Scores are desk assessments of published materials; security scans are shown separately, and no score here uses production telemetry. Each row carries the evidence class behind its number.
Last update: 19 October 2026. Scores are re-assessed every week against each agent's public materials; changes of more than 5 points are checked by a person before they publish. We are not adding new agents right now.
Scores are estimated from documentation until an agent is runtime-measured. Methodology v2.6.0 rev 1.27.
Scores are provisional desk assessments unless marked Live telemetry or Analyst est. Why →
| # | Agent | Category | Score | ⭐ Stars | 👥 Contrib. | Activity | Success | Latency | Cost | Reliability |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | stata-mcpFounding | Multi-Step Reasoning | 69.2Estimated from documentation | 7 | 1 | 🟡 Stale | 74.0 | 62.0 | 78.0 | 66.0 |
| 2 | vision-mcpFounding | Multi-Step Reasoning | 65.4Estimated from documentation | 0 | 1 | 🔴 Dormant | 68.0 | 60.0 | 88.0 | 52.0 |