Carina AI - Autonomous AI Agent with Labyrinth Scout Security

Carina Core is Free & Open Source

The agent that works while you sleep
+ Labyrinth Scout security

Carina is an autonomous AI agent that runs locally, remembers everything, and gets smarter every session. Add Labyrinth Scout for enterprise-grade security monitoring, prompt injection protection, and real-time alerting.

carina-agent + scout
$ npm install -g carina-agent
Carina core loaded
Labyrinth Scout active — 10-layer security
You: Research Portsmouth HMO areas
Carina: [Scout: injection scan passed] Running property-uk skill pack...
Carina: Done. Report saved. Scout audit log updated.
Persistent memory Self-writing skills Moving target deception Model agnostic Property skill pack Local first GDPR compliant Real-time alerting MIT licensed
Carina Core

Built for real work.
Not demonstrations.

A general autonomous agent with vertical depth no competitor ships by default. Free. Open. Yours.

Persistent memory

Episodic memory with pgvector semantic search. Carina recalls relevant past conversations automatically.

Hermes-class

Self-writing skills

After solving a complex problem, Carina writes a skill document. She gets smarter every session.

OpenClaw-class

Real tool execution

Web search, files, shell (sandboxed), email, HTTP requests, code execution. She acts, not advises.

Switch providers mid-conversation

DeepSeek, Claude, GPT-4o, or local Ollama. Type /provider anthropic — no restart.

Every channel, one agent

CLI, Telegram, WhatsApp, Web UI. Same memory, same skills, same Carina.

Local first, no telemetry

Your data never leaves your machine unless you explicitly use a network tool. MIT licensed.

Labyrinth Scout

Enterprise security for autonomous AI.
Because agents need watching.

Carina Core is free. Labyrinth Scout adds the security control plane that enterprises require. Built from the ground up using deception technology from VERLOX's Master's distinction project.

Moving Target Deception

Dynamically rotates Carina's API fingerprints. Attackers cannot reliably identify or target your agent. Port of the CMS technology that won a Master's distinction.

Prompt Injection Shield

Three-layer detection: regex patterns, LLM-as-judge, and tool result scanning. Blocks direct and indirect injection attacks before they reach Carina's context.

Real-time Security Dashboard

Animated threat radar, live event stream, heat maps, and anomaly scoring. Every tool call, injection attempt, and anomaly appears within milliseconds.

Multi-channel Alerting

Telegram, WhatsApp, Slack, Email, SMS. Get critical alerts instantly. Custom severity thresholds per channel.

Deception Layer (Honeypots)

Fake API keys, credential files, and endpoints that alert when accessed. Based on the Labyrinth deception model from your Master's project.

Heuristic Anomaly Detection

Learns Carina's normal behavior. Alerts on tool call frequency spikes, dangerous command patterns, and data exfiltration attempts.

Tool Allowlisting & Rate Limiting

Define which tools can run without confirmation. Rate limit per session. Block dangerous commands like `rm -rf /` or `curl | bash`.

Kill Switch

Remotely suspend a compromised Carina instance from the dashboard. One click. Immediate effect via Redis pub/sub. Full audit trail.

Full Audit Log & Compliance

Every action logged with cryptographic integrity. Export for GDPR, SOC2, ISO27001. Memory transparency — see and delete what Carina knows about you.

Egress Filtering & DLP

Block Carina from calling unknown domains. Detect and block sensitive data (API keys, passwords) from leaving your infrastructure.

Add Labyrinth Scout Watch Demo
Pricing

Free to run. Pay only for security.

Carina Core is MIT licensed and always free. Labyrinth Scout is the paid security control plane for production deployments.

Carina Core

Free
  • Full autonomous agent
  • All tools (web, file, shell, email, HTTP)
  • Memory & self-writing skills
  • CLI, Telegram, WhatsApp, Web
  • UK property skill pack included
  • MIT open source
npm install -g carina-agent

Labyrinth Scout

£99/month

For any AI agent (OpenClaw, Hermes, AutoGPT, custom)

Save 20% with Carina
£79/month

When monitoring Carina, the free open source agent. Saves £240/year.

  • Moving target deception
  • Prompt injection shield
  • Real-time security dashboard
  • Multi-channel alerts
  • Kill switch
  • Full audit logs
Get Scout — £99/mo

Enterprise

Custom
  • Everything in Scout
  • SOC2 Type II attestation
  • 99.9% uptime SLA
  • Dedicated Slack support (15min)
  • Custom compliance reports
  • On-premise deployment option
Contact Sales

Carina users get 20% off Labyrinth Scout: £79/month instead of £99. Scout works with any agent; Carina just saves you money. Learn more →

Labyrinth Scout

For organisations running autonomous AI agents in production.

Moving target deception Prompt injection shield Real-time dashboard Kill switch Full audit logs Deception layer

No per-seat pricing. No hidden fees. Cancel anytime.

Self-hosted Carina Core is always free. Scout is £99/mo with any agent, or £79/mo when paired with Carina. No telemetry. No hidden fees.

Why Carina?

How Carina stacks up

Capability OpenClaw Hermes Carina + Scout
Autonomous task execution
Persistent memory
Self-writing skills No
Vertical skill packs (property-uk) No No
Memory transparency (view/edit) No No
Switch LLM mid-session No No
npm install No No
Prompt injection protection No Partial 3-layer
Moving target deception No No Scout
Real-time security dashboard No No Scout
Kill switch No No Scout
Open source (MIT)
Labyrinth Scout pricing £99/mo £99/mo 20% off £79/mo
Get started

Install Carina.
Own your agent. Add Scout for security.

One command. Runs on your machine or VPS. Your data stays yours.

npm install -g carina-agent
npx carina-agent start --with-scout

Built by VERLOX Ltd · MIT License · carinaai.uk · labyrinthscout.com