#8585th of 87 in Coding agents and assistants
aiac
CLI that generates Terraform, Dockerfiles, k8s manifests and queries from prompts
- Stars
- 3.8k
- License
- Apache-2.0
- Last commit
- Mar 2026
- Last release
- Oct 2024
- Language
- Go
Missed the latest GitHub check; these facts may be older.
Overview
aiac is a Go command line tool and library that sends a prompt such as "terraform for AWS EC2" to an LLM backend and extracts the code from the reply. It supports OpenAI (including Azure OpenAI), Amazon Bedrock and Ollama, configured as named backends in a TOML file. Output goes to stdout or files, with an interactive shell for retries and follow-ups.
Who it is for: DevOps engineers who want IaC and config snippets generated from the terminal
Strengths
- Named backends in one TOML file, so staging and production providers can coexist
- Works with OpenAI, Azure OpenAI, Amazon Bedrock and local Ollama
- Quiet mode with file output and clipboard flags suits scripting
- Usable as a Go library (libaiac) as well as a CLI
Weaknesses
- Does not read your repo or run commands; it only generates code from a prompt
- Chat models only; completion models dropped in v5
- Does not validate model names, and --list-models may show unusable models
- Last release 2024-10-29; Ollama behind an authenticating proxy is unsupported
What it needs
- no GPU
- Docker
- Needs OpenAI API key, Amazon Bedrock account, or Ollama server
- Models: OpenAI, Azure OpenAI, Amazon Bedrock, Ollama
Also in Coding agents and assistants
See all 87| Rank | Project | Score |
|---|---|---|
| 1 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 2 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 82 out of 100 |
| 3 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |
| #4 | Open SWELangChain coding agent that plans, implements and reviews pull requests | 80 out of 100 |
| #5 | opencodeTerminal coding agent with build and plan modes, plus a desktop app | 79 out of 100 |