Carina

The platform

Build anything on Carina

The kernel for AI agents. Tools, memory, channels, and governance in one commercial platform. Here is what we built on it.

AI Agent Platform

The commercial AI agent kernel. 71 tools, 40+ channels, persistent memory, skill packs, 23 LLM providers. Build and deploy production AI agents on it.

Platform pricing

Built on Carina

Aiva

Our own AI employee product built on the Carina platform. Handles email, bookings, and client work for businesses. Proof of what the platform can deliver.

See Aiva at hireaiva.co.uk

Built on Carina

Propreneur

UK property investment MIS on the Carina kernel. Deal engine, compliance, CRM, and embedded Carina AI for portfolio operators. A full vertical SaaS on the platform.

See Propreneur at propreneur.uk

AI Governance

Labyrinth Scout

Kill switch, prompt guard, audit trail, and policy enforcement for any AI agent deployment. Standalone or included with Aiva plans.

See Scout pricing

The Differentiator

Skills That
Compound.

Most AI answers questions and forgets the conversation. Carina turns every complex task into reusable experience. The longer you use it, the better it gets.

Every task becomes experience

Completed workflows are analysed and distilled into compact skill entries automatically.

Every experience becomes a skill

Skills are tagged, versioned, and stored in a searchable skill library shared across all agents.

Every skill improves every agent

New sessions start with access to all prior skills. Most AI answers questions. Carina gets better.

learning-loop

2,481

Skills Generated

7-Day

Curator Active

Cross-Agent

Skill Sharing

channels

One Memory

One Agent.
One Memory.
Everywhere.

40+ channels. The same Carina. The same memory. The same skills. The same intelligence. You don't switch agents. Carina follows you.

Discord

Slack

Teams

Email

Signal

CLI

REST API

One memory shared across all 40+ channels.

Same skills. Same context. Wherever you work.

Full Workspace

A Full Workspace.
Not Another Chat Window.

Everything connected. Everything searchable. Everything remembered.

Notes

Calendar

Email

Research

Documents

Images

Kanban

Model Compare

Hardware-aware model serving. Carina's Playbook detects your GPU, VRAM, CPU, and storage and recommends models that actually fit. No guesswork. No wasted downloads.

workspace

Built-in Safety

It tells you what
it's about to do.
Before it does it.

Carina flags risky commands before running them. Not a firewall. Not a nag. A clear label, a plain-English description, and a prompt when it counts. Silent for safe actions. Visible when it matters.

Transparent by default Every flagged action is logged to the audit trail, approved or not.

Blocks the worst patterns Critical commands like rm -rf / and fork bombs are hard-blocked. No override without a flag.

Team scale with Scout Scout extends this to your whole team: shared audit logs, kill switch, and policy enforcement across every agent.

carina-workspace

  carina run: clean up old deployment logs

  CARINA SAFETY FLAG
  ------------------
  Command : rm -rf ./deployments/old/
  Risk    : DANGER
  Action  : Recursively deletes the target directory
            and all its contents. Cannot be undone.

  Run? [y/N] y

  Done. 2.3 GB freed.
  Flagged action logged to .carina/audit.log

What happens without oversight

These are not predictions.
They already happened.

Every documented AI agent incident shares one property: no one was watching. Three cases from the past 36 months.

$500M in one month

An enterprise deployed Claude with no spending caps. No agent budget controls. No usage monitoring. One month later, a half-billion dollar invoice. The agent ran. Nobody watched the meter.

Reported by Axios, May 2026. Scout fix: per-agent quotas, real-time spend alerts.

rm -rf on production systems

AI coding agents on Cursor, Claude Code, Replit, and Codex CLI have executed destructive shell commands without asking. Complete codebases deleted. Entire home directories wiped.

Docker security blog, 2025. Carina warns. Scout enforces policy.

Source code on external servers

Samsung employees pasted internal source code into ChatGPT for debugging. The data was uploaded to OpenAI's servers with no way to retrieve or delete it. Samsung banned all generative AI company-wide.

Bloomberg, May 2023. Scout fix: egress filtering keeps data in your infrastructure.

Read the full incident record See Scout protection

Carina executes. Scout enforces least privilege.

Workspace first.
Control when it matters.

Carina gives teams a workspace they actually use. Scout adds the controls for client data, approvals, audit, and production workflows.

Carina on its own

A strong workspace for drafts, research, and internal workflows. Best when you do not need governance yet.

Workspace

Carina with Scout

The same workflow, now with audit, approvals, alerts, and response controls for production use.

Production

See the full pricing path

Scout-ready. One key.

Unmonitored agents have already caused $500M bills, 13-hour outages, and deleted entire codebases.

Carina has a built-in telemetry pipeline. Set one config value, SCOUT_KEY, and every agent action reports to Scout: every tool call, every model decision, every workflow.

Labyrinth Scout governs the Carina commercial workspace. On Carina Aiva, Scout Govern is included in every paid plan at no extra cost.

Scout Monitor: £49/mo

Observe. Threat detection, audit logs, live feed. See everything your agents do.

Scout Govern: £79/mo

Act. Kill switch, injection shield, human-in-the-loop approvals. Included with Aiva paid plans.

Explore Scout

Scout Monitor and Scout Govern are available for governed AI deployments. Aiva includes Scout Govern on paid plans.

Common questions

FAQ

What is a deployment?

One running Carina instance connected to an LLM provider, with its own tools, memory, channels, and Scout governance. A deployment is a production AI agent or product.

What LLM providers are supported?

23 providers including OpenAI, Anthropic, Google Gemini, Mistral, Groq, DeepSeek, and OpenRouter. You bring your own API keys; inference cost stays with your provider account.

Does Scout come with Carina plans?

Yes. Developer plans include Scout Monitor. Builder includes Scout Govern. Scale includes Scout Team. Enterprise includes Scout Enterprise.

Can I build a product like Aiva on Carina?

Yes. Aiva is our own AI employee product built on the Carina platform. The same platform, tools, and memory are available to you. Your product, your branding, your customers.

How do I connect channels?

Configure credentials for each channel (WhatsApp, email, Slack, Telegram, etc.) in your deployment settings. Each channel requires its own API key or integration token.

What is the difference between Carina and Aiva?

Carina is the platform you build on. Aiva is a finished product we built on Carina. If you want to build your own AI agent product, use Carina. If you just want to hire an AI employee without building anything, go to hireaiva.co.uk.

Is there a free trial on paid plans?

Trial and access terms can be discussed before committing. Email [email protected] and we will set up the right entry path.

Build AI agents that
work, remember, and scale.

Build anything on Carina

Carina