LBE – open-source execution control layer for AI agents Letterblack released LBE, an open-source execution control layer for AI agents that validates every action locally before execution, enforcing policy gates without cloud dependencies. The tool, already used in production for Letterblack for After Effects, provides a 7-gate pipeline for schema, timestamp, key lifecycle, signature, rate limit, nonce, and policy checks, with observer and enforce modes. LBE puts a local policy gate between what an AI agent proposes and what the system actually executes. Every action — file write, shell command, anything — is validated locally before it runs. No cloud service. No daemon. Used in production:LBE is the safety engine inside Letterblack for After Effects — every AI-generated script and automation command passes through it before touching a live project. | I want… | Package | |---|---| | LBE to handle file writes and shell commands for me full controller | @letterblack/lbe-exec | | Just the allow/deny decision — I'll execute it myself | @letterblack/lbe-sdk ← you are here | npm install @letterblack/lbe-sdk Requires Node.js ≥ 20.9.0. js import { execute } from '@letterblack/lbe-sdk'; const request = { version: '1.0', request id: 'req-001', timestamp: Math.floor Date.now / 1000 , actor: { id: 'agent:local', role: 'agent' }, intent: { type: 'command', name: 'write file', payload: { target: 'out.txt' } }, context: { workspace: process.cwd , env: {}, history: }, constraints: { policy mode: 'strict', timeout ms: 5000 }, auth: { signature: '