Loading page
Loading page
AI
Put a policy and audit layer between your AI clients and the models and tools they call.
systemprompt is a self-owned AI control plane. It sits between your AI clients and the models and tools they use. Each request is tied to an authenticated user. Policy decides what that user may do, and the result is written to an audit log in PostgreSQL.
This template is the evaluation build. It bundles the Core runtime with configuration, an admin UI, extensions and demos. You can add your own Rust extensions for routes, tools, jobs and policies.
It is for teams that let staff use AI models and MCP tools and need control over who uses what. Security and platform teams that must show an audit trail are the main audience.
Governance data is sensitive. Self-hosting keeps the audit records and policy decisions inside your own perimeter, in your own database.
Read the license before production use. The template is MIT, but Core is BSL-1.1 and needs a commercial license in production. Inference still goes to the provider you choose, so prompts leave your server. You look after updates, backups and the provider keys.
Containers: ghcr.io/systempromptio/systemprompt-template:0, postgres:18-alpine
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose systemprompt, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the systemprompt setup screen.