# gofireflyio/aiac

Artificial Intelligence Infrastructure-as-Code Generator.

Repository: https://github.com/gofireflyio/aiac
Canonical: https://ross.abutalabs.com/products/aiac
Language: Go
License: Apache-2.0
License Family: permissive
Topics: ai, chatgpt, iac, openai, pulumi, terraform, amazon-bedrock, ollama, llms
Last push: 2026-03-24T10:56:24+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 73, release rhythm 8, longevity 97
- inputs: {"age_days": 1365, "days_push": 162, "days_rel": 673, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3786, forks 295 (observed 2026-08-28T04:08:18.591646+00:00)

## What it is
aiac is a command line tool and Go library that uses LLM providers such as OpenAI, Amazon Bedrock, and Ollama to generate Infrastructure-as-Code templates, configuration files, CI/CD pipelines, and policy-as-code from natural language prompts. It composes requests to the selected model backend, saves the generated code to a file or stdout, and supports multiple configurable backends.

## Use cases
- generate terraform code from a text prompt
- create dockerfile or kubernetes manifests using an llm
- generate ci/cd pipelines like jenkins or github actions with ai
- write opa policy as code from a description
- generate pulumi or cloudformation templates via chatgpt or bedrock
- use a local llm with ollama to produce infrastructure code
- build shell scripts or query snippets from natural language

## When to choose
- you want to scaffold terraform, pulumi, or cloudformation templates quickly from plain-english prompts
- you need to generate dockerfiles, k8s manifests, ci/cd pipelines, or policy-as-code without writing boilerplate by hand
- you want a scriptable cli that can target multiple llm providers including local models via ollama
- you prefer storing generated iac to files or piping it into your existing devops workflow

## When to avoid
- you need guaranteed-correct, production-ready infrastructure code without human review, since llm output must be validated
- you require an interactive ide plugin or gui rather than a command line tool
- you cannot access any llm provider (cloud or local) due to network or policy restrictions
- you need deep drift detection or state management for existing infrastructure, which is the job of terraform or pulumi themselves

## Facets
- artifact type: cli-tool
- maturity: active
- function: infrastructure-as-code, llm-inference, cli
- domain: infrastructure-as-code, cloud-computing, artificial-intelligence, large-language-models, developer-tools
- platform: cli, go, cross-platform
- tags: terraform, pulumi, cloudformation, openai, amazon-bedrock, ollama, iac-generator, llm-codegen, devops-automation, policy-as-code, code-generation, devops, command-line, docker

## Member repositories
- gofireflyio/aiac (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.591646+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:27:40.153676+00:00, confidence not recorded.
  - readme: https://github.com/gofireflyio/aiac (fetched 2026-08-28T04:08:18.591646+00:00, sha 6e8750ad520a)
- Data as of 2026-08-30T08:39:29.467469+00:00.