Kastor - Terraform-style declarative specs for AI agents
Show HN: Kastor – Terraform-style specs for AI agents
Kastor brings infrastructure-as-code principles to AI agent development, acting as a vendor-neutral source of truth. Instead of defining agents imperatively within frameworks like LangGraph or CrewAI, users write typed, declarative specifications in HCL. The toolchain compiles these specs into runnable projects or manages agents on hosted platforms with plan and apply semantics. This approach enables version control, code reviews, and drift detection for AI workflows, ensuring reproducibility and eliminating the chaos of UI-based or framework-locked agent definitions.
Agents today are defined imperatively inside frameworks or clicked together in platform UIs — there is no vendor-neutral, versionable, reviewable source of truth. Kastor provides one.
- empath75
The problem right now with something like this is you're trying to nail jello to a wall. People haven't figured out what an agent is yet, and trying to crystalize what people happen to be doing right now means in a few months, you're going to be obsolete.
- whattheheckheck
Why not just make an actual terraform module?
- handfuloflight
The website is down?