HN Showcase
Back to browse
GitHub Repository

Trust infrastructure for AI agents. Enforces constitution-as-code constraints during execution — halts on violation, escalates risky actions, generates Ed25519-signed cryptographic receipts. MCP gateway proxy with authority boundaries, approval workflows, circuit breakers, drift analytics, and offline verification. No vendor lock-in.

1 starsPython

Sanna – Enforce AI agent constitutions with cryptographic receipts

by nicallen·Feb 19, 2026·1 point·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainNiche Gem
The Take

Governance rules live in version-controlled YAML and can be applied either by decorating functions with @sanna_observe or by dropping a gateway between an MCP client and downstream tools. It emits portable Ed25519-signed receipts you can persist and verify, which is a neat, practical way to build an auditable trail — the tough part will be ecosystem adoption around MCP and agent integrations.

Category
Security
Target Audience

AI/agent developers, platform engineers, and security/governance teams

Similar Projects

Developer Tools●●Solid

Core – Constitutional governance runtime for AI coding agents

Constitutional enforcement blocks AI agent violations at runtime, but unclear if practical for most teams.

Big BrainBold Bet
DNewecki
123mo ago
Security●●●Banger

I'm 15 and built a cryptographic accountability layer for AI agents

Microsoft merged this teenager's code into their agent governance toolkit twice.

Zero to OneBold BetDark Horse
arian_
421mo ago