Qvickt supports all major LLM providers including OpenAI, Anthropic, and Google Gemini. Since you bring your own API key, you can switch providers at any time without changing your agent's logic.

You add your own LLM API key in your Qvickt dashboard. Your key is encrypted at rest and only used when your agent runs. You control your costs directly with the provider — Qvickt never marks up LLM usage.

Qvickt automatically restarts crashed agents within seconds. Every run is logged with full input/output traces, so you can debug exactly what went wrong. Your agent's container state is preserved across restarts.

Yes. The free plan includes 1 AI agent and 100 executions per month — no credit card required. It's a great way to test the platform before scaling up.

Absolutely. Agents can use CLI tools (any apk package) or custom Node.js modules with full npm ecosystem access. Define your tools as ES modules with TypeScript support and they'll be available in your agent's container.

Each agent runs in an isolated container with its own filesystem and network. No data is shared between agents. Your LLM keys are encrypted at rest and never logged. We don't store conversation data unless you explicitly enable logging.

Yes. The Qvickt dashboard shows live status, execution logs, and performance metrics for all your agents. You can also set up webhook notifications for specific events like errors or completed tasks.

Scheduled triggers run your agent on a cron schedule (e.g., every hour, daily at 9am). Webhook triggers let external services like GitHub, Slack, or Zapier start your agent via an HTTP endpoint. You can combine both on the same agent.