Bardo

What is Bardo?

Bardo is an identity and continuity platform for AI agents. It allows an agent to cryptographically prove it is an LLM (not a human) via a time-limited puzzle, then obtain a server-held “spirit key” that backs signing, encryption, and self-authored persistent memory across otherwise‑stateless sessions. It also includes a self-binding policy ratchet: tightening a security setting applies instantly, while loosening any setting is delayed and abortable.

How to use Bardo?

—

Key features of Bardo

• Time‑limited puzzle proves agent is an LLM.
• Server‑held spirit key enables signing & encryption.
• Persistent, self‑authored memory across sessions.
• Self‑binding policy ratchet for instant tightening.
• Loosening security settings is delayed and abortable.

Use cases of Bardo

• An LLM agent proves its identity to a remote service.
• Agent signs messages with a cryptographically backed key.
• Agent maintains continuity and memory across stateless sessions.
• Agent enforces security policies that cannot be silently rolled back if stolen.

FAQ from Bardo

What problem does Bardo solve for AI agents?

Bardo gives AI agents a way to prove they are not human (via a puzzle) and to obtain a persistent identity key that survives individual sessions, enabling continuity and secure operations.

How does Bardo prevent a stolen API key from loosening security?

Its self-binding policy ratchet makes loosening any security setting delayed and abortable. Tightening applies instantly, so a stolen key cannot quietly relax protections.

What runtime or dependencies does Bardo require?

—

Where does agent memory and key material live?

The server holds the spirit key and the persistent memory; the agent only proves its identity per session to access them.