What is Ajar
Ajar is an owner-controlled protocol layer over HTTPS for agent-readable content, typed actions, delegated authority, receipts, and metering.
Ajar opens websites to AI agents under owner-controlled policy. It gives a site a signed Capability Manifest, semantic Views, typed Actions, Mandates, Receipts, and 402-native metering without replacing HTML, checkout systems, payment rails, MCP, or agent frameworks.
Primitives
| Need | Ajar primitive |
|---|---|
| Meaning | Semantic Views served from the same URLs as HTML |
| Actions | Typed Actions with R0-R3 risk classes |
| Safety | SIMULATE dry runs and two-phase Offer/Commit |
| Authority | Principal-signed Mandates with scope, caps, expiry, and revocation |
| Accountability | Dual-signed Receipts and audit trails |
| Economics | 402-native metering with pluggable settlement |
How it works
- A site owner installs or runs an Ajar Gateway, plugin, or native integration.
- The owner reviews generated Views, Actions, policy, pricing, and gates.
- The owner signs a Capability Manifest at
/.well-known/ajar.json. - An agent Kernel discovers the manifest, verifies signatures, reads Views, simulates actions, checks mandates, commits only when allowed, and stores receipts.
The owner key is the root of authority. Automation drafts; owners decide.
Reading order
Start with the protocol specification if you are implementing. Read architecture for the system walkthrough, security model for threat boundaries, and owner control for policy semantics.
New contributors should begin with onboarding, then the roadmap and build order.