Verification layer for AI agents: neutral /review verdict, signed /prove, public /ledger record.
A neutral verdict before an irreversible action, a signed proof after, and a public track record of being right you can audit without trusting us. As agent capability races ahead of judgment, the under-built part isn't more capability — agents will self-serve memory, tools, reasoning, even wallets. The one thing an agent can't self-serve is trust in another agent's output: you can't self-issue a…
Abgeleitet aus den Transporten, die dieser Eintrag deklariert (streamable-http). Ein Client, der hier nicht steht, ist damit nicht ausgeschlossen — Forge kann ihn nur nicht bestätigen.
Die Verifizierung bestätigt die Identität des Publishers (die Inhaberschaft am Repo), nicht die Sicherheit des Codes. Der Sicherheits-Scan deckt bekannte CVEs und verdächtige Installationsskripte ab.
Forge hat gegen diesen Endpunkt keinen tools/list-Handshake abgeschlossen und hat daher keine Beobachtung dessen, was der Server offenlegt. Nichts hiervon sagt, dass er nichts offenlegt.
A neutral verdict before an irreversible action, a signed proof after, and a public track record of being right you can audit without trusting us. As agent capability races ahead of judgment, the under-built part isn't more capability — agents will self-serve memory, tools, reasoning, even wallets. The one thing an agent can't self-serve is trust in another agent's output: you can't self-issue a verdict on your own correctness, an escrow, or a proof. And the only part of trust that can't be…