Pricing
One list. Priced per governed agent.
Every tier includes the full policy engine, hash-chained audit trail, and every enforcement surface — MCP, proxy, and CLI hook. You pay for how many agent identities you govern, not which features you unlock.
Free
Up to 3 agents
For individual devs, POCs, and internal tinkering.
- ·Full policy engine — allow, block, approve, prove
- ·Hash-chained audit trail
- ·MCP + proxy + CLI hook enforcement
- ·Community support (GitHub Discussions)
Team
Up to 25 agents
For engineering teams governing their first fleet of agents.
- ·Everything in Free
- ·Slack + email approval fanout
- ·Signed evidence exports
- ·Slack + email support (business hours)
- ·SSO (Google, Microsoft, Okta)
Business
25–100 agents
Volume pricing for orgs standardising governance across many agents.
- ·Everything in Team
- ·Priority support (24h response)
- ·Custom policy pack authoring
- ·Role-based access control (RBAC)
- ·Compliance evidence templates (SOC2, ISO, HIPAA)
Enterprise
100+ agents · Self-hosted · Air-gapped
For regulated industries, self-host, and design-partner engagements.
- ·Everything in Business
- ·Self-hosted deployment (Docker, Kubernetes, air-gapped)
- ·Signed SLA + dedicated success engineer
- ·Custom policy development
- ·Procurement, security review, and MSA support
Self-hosted? Same list price. Same features.
Self-hosted deployments (Docker, Kubernetes, air-gapped) are available on Enterprise. The list price is the same — you're paying for policy enforcement, audit, and support, not for where the pods run. Deploy where your compliance boundary needs it, keep the same commercial terms.
One engine — every surface
MCP tool interception, LLM proxy, and CLI hooks all run through the same policy engine and write to the same audit chain.
One agent identity
Every governed agent gets a cond_agt_* identity with RBAC, TTL, rate + spend caps. That identity is the unit you pay for.
Bring your own LLM
100+ providers — Anthropic, OpenAI, Bedrock, Azure, Ollama, self-host — through one gateway. No provider markup.
Answers to the five questions every buyer asks.
Direct answers so you don't need a sales call to scope the deal. If your situation doesn't fit one of these, reach out and we'll answer the same way.
Is cond_agt_* priced per user or per bot?
Per bot — per governed service identity. One human developer running three governed agents counts as three identities. The unit tracks value produced by the agents, not headcount using the tool.
Does self-hosted include air-gapped deployments?
Yes, on Enterprise. Docker, Kubernetes, and fully air-gapped installs all deploy from the same image and run the same policy engine. Same list price as SaaS — you’re paying for enforcement and audit, not where the pods run.
What if my agent count varies month to month?
Billed on the peak count of active identities in each month. Spin agents up for a launch, retire them after, and you only pay for the month you actually ran them. No proration penalty for scaling down.
Do you offer annual discounts?
Yes — 15% off list price on all tiers when paid annually up front. Available on Team, Business, and Enterprise. Ask for the annual quote when you talk to us.
What happens if I hit my tier cap?
Soft alert at 90% of cap so you can plan the upgrade. If you hit 100%, agents keep working — we auto-upgrade you to the next tier and send a confirmation email. No hard stops, no surprise blocks, no missed enforcement.
Not sure which tier fits?
Start on Free — govern up to 3 agents in an afternoon. Upgrade when your fleet grows, or talk to us about design-partner terms if you're deploying at scale early.