Getting Started

Canonical inventory

See Capability inventory for the full list of tools, providers, channels, and optional surfaces.

Carina Cloud (no install)

Use the hosted app at app.carinaai.uk if you want a browser workspace with BYOK keys and optional Pro security (Labyrinth Scout). Full guide: Carina Cloud.

Agencies and resellers: start with the White-label getting started path for branding, domains, client handoff, and partner tiers.

If you are running a team and need BYOK vaults, audit retention, usage controls, or model routing, upgrade to Carina Ops from the app billing page.

Prerequisites (self-hosted)

Requirement	Version	Notes
Node.js	22+	Required for runtime and CLI
pnpm	9+	Used for development from source
PostgreSQL	16	With pgvector extension for episodic memory and RAG
Redis	7+	Session persistence and Scout kill-switch channel
Docker	Latest (optional)	Required for shell-exec and full code-exec sandboxing

Windows is supported with Node.js 22+ and npm. Use Docker Desktop if you need stronger shell isolation or Python code execution through the sandboxed tools.

warning

Never commit .env or ~/.carina/.env. API keys in git are a common breach vector.

Install (global)

See the dedicated Install page for curl, npm, Docker, and source paths.

npm install -g carina-agent
carina

Package: carina-agent v0.2.0 on npm (Node.js 22+). On first run, Carina introduces itself, asks your name and what you are building, and optionally collects an API key. Config is written to ~/.carina/ automatically.

Install from source

git clone https://github.com/malike2356/carina-agent.git
cd carina-agent
pnpm install
pnpm build
pnpm cli

Source lives in the public carina-agent repo (core only). The private carina-ai monorepo is VERLOX internal and is not cloned by customers.

pnpm cli starts the full gateway stack (CLI + web + Telegram when configured). Use SKIP_CLI=true pnpm dev to run without an interactive terminal.

First run

When ~/.carina/.env does not exist (or onboarding is incomplete), carina prompts for:

1. Your name and what you are building (one sentence)
2. Optional API key - DeepSeek, Anthropic, or OpenAI now, or local mode until you add a key later

No YAML editing required. The flow writes ~/.carina/.env and ~/.carina/config.yaml with mode 0600.

carina setup          # re-run onboarding or change provider
carina setup --full   # advanced wizard (Postgres, Scout, WhatsApp, packs)
carina doctor         # install health check

Optional fourth step: Labyrinth Scout. If you already have a Scout subscription, paste the console URL and API key from your provisioning email. See Labyrinth Scout.

Your first conversation

After setup, ask a task in your domain. If you installed packs, Carina matches curated skills and RAG chunks from keywords in your message:

You: Summarise our sprint blockers and draft a standup update for Slack.

Carina: [using devops pack skills...]
Done. Standup draft saved; three blockers flagged for follow-up.

See skill packs overview and carinaai.uk/skill-packs for all 16 packs.

Environment variables

See Configuration for the full reference. Minimum to chat without memory:

Variable	Required	Purpose
DEEPSEEK_API_KEY (or other provider key)	Yes	LLM inference
DATABASE_URL	For memory/RAG	PostgreSQL with pgvector
GEMINI_API_KEY	For embeddings	text-embedding-004 (768 dims) for ingest and memory

Running without a database

PostgreSQL is optional. Without it, Carina runs in stateless mode:

Feature	Without Postgres	With Postgres + pgvector
Chat (LLM conversation)	Works	Works
Web search (Tavily)	Works	Works
Tool execution	Works	Works
All gateways	Works	Works
Skill packs	Works	Works
Episodic memory (/recall)	Not available	Available
RAG knowledge search	Not available	Available
Session persistence across restarts	Not available	Available

To run without Postgres, omit DATABASE_URL from your .env. Carina logs "Memory store not ready - running in chat-only mode" at startup; this is expected and not an error.

tip

Start without a database, try Carina for a day, then add Postgres when you want memory and RAG.

Database setup

Start Postgres and Redis with the included compose file (maps Postgres to host port 5433):

cd core.carinaai.uk
docker compose up -d postgres redis

Then point Carina at the database:

DATABASE_URL=postgresql://carina:secret@localhost:5433/carina

Run migrations on first connect (handled automatically at startup). To ingest RAG corpus for a pack (e.g. property-uk):

pnpm ingest

Requires GEMINI_API_KEY (or configure OpenAI embeddings in your deployment). Not required for packs without a knowledge corpus.

Verify memory is working

1. Start Carina with a valid DATABASE_URL. Startup should log Memory store ready.
2. Have a short conversation, then type /recall in the CLI.
3. You should see recent user and assistant turns for the current session.

If memory is unavailable, Carina continues in chat-only mode and logs a warning at startup.

Next steps

• Configuration - all env vars
• CLI gateway - commands and streaming
• Skill packs overview - all 16 domain packs
• property-uk pack - optional UK property vertical
• Labyrinth Scout - optional security control plane
• CLI gateway - command reference and operations