Guardrailed hosting agent

Your agent wants root. Give it guardrails instead.

Autonomous agents execute infra commands — one unchecked terraform destroy and your production database is gone. SoloShip wraps every command in a plan: danger-classified, guardrail-checked, AI risk-scored — and critical plans cannot execute without your explicit approval.

No agent framework. No lock-in. Every execution sealed into a tamper-proof vault.

Three steps

From raw command to sealed receipt

1

Submit a command plan

Paste the command your agent wants to run — rm -rf /data, terraform destroy, systemctl status nginx — plus the target environment and agent name.

2

Classify & guardrail

SoloShip classifies danger — safe, destructive, critical — checks region pinning and backup verification, generates a rollback plan, and scores the risk with AI (deterministic fallback if the AI is down).

3

Approve, execute, seal

Critical plans are blocked until you approve. Executions run through the gated wrapper and every one is hash-sealed into the evidence vault — a receipt no one can rewrite.

Capabilities

Rails that agents cannot argue with

🎯 Danger classification

Deterministic regex rules sort every command into safe, destructive, or critical — terraform destroy, db wipes, volume deletes, region migrations, and prod+delete combos never slip through.

🛡 Guardrail checks

Region pinning keeps staging workflows away from prod. Destructive plans require a verified backup. Every plan ships with a generated rollback plan.

🧠 AI risk analysis

GateAI scores blast radius 0–100 with concrete factors. If the AI gateway is unreachable, a deterministic heuristic answers instead — same shape, labeled fallback, never a 500.

🔐 Approval gate + vault

Critical plans return 403 without approved=true. Every execution is sealed into the hash-chained evidence vault with a full audit trail, newest first.

403
Unapproved critical plans — hard stop
3 tiers
Safe · destructive · critical classification
Hash-sealed
Every execution in the evidence vault
No lock-in
Wrapper, not a framework — your agents stay yours
Pricing

Start free. Upgrade when the stakes grow.

Free

$0

For the first projects you dare to automate.

3 projects
Danger classification & diff preview
Guardrail checks & audit trail
Start free

Launch

$29/mo

For founders running real deploy agents.

Unlimited projects
AI risk analysis (GateAI) + fallback
Approval workflows for critical plans
Vault-sealed executions
Start Launch

Fleet

$99/mo

For operators running fleets of named agents.

Everything in Launch
Multi-agent policies
Region pinning rules
Priority audit export
Start Fleet
FAQ

Questions, answered straight

Does SoloShip execute commands on my servers?

Not in v1. The executor is simulated: it records the gated execution — exit code, output log, applied-at timestamp — and seals the record into the evidence vault. The classification, guardrails, approval gate, and audit trail are all real. Real host adapters arrive after validation; the guardrails won't change when they do.

How does danger classification work?

Deterministic regex rules, checked in order. Critical patterns first — terraform destroy, database wipes, volume deletes, region migrations, and any destructive command targeting prod. Then destructive patterns — rm -rf, drop, delete, resize, migrate, force flags. Everything else is safe. Same input, same answer — no black box.

What happens if the AI risk analysis fails?

Nothing breaks. GateAI falls back to a deterministic heuristic that scores the plan from its danger class, environment, region and backup posture. The response is labeled mode: "fallback" so you always know which path produced the score. AI output is advisory — it never blocks or auto-approves a plan.

Can a critical plan execute without me?

No. A critical plan returns HTTP 403 from the execution endpoint unless the request carries approved=true. There is no override flag, no API key, no agent-side bypass. Approval is a human action by design.

Let your agents work. Not destroy.

Gate the next command in under a minute — free, with a sealed audit trail from day one.

Open the app — free