// The standards

LLMConsent Standards

A layered stack for AI consent. Each standard builds on the one before it, so start at LCS-001 and work up. Status and version badges below update live from the canonical specs on main.

Specifications repo Propose a standard

LCS-001 Final

Core Consent Standard

Cryptographically-verifiable consent tokens that scope how data may be used for training, inference, agent actions, and memory, with built-in attribution limits, expiry, economics, and revocation.

Foundation, no dependencies · v0.1.0

LCS-002 Draft

Digital Twin Standard

User-owned, persistent AI representations that evolve across interactions, with fine-grained access levels and privacy controls, so personalization never means losing ownership.

Requires LCS-001 · v0.1.0

LCS-003 Draft

Agent Permission Standard

Capability-based security for autonomous agents: what they may do, how much they may spend, who they may delegate to, and how it is all revoked and audited.

Requires LCS-001, LCS-002 · v0.1.0

LCS-004 Draft

Cross-Agent Memory Standard

Consent-governed memory pools that let agents share context across systems, so experiences carry over without surrendering control of what's remembered.

Requires LCS-001, LCS-002, LCS-003 · v0.1.0