# Nexent

A zero-code platform for building production-grade AI agents that unifies tools, skills, memory and orchestration with built-in constraints and feedback loops, described in plain language rather than assembled with drag-and-drop.

Nexent is a platform for auto-generating AI agents without writing orchestration code. It provides unified tools, skills, memory and orchestration with built-in constraints, feedback loops and control planes, so an agent is described in plain language rather than assembled in a drag-and-drop builder.

It deploys with Docker or Kubernetes; the root `deploy.sh` script forwards to a Docker or Kubernetes deploy script sharing the same configuration model, with an interactive terminal menu for component selection, port policy and image source, or a `--defaults` flag to skip the menu. An `infrastructure` component is required, while `application`, `data-process` and `supabase` are enabled by default and can be turned off for a smaller deployment.

It is written in Python and licensed under MIT.

Website: http://modelengine-group.github.io/nexent/