gofireflyio/aiac

Artificial Intelligence Infrastructure-as-Code Generator.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 29 minutes ago
Added to GitGenius on September 18th, 2026
Created on December 7th, 2022
Open Issues & Pull Requests: 3 (+0)
GitHub issues: Enabled
Number of forks: 296
Total Stargazers: 3,788 (+0)
Total Subscribers: 45 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 8.8 days
Mean response time: 8.8 days
90th percentile: 8.8 days
Tracked items: 1

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 2
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 301 days
Stale 30+ days: 1
Stale 90+ days: 1

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

AIAC is a command-line tool and library that generates Infrastructure-as-Code templates, configuration files, CI/CD pipelines, and related code by sending natural language prompts to large language model providers.

The tool solves the problem of manually writing boilerplate infrastructure code by accepting plain English requests and delegating code generation to LLM backends. Users describe what they need—for example, "terraform for a highly available eks" or "dockerfile for a secured nginx"—and the tool composes an appropriate request to a configured LLM provider, then outputs or saves the generated code. It supports multiple LLM backends including OpenAI, Amazon Bedrock, and Ollama, with configuration managed through a simple configuration file that lets users define different backends for different environments.

The tool suits developers and infrastructure engineers who want to accelerate boilerplate generation across Terraform, Pulumi, CloudFormation, Kubernetes manifests, Dockerfiles, and other infrastructure artifacts. It also handles policy-as-code generation, CI/CD pipeline creation, and utility script writing. Teams should choose this tool if they have a preferred LLM provider already in use and want to reduce time spent on repetitive infrastructure templating. The README does not compare it to alternative code generation approaches.

Development activity shows consistent engagement with the codebase through regular updates and refinements. The project maintains active support for multiple LLM providers and has undergone significant architectural changes between major versions to improve configuration handling and model support. The tool is available both as a standalone CLI and as an importable library, indicating attention to different usage patterns. Documentation includes troubleshooting guidance and migration instructions for version upgrades, suggesting responsiveness to user needs.