Show HN: Kastor – Terraform-style specs for AI agents
Kastor is a new open-source tool designed to manage AI agents using a declarative, Terraform-style configuration. It allows developers to define, version, and deploy AI agents across various platforms using a unified spec.
Why it matters
As AI agent development becomes more complex, standardized infrastructure tools are necessary to improve reliability and maintainability in production environments.
Kastor is "Terraform for AI agents." Agents today are defined imperatively inside frameworks (LangGraph, CrewAI) or clicked together in platform UIs (OpenAI Assistants, Bedrock Agents) — there is no vendor-neutral, versionable, reviewable source of truth. Kastor provides one: a typed, declarative spec ( .agent , .tool , .prompt files in HCL) and a Go toolchain with two paths — kastor build generates runnable projects for target frameworks, and kastor plan / kastor apply reconcile agents as long-lived resources on hosted platforms, with state, diffs, and drift detection.
The content is a technical announcement for a developer tool, devoid of political or social bias.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in