Bus AI Platform
Turn a model into a billable AI product — on infrastructure you control.
Bus AI Platform covers everything between a model and a paying customer: OpenAI-compatible APIs, inference runtime control, deployment from laptop to server, login and entitlements, usage metering, billing, and VM and container runtimes. Self-hosted, so your models, your customer data, and your billing relationship stay under your control.
What it is for
This product is for technical founders, SaaS developers, and platform teams that need AI APIs, runtime control, product controls, and deployment paths without building a custom pile of gateways, scripts, usage hooks, and billing glue. Like every BusDK product, the core surfaces are designed to be driven through CLI, API, and events, so AI agents can take on platform work alongside your team.
Core workflows
- Start an AI service locally and promote the same setup to deployed environments.
- Keep OpenAI-compatible interfaces while staying free to swap model backends.
- Add login, entitlements, usage capture, billing, and service tokens.
- Manage the VMs, containers, databases, and inference backends underneath with the same tooling.
Modules behind the product
The product includes modules for model and inference access, runtime control, deployment and infrastructure operations, login and sessions, usage metering, billing with Stripe support, cloud, database, and node integrations, and SSH runners.
Plan your deployment
Read the documentation for the current module surface, then talk through a deployment that fits your infrastructure — managed, dedicated, or fully self-hosted.