Graphiti vs Hindsight
An independent, evidence-based trust comparison of Graphiti and Hindsight, two Memory & Knowledge projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Graphiti leads on trust — 86.0/100 (Grade A) vs 83.4/100 (Grade A), a 2.6-point gap. Note: Graphiti's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types. Full breakdown below.
| Signal | Graphitigetzep/graphiti | Hindsightvectorize-io/hindsight |
|---|---|---|
| HVTrust score | 86.0 | 83.4 |
| Evidence grade | A | A |
| Coverage grade | B | A |
| Overall rank | #44 | #62 |
| Rank in Memory & Knowledge | #4 | #6 |
| GitHub stars | 29.9k | 20.0k |
| Last updated | 2d ago | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 5.1 / 10 | 5.0 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 299k/wk | 17k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 17.9 | 18.4 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 12.8 | 12.8 |
| Maintenance / 20 | 18.8 | 20.0 |
| Adoption / 20 | 18.0 | 16.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | 6 — Amazon Bedrock, Anthropic, Google Gemini, … | 2 — Anthropic, OpenAI |
| Requires API keys | Yes | Yes |
| Plugin surface | — | plugins |
| Provenance drift | Match | Unknown |
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 v4.3 →