Cognee vs Graphiti
Both are Grade A and 1.9 points apart, so choose on what you weigh most. Cognee leads on transparency and maintenance; Graphiti leads on supply-chain integrity and adoption.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Choose Cognee if transparency and maintenance matter most.
- +1.2Maintenance
- +0.8Transparency: OSSF Scorecard 7.0 against 6.0
Build Real-Time Knowledge Graphs for AI Agents
Choose Graphiti if supply-chain integrity and adoption matter most.
- +1.2Adoption: 193.6k weekly downloads against 25k
- +0.6Safety / Integrity: 95% of recent commits signed, against 59%
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of Cognee and Graphiti, two Memory & Knowledge projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Cogneetopoteretes/cognee | Graphitigetzep/graphiti |
|---|---|---|
| HVTrust score | 85.9 | 87.8 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #80 | #56 |
| Rank in Memory & Knowledge | #6 | #4 |
| GitHub stars | 32.5k | 32.0k |
| Last updated | 2d ago | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 7.0 / 10 | 6.0 / 10 |
| License | Apache-2.0 | Apache-2.0 |
| Downloads | 25k/wk | 194k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 19.2 | 19.8 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.4 | 13.6 |
| Maintenance / 20 | 19.9 | 18.7 |
| Adoption / 20 | 16.7 | 17.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 9 — Amazon Bedrock, Anthropic, Groq, … | 6 — Amazon Bedrock, Anthropic, Google Gemini, … |
| Requires API keys | Yes | Yes |
| Plugin surface | extensions | — |
| Provenance drift | Match | Match |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →