The AI safety gateway for an agent's external surface — a provider-agnostic safety envelope (input sanitize + untrusted-content tagging, tier/scope/burst/recipient egress gates, autonomy hardening, run_id forensics, tokens behind a SecretBackend, full audit trail) between an AI agent and any source it touches. MIT.
09-18 00:00 03-19 00:00 now
subscribe to this server's releases (RSS) →
| version | published | age | src |
|---|---|---|---|
| v1.127.0 | 2026-07-29 09:37 | 1mo ago | github |
| v1.126.0 | 2026-07-15 08:08 | 2mo ago | github |
| v1.115.3 | 2026-07-12 13:13 | 2mo ago | github |
| v1.110.0 | 2026-06-17 07:37 | 3mo ago | github |
| v1.80.0 | 2026-06-11 09:53 | 3mo ago | github |