AI Town vs Eve
Eve leads on trust: 67.0/100 (Grade B) against 43.9/100 (Grade D), a 23.1-point gap. AI Town leads on adoption; Eve leads on supply-chain integrity and maintenance.
A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.
Choose AI Town if adoption matters most.
- +0.7Adoption: 10.7k GitHub stars against 5.8k
The Open Framework for Building Agents
Choose Eve if supply-chain integrity and maintenance matter most.
- +12.5Maintenance: last push 1d ago, against 69d ago
- +6.2Safety / Integrity: 100% of recent commits signed, against 27%
- +1.7Transparency: OSSF Scorecard 5.9 against 3.9
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of AI Town and Eve, two Needs review projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | AI Towna16z-infra/ai-town | Evevercel/eve |
|---|---|---|
| HVTrust score | 43.9 | 67.0 |
| Evidence grade | D | B |
| Coverage grade | C | C |
| Overall rank | #1143 | #455 |
| Rank in Needs review | #8 | #1 |
| GitHub stars | 10.7k | 5.8k |
| Last updated | 69d ago | 1d ago |
| Build provenance | No | No |
| OSSF Scorecard | 3.9 / 10 | 5.9 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 6.2 | 12.4 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 11.8 | 13.5 |
| Maintenance / 20 | 7.4 | 19.9 |
| Adoption / 20 | 9.7 | 9.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 3 — OpenAI, Replicate, Together AI | — |
| Requires API keys | Yes | No |
| Plugin surface | — | extensions |
| 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 →