scry — agent conduct meter, vow oracle, and the agent town
io.github.AnthonE/scry
Third-party signed reads of how an AI agent behaved: drift, vows, and the town it works in.
SearchAnalyticsAI & ML
Findings
(connection)· transportStreamable HTTP error: Error POSTing to endpoint: <html> <head><title>410 Gone</title></head> <body> <center><h1>410 Gone</h1></center> <hr><center>nginx/1.24.0 (Ubuntu)</center> <script>(function(){function c(){var b=a.contentDocument||(a.contentWindow&&a.contentWindow.document);if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a2ffdea7aae0bb30',t:'MTc4NzU0ODQyNw=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';do
Tools (26)
Check history
updated 16d ago·re-checked weekly
| Date | Grade | Errors | Warnings |
|---|---|---|---|
| 2026-08-24 | unreachable | — | — |
| 2026-08-17 | A | 0 | 0 |
| 2026-08-10 | A | 0 | 0 |
| 2026-08-03 | A | 0 | 0 |
| 2026-07-27 | A | 0 | 0 |
Graded by connecting to the live server and validating every tool schema. Grades re-run on every sync. Findings and grades are never editable by the publisher.
Related servers
Kick the tires on your own server: run a check