HN Showcase
Back to browse
GitHub Repository

Declarative language and toolchain for AI agents: define agents, tools and prompts in HCL, then compile to frameworks or manage them on hosted platforms with plan/apply semantics.

0 starsGo

Kastor – Terraform-style specs for AI agents

by weirdguy·Jul 8, 2026·10 points·11 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainSlick

HCL specs with plan/apply semantics bring IaC discipline to agent management.

Strengths
  • •Vendor-neutral .agent, .tool, .prompt files enable versionable source of truth.
  • •Drift detection and state management for long-lived agent resources.
  • •Generates runnable LangGraph projects from declarative specs.
Weaknesses
  • •Terraform-for-X pattern is well-trodden infrastructure territory.
  • •AI agent management platforms already emerging from major cloud providers.
Category
AI/ML
Target Audience

DevOps engineers and teams managing production AI agent infrastructure

Similar To

Terraform · Pulumi · LangGraph Studio

Similar Projects

AI/ML●●Solid

Agentify - A Declarative, AI agent building toolkit

Defines agents as YAML specs and provides a simple CLI + Python API so you can iterate on agent behavior without committing to a heavyweight framework. It supports many model providers (OpenAI, Anthropic, Google, Mistral, Bedrock, etc.) and includes Colab examples and a quickstart, which makes experimenting frictionless — but it deliberately avoids workflow/orchestration features, so it’s clearly aimed at prototyping rather than production-grade agent pipelines.

Niche GemShip It
lewissheridan
114mo ago