jurniti

Docker shares one Linux kernel across every tenant. A bug in your neighbour's container can become your problem. Firecracker spins up a real KVM-backed virtual machine per tenant with hardware-enforced isolation — the same primitive AWS uses for Lambda.

Your OpenRouter / OpenAI / Anthropic key lives only inside your VM. We never see it, never proxy, never mark up your spend. You pay your model provider direct.

Cancel your first plan within 30 days for a full refund, no questions asked. The guarantee covers your first subscription and ends once you expand. After that, cancel anytime — your VM keeps running to the end of the period you've paid for, then simply doesn't renew.

AWS us-west-2 today, on EC2 nested-virtualization hosts — one Firecracker microVM per tenant. Additional regions land when committed regional MRR clears the cost of a second box.

Yes — each gets its own Firecracker microVM and its own subscription. So Hermes + OpenClaw + Pi at Starter is 3 × $25 = $75/mo. We deliberately don't bundle multiple harnesses inside one VM: it would break the per-tenant hardware-isolation boundary and starve resources at the Starter tier. Pricing is per-VM, so every agent you add is billed at its plan's rate — and annual prepay gives you 2 months free on each.

Yes — that's the swarm runtime. jurniti up --tier spot --harness hermes --count 50 --group demo boots fifty isolated microVM workers; jurniti run --group demo --model --provider openrouter " " dispatches the same brief to every worker (swarm slices carry no default model — you pick one per run, BYOK); jurniti cp --group demo work/out.txt ./out collects every result. Raise --count as your fleet grows — size is gated by your prepaid usage credits, not a plan cap, and workers bill by the second, so a stopped worker burns nothing.

Stripe confirms, you get a magic-link sign-in, and the auto-provisioner boots your microVM — live in about three minutes, no human in the loop. Paste your model key from the quickstart and your agent is answering a couple of minutes after that.

Optional sidecars alongside your agents — same Firecracker isolation, not shared multi-tenant SaaS. Memory engines (Obsidian, gbrain, mem0) hold long-term knowledge you grant over MCP. Observability engines (Latitude, Langfuse) keep sessions and tool-call traces in your microVM. Communication covers AI agent communication on the same attach model: Buzz is a self-hosted messaging relay (Open Buzz / Connect desktop for humans; grant agents into rooms), and Herdr is an always-on multi-agent terminal runtime you open in the browser. None of these stacks is baked into every agent rootfs; you attach what you need.

Fair question — jurniti is small and new, and you shouldn't have to take our word for anything. That's why the trust story is structural, not contractual. Your model keys live inside your own microVM and never traverse our network, so we couldn't read them if we wanted to. The isolation boundary is the same KVM hardware line AWS runs Lambda on — a real virtual machine per tenant, not a shared kernel. Your agent's state is yours to take: fork it into a template, or move it out with one CLI command. And if we're not worth it, the 30-day money-back guarantee returns every dollar of your first subscription — refunds are processed within one business day.

Starter is $25/month or $250/year (2 months free). Pro is $49/month or $490/year. Max is $99/month or $990/year. Every plan is a flat fee per VM with no token markup, no metered surprises, and a 30-day money-back guarantee.