Open-source AI workspace

Your work lives in 20 apps.
Your intelligence shouldn't.

One memory. One agent. Everywhere you work. Carina connects across 40+ channels and remembers everything, so you never re-explain yourself to an AI again.

carina-workspace
Carina workspace hub
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
Skills that compound - learning loop
2,481
Skills Generated
7-Day
Curator Active
Cross-Agent
Skill Sharing
channels
One agent, everywhere - 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.

Telegram
WhatsApp
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
Carina 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.
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

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.

Scout is a separate product that monitors any autonomous agent. Carina is pre-wired for it. Other agents need custom integration. Carina needs one line.

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. Same price on self-host or Carina Cloud.

Explore Scout

Scout is one price everywhere. Self-host Carina for free and add Scout, or run on Carina Cloud (£20/mo) and stack Scout on top.

71 Tools
40+ Channels
23 LLM Providers
18 Skill Packs
MIT Licensed

Start working. Carina remembers.
Add Scout when it matters.

Self-host for free and build the workflow. Add Scout before the work touches client data, approvals, or ships to production.