New customers can spin up VMs, build with AI, and query data at no cost.
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Start Free
Host LLMs in Production With On-Demand GPUs
NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.
Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
An open source, self-hosted implementation of the Tailscale control
Headscale is a fully open-source, self-hosted implementation of the Tailscale coordination server (control plane). It uses WireGuard for P2Pencrypted networks (tailnets), providing users with IP assignment, key exchange, and device management—all via a lightweight Go server.
Bringing intranet on the internet with Zero-Config Mesh VPNS.
OmniEdge is an Open source p2p layer 2 , zero-config mesh VPN infrastructure, a traditional VPN, AWS VPC, Ngrok, DDNS alternative. No central server, easy to scale with less maintenance. What happens in intranet, stays in in intranet.