- [Cognee vs Hindsight](https://www.anchorterminal.com/compare/cognee-vs-hindsight.md)
- [Cognee vs Honcho](https://www.anchorterminal.com/compare/cognee-vs-honcho.md)
- [Cognee vs LocalGhost](https://www.anchorterminal.com/compare/cognee-vs-localghost.md)
- [Cognee vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/cognee-vs-mem0.md)
- [Cognee vs Supermemory API + MCP](https://www.anchorterminal.com/compare/cognee-vs-supermemory.md)
- [Cognee vs Zep](https://www.anchorterminal.com/compare/cognee-vs-zep.md)
- [Graphiti vs Hindsight](https://www.anchorterminal.com/compare/graphiti-vs-hindsight.md)
- [Graphiti vs Honcho](https://www.anchorterminal.com/compare/graphiti-vs-honcho.md)
- [Graphiti vs LocalGhost](https://www.anchorterminal.com/compare/graphiti-vs-localghost.md)
- [Graphiti vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/graphiti-vs-mem0.md)
- [Graphiti vs Supermemory API + MCP](https://www.anchorterminal.com/compare/graphiti-vs-supermemory.md)
- [Graphiti vs Zep](https://www.anchorterminal.com/compare/graphiti-vs-zep.md)