pohi-protocol/pohi
Proof of Human Intent (PoHI) - Cryptographically verifiable human approval for AI-driven development
This helps development teams prove that a real human, not just an AI, approved critical software changes before they are merged or deployed. It takes input from various identity verification services like World ID and combines it with code change information to produce a cryptographically verifiable record of human approval. Software developers, DevOps engineers, and security auditors who oversee AI-driven development workflows would use this.
Use this if you need an undeniable, verifiable record that a human explicitly approved an AI-generated code change or deployment, preventing 'the AI did it' excuses.
Not ideal if your development process does not involve AI agents making critical decisions or if you don't require cryptographic proof of human oversight.
Stars
18
Forks
1
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/pohi-protocol/pohi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
Dicklesworthstone/destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being...
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...
Pro-GenAI/Agent-Action-Guard
🛡️ Safe AI Agents through Action Classifier