AIPass vs Concordia
AIPass leads on trust: 85.5/100 (Grade A) against 66.7/100 (Grade B), a 18.8-point gap. AIPass leads on supply-chain integrity and provenance; Concordia leads on adoption.
Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.
Choose AIPass if supply-chain integrity and provenance matter most.
- +11.6Safety / Integrity: 100% of recent commits signed, against 5%
- +7.2Identity / Provenance: package provenance attested, against none
- +1.9Maintenance: last push today, against 1d ago
A library for generative social simulation
Choose Concordia if adoption matters most.
- +2.5Adoption: 627 weekly downloads against 224
Where they differ
An independent, evidence-based trust comparison of AIPass and Concordia, two Multi-Agent Systems projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | AIPassAIOSAI/AIPass | Concordiagoogle-deepmind/concordia |
|---|---|---|
| HVTrust score | 85.5 | 66.7 |
| Evidence grade | A | B |
| Coverage grade | B | B |
| Overall rank | #86 | #449 |
| Rank in Multi-Agent Systems | #1 | #6 |
| GitHub stars | 288 | 1.8k |
| Last updated | today | 1d ago |
| Build provenance | Yes | No |
| OSSF Scorecard | 7.3 / 10 | 7.8 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | 224/wk | 627/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 21.6 | 10.0 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 14.7 | 15.1 |
| Maintenance / 20 | 20.0 | 18.1 |
| Adoption / 20 | 9.0 | 11.5 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Declared |
| External providers | 2 — Anthropic, OpenAI | 6 — Amazon Bedrock, Anthropic, Google Gemini, … |
| Requires API keys | No | No |
| 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 →