agent-check
com.basenull/agent-check
Process monitoring for AI agents: start runs, submit per-task evidence, complete runs.
AI & MLProductivity
Findings
(connection)· transport[ { "code": "invalid_union", "errors": [ [ { "code": "invalid_union", "errors": [ [ { "expected": "string", "code": "invalid_type", "path": [], "message": "Invalid input: expected string, received null" } ], [ { "expected": "number", "code": "invalid_type", "path":
Check history
updated 8h ago·re-checked weekly
| Date | Grade | Errors | Warnings |
|---|---|---|---|
| 2026-08-17 | unreachable | — | — |
| 2026-08-10 | unreachable | — | — |
| 2026-08-03 | unreachable | — | — |
| 2026-07-27 | unreachable | — | — |
| 2026-07-20 | unreachable | — | — |
| 2026-07-08 | unreachable | — | — |
| 2026-07-08 | unreachable | — | — |
| 2026-07-06 | unreachable | — | — |
| 2026-07-06 | unreachable | — | — |
| 2026-07-05 | unreachable | — | — |
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.
Kick the tires on your own server: run a check