
by jurniti
jurniti is managed hosting that runs each AI agent in its own Firecracker microVM, so agents stay on around the clock without a laptop left open. You bring your own model keys.
APIContact for pricing
Step 1: Sign in at the web dashboard with a magic link, or install the CLI with the one-line script for macOS, Linux or Windows.
Step 2: Add a card on file, since there is no free tier.
Step 3: Pick a plan size and an agent runtime, then provision the VM.
Step 4: Paste your own model provider key into the VM.
Step 5: Connect through the browser terminal or the CLI, and use the assigned subdomain for webhooks or dashboards.
Step 6: Optionally snapshot the VM as a template or manage it from your own agent over MCP.
No. The pages state there is no free tier and no free trial. The first subscription comes with a 30-day money-back guarantee.
The maker says no. You use your own keys, they stay inside your VM, and the model bill goes to your provider.
Flat per-VM plans (Starter, Pro, Max) from $25/month, with a discount for yearly billing. You can also pay by the hour from prepaid credits.
Through the web dashboard, the CLI, a REST API, or MCP from your own agent.
OpenAI Realtime APIOpenAI's Realtime API lets developers build speech-to-speech voice agents that work directly with audio, keep conversation state and call tools. It is for developers building voice assistants and other low-latency conversational apps.
Cloudflare AI GatewayCloudflare AI Gateway sits between your application and AI model providers. It adds analytics, logging, caching, rate limiting, routing with fallbacks and safety controls, and takes one line of code to start.
SambaNova CloudFast model inference cloud from SambaNova with OpenAI-compatible APIs for leading open-source AI models.