Vibe Coding Discover

AI Agents

emilia-protocol

View on GitHub

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

★ 61516 forksTypeScriptApache-2.0emiliaprotocol

EMILIA provides an open protocol and enforcement boundary for consequential agent actions. Gate checks exact-action authority, admits covered provider attempts, and creates verifiable evidence; it is effective only on fully mediated paths with authoritative shared state.

Use Cases

Enforce finite mandates on autonomous agent actionsRequire authorization before consequential tool executionPrevent unauthorized or repeated provider attemptsCapture verifiable receipts for agent actionsGate protected GitHub merges using repository mandatesControl finance workflows such as payment release or bank-detail changesFreeze new agent actions while preserving reconciliation requirements

Built With

Language
TypeScript
Frameworks
Model Context Protocol · smolagents · Next.js · Tamarin

Tags

agent security · authorization · policy enforcement · exact-action control · human authorization · audit evidence · cryptographic receipts · consequence firewall · MCP security · formal verification · zero trust