Dyad vs Odysseus
Odysseus leads on trust: 70.5/100 (Grade B) against 62.7/100 (Grade C), a 7.8-point gap. Odysseus leads on supply-chain integrity and transparency, and rests on broader evidence.
Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!
Dyad doesn't lead on any scored dimension in this pair.
Self-hosted AI workspace.
Choose Odysseus if supply-chain integrity and transparency matter most.
- +3.7Safety / Integrity: OSSF Scorecard 7.8 against 4.4
- +2.9Transparency: OSSF Scorecard 7.8 against 4.4
- +1.6Adoption: 95.9k GitHub stars against 22.4k
- +0.6Maintenance: last push today, against 1d ago
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Dyad and Odysseus, two UI & App Builders projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Dyaddyad-sh/dyad | Odysseusodysseus-dev/odysseus |
|---|---|---|
| HVTrust score | 62.7 | 70.5 |
| Evidence grade | C | B |
| Coverage grade | C | B |
| Overall rank | #627 | #371 |
| Rank in UI & App Builders | #11 | #7 |
| GitHub stars | 22.4k | 95.9k |
| Last updated | 1d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | 4.4 / 10 | 7.8 / 10 |
| License | NOASSERTION | AGPL-3.0 |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.5 | 14.2 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.2 | 15.1 |
| Maintenance / 20 | 19.4 | 20.0 |
| Adoption / 20 | 10.4 | 12.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | 5 — Anthropic, OpenAI, Postgres, … | 1 — Postgres |
| Requires API keys | No | Yes |
| Plugin surface | plugins | plugins |
| Provenance drift | — | — |
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 →