Starter
25
named agents in the registry
$29 / month
30-day trail · 5 console seats
Get started
Pricing
How many agents may act
You pay for how many named software agents sit in the registry, and how long the trail is kept. Console seats are humans who sign in. Pick a plan, then read the table under it.
Pro
250
named agents in the registry
$149 / month
90-day trail · export · 25 console seats
Get startedScale
∞
named agents in the registry
$499 / month
1-year trail · SSO · unlimited seats
Get startedPlan details
| Feature | Starter · $29/mo | Pro · $149/mo | Scale · $499/mo |
|---|---|---|---|
| Identity & registry | |||
|
Named agents in the registry
Distinct software identities (ACTIVE or SUSPENDED) at one time.
Kill or revoke frees the slot. A concurrent registry cap, not a usage quota.
|
25 at a time | 250 at a time | Unlimited |
| Agent registry (register, list, status) | Yes | Yes | Yes |
| Agent passport (HTML + JSON download) | Yes | Yes | Yes |
| Policy-gated spawn (agent creates agent) | Yes | Yes | Yes |
| Human mint mode (allow / break-glass / approve) | Yes | Yes | Yes |
| Session clearance (Read / Build / Deploy) | Yes | Yes | Yes |
| HIGH-risk shrink mode (operator / auto / approve) | Yes | Yes | Yes |
| Signed agent passport + session claim | Yes | Yes | Yes |
| Verify claim API | No | Yes | Yes |
| Orphan / parent-tree report | No | Yes | Yes |
| Version hash on register (prompt + tools + policy) | Yes | Yes | Yes |
| Kill / revoke agent | Yes | Yes | Yes |
| Policy & human approval | |||
| Runtime policy: ALLOW / DENY / REQUIRE_APPROVE | Yes | Yes | Yes |
| Fail-closed defaults (missing approval → deny) | Yes | Yes | Yes |
| Policy playground (console evaluate) | Yes | Yes | Yes |
| Policy evaluate API (MCP / OpenAPI / HTTP) | Yes | Yes | Yes |
| Approvals queue (approve / reject) | Yes | Yes | Yes |
| Approval priority queue | No | Yes | Yes |
| PII redaction before model calls | Yes | Yes | Yes |
| Observe, evidence & trail | |||
| Session ingest + session list | Yes | Yes | Yes |
| Session timeline (tools, risk, raw payload) | Yes | Yes | Yes |
| Session risk only raises severity (never auto-allows) | Yes | Yes | Yes |
| Evidence & cases | Yes | Yes | Yes |
| Hash-chained event / audit trail | Yes | Yes | Yes |
| Audit trail retention | 30 days | 90 days | 1 year (custom on request) |
| CSV / export of trail and cases | No | Yes | Yes |
| Evidence graph dual-write (audit module) | No | No | Yes |
| KYA metrics (console) | Yes | Yes | Yes |
| KYA metrics JSON API | No | Yes | Yes |
| Edge & complements | |||
| Edge status page (Gatekeeper complement flags) | Yes | Yes | Yes |
| Shield Agent Gatekeeper (edge after Shield approves) | No | Optional | Included / assisted |
| Connectors & install | |||
| Marketplace install (Claude, ChatGPT, Grok, Gemini, AWS, Azure, GCP) | Yes | Yes | Yes |
| MCP connector surface | Yes | Yes | Yes |
| OpenAPI / GPT Actions surface | Yes | Yes | Yes |
| Install agents hub in console | Yes | Yes | Yes |
| Console, tenant & access | |||
| Hosted operator console (dashboard + all KYA pages) | Yes | Yes | Yes |
| Tutorial mode + welcome tour | Yes | Yes | Yes |
| Tenant isolation | Yes | Yes | Yes |
|
Console seats
Humans who sign in to approve and operate. Not company headcount.
|
5 | 25 | Unlimited |
| Roles: OWNER / ADMIN / OPERATOR / READ_ONLY | Yes | Yes | Yes |
| API keys (machine access) | 1 | 10 | Unlimited |
| SSO / SAML login | No | No | Yes |
| Profile, security, billing settings | Yes | Yes | Yes |
| Support & onboarding | |||
| Email support | Standard | Priority | Priority |
| Slack or dedicated channel | No | No | Yes |
| Guided setup / onboarding help | No | No | Yes |
| Local free for development (self-host, see repo docs) | Included for every plan. No seat charge on local-only runs | ||
Prefer to try first? Create a free console account or sign in. Local development stays free (see repo docs). Marketplace install is on every plan. Install hub.