For engineers building agent systems and leadership deploying them responsibly.

Governance Beneath Orchestration

Protocols, not prompts.

DaemonCore sits below your orchestration layer. It doesn't coordinate agents—it defines what they're allowed to do, enforces boundaries structurally, and ensures outputs follow protocol before any action occurs.

The layer that makes AI behaviour enforceable instead of advisory.

The Evolution of AI Control

Raw Prompts Hope for the best
Better Prompts More detailed instructions
Prompt Engineering Systematic instruction design
Orchestration Frameworks coordinate agents
Governance Protocol-enforced boundaries

Where Risk Appears

Orchestration coordinates. But coordination without governance creates gaps.

Drift

Agents interpret instructions differently over time. Without structural constraints, behaviour shifts unpredictably.

Ambiguity

Natural language instructions leave room for interpretation. Edge cases become judgment calls the model makes alone.

Responsibility

When something goes wrong, who's accountable? Prompt-based systems make audit and attribution difficult.

From Instructions to Protocols

DaemonCore doesn't give agents better instructions—it changes what counts as valid output. Agents produce protocol-shaped responses. Those responses are classified and validated before any action occurs. The shift isn't "tell the model to be careful." It's "only protocol-compliant outputs are eligible for execution."

How It Works

Concrete mechanisms, not abstract principles.

Action Protocol

Only protocol-shaped outputs are eligible for action.

Agent output → Protocol validation → Classification → Action (or rejection)

MAX Messaging Bus

Typed, schema-validated message routing between agents and systems.

Messages carry type, sender, recipient, payload schema. Malformed messages rejected.

Template-Driven Operations

Complex operations follow predefined templates with explicit boundaries.

Code review template defines: scope, checklist, output format, approval gates.

What We Promise (and When)

V1 (Current)

  • Protocol-shaped output validation
  • Message schema enforcement
  • Template-constrained operations
  • Deterministic boot sequences
  • Audit trail for agent actions

V1.5 (Planned)

  • Cryptographic action signing
  • Hardware-backed attestation
  • Cross-agent capability delegation
  • Real-time constraint verification

We ship what's working. V1.5 features are in development—we'll announce them when they're ready.

Get Started

From technical mechanisms to organisational outcomes—explore what matters to you.

Status

Kernel V1 specification stable. Protocol validation and MAX bus operational. Public documentation available for review.

View on GitHub