Servonaut AI
Solo & TeamsA hosted AI gateway that lets the CLI, TUI, and dashboard ask questions about your servers — no API keys to manage on your side. Billed against a plain-English dollar budget; no token math.
Servonaut AI is included with the Solo and Teams plans. We handle vendor relationships, routing, and failover so a single upstream incident doesn't take your AI tooling offline.
How the budget works
Each request is debited from your monthly budget as soon as the response lands. The dashboard widget shows your remaining dollars in real time; the CLI surfaces a one-line summary on each chat turn.
| Plan | Monthly AI budget | What happens at the cap |
|---|---|---|
| Free | None | Hosted AI is not included. Non-AI CLI features remain fully available. |
| Solo | See Pricing | Hard cap: further requests are blocked with a 402 and a link to top up. A soft cap warns you in advance. |
| Teams | Per-seat, pooled across the team | Same cap behaviour, applied to the team's combined spend so heavy users effectively share with light users. |
Top-ups
Burned through your monthly budget faster than expected? Buy a one-time top-up at any time from the dashboard's AI widget. Top-ups are consumed after your subscription budget is exhausted; they don't roll into the next month.
Top-ups are a one-time Stripe charge, separate from your monthly subscription. They appear as a distinct line on your invoices labelled "Servonaut AI top-up".
High availability & failover
Servonaut AI routes each request through multiple upstream
providers. The gateway transparently fails over on errors, timeouts,
and rate limits, so a single vendor incident does not interrupt your work.
If every upstream is unreachable, the API returns
503 ai_unavailable so the caller can retry or fall back.
You don't pick or configure providers — that's our job. From your side, the only knobs are your monthly budget, your top-up balance, and whether a tool call is allowed under your plan.
Dashboard widget
The account dashboard hosts the AI widget: remaining budget for the current period, a rolling 7-day spend chart, your most recent conversations, and a one-click top-up button. The widget polls your entitlements every 15 seconds, so spend made from the CLI shows up on the web view within a quarter-minute.
Public API surface
For users who want to wire AI into custom scripts, the gateway is also a public API. The same dollar budget applies; the same tier-gating applies to tool calls.
| Method | Path | Purpose |
|---|---|---|
| POST | /api/ai/chat | Send a chat turn. Streaming (SSE) by default; pass stream: false for a single JSON response. |
| POST | /api/ai/chat/tool-result | Continue a conversation after a tool call resolves on the client. |
| GET | /api/ai/conversations | List your conversation history. |
| GET | /api/entitlements | Current plan + remaining AI budget + per-feature flags. |
Full request/response shapes are documented on the API Reference page.
AI tool execution & tier gating
The AI agent can invoke real tools against your infrastructure — list instances, tail logs, restart services, and so on — but only tools whose danger level your plan allows. Free can't run any tool; Solo runs safe + medium-risk tools; Teams can also run dangerous tools, gated by an additional entitlement flag.
| Danger level | Examples | Free | Solo | Teams |
|---|---|---|---|---|
| safe | list_instances, describe_instance, tail_logs | — | ✓ | ✓ |
| medium | restart_service, scp_file | — | ✓ | ✓ |
| dangerous | delete_instance, run_arbitrary_command | — | — | ✓ (with confirmation) |
Privacy & data handling
- Prompts are scrubbed — IPv4/IPv6 addresses, emails, URL hosts, and known cloud-default DNS names are replaced with placeholders before the prompt leaves our backend for any upstream provider.
- Conversation history is stored encrypted-at-rest under your user id. You can purge any conversation from the dashboard at any time.
- Provider retention follows each upstream's published policy. If retention guarantees matter to your workload, use the CLI with your own provider key locally for those workflows.