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.
Trending = 10+ GitHub stars.
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 | depguardFounding | Code Generation | 81.7Estimated from documentation | 15 | 3 | 🟢 Active | 87.0 | 74.0 | 83.0 | 84.0 |
| 2 | attestorFounding | Code Generation | 77.2Estimated from documentation | 14 | 1 | 🟡 Stale | 80.0 | 68.0 | 75.0 | 84.0 |
| 3 | memorywebFounding | Code Generation | 76.1Estimated from documentation | 14 | 3 | 🟢 Active | 76.0 | 68.0 | 83.0 | 77.0 |
| 4 | Axme-codeFounding | Code Generation | 75.0Estimated from documentation | 14 | 1 | 🟡 Stale | 78.0 | 68.0 | 80.0 | 75.0 |
| 5 | ControlKeelFounding | Code Generation | 73.3Estimated from documentation | 10 | 8 | 🟢 Active | 74.0 | 70.0 | 78.0 | 72.0 |
| 6 | SharkMCPFounding | Code Generation | 72.0Estimated from documentation | 76 | 1 | 🔴 Dormant | 82.0 | 70.0 | 78.0 | 65.0 |
| 7 | ai-memoryFounding | Code Generation | 69.8Estimated from documentation | 43 | 2 | 🔴 Dormant | 72.0 | 58.0 | 80.0 | 70.0 |