JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 50
  • Score
    100M100P100Q105318F
  • License MIT

Aura Code — model-agnostic AI coding agent. Works with Claude, GPT, Gemini, MiMo, Ollama, and any OpenAI-compatible endpoint. MIT licensed.

Package Exports

  • aura-code
  • aura-code/dist/cli/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (aura-code) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Aura

Aura Code — Autonomous Coding Agent

I don't try. I verify.

npm version CI 734+ tests MIT License Node.js 18+ GitHub Stars

Architecture Diagram
View full architecture documentation →

Aura Code CLI Demo
CLI demo — help, models, and version overview

What is Aura Code?

Aura Code was developed using AI-assisted engineering workflows, with multiple AI agents contributing to design, implementation, testing, and verification. Written in TypeScript — not related to the Ruby programming language.

Built on the Praktess framework — from Ancient Greek: she who acts and executes.

Quick Start

npm install -g aura-code
aura 'your task here'

Set at least one API key before running:

export ANTHROPIC_API_KEY="sk-ant-..."   # Claude
export OPENAI_API_KEY="sk-..."          # GPT
export GOOGLE_API_KEY="..."             # Gemini
export XIAOMI_API_KEY="tp-..."          # MiMo
# Local — no API key needed:
# ollama pull qwen2.5-coder:1.5b

What Aura Does

  1. Reads your codebase — files, structure, dependencies
  2. Plans a strategy — decides what to change and how
  3. Executes — writes code, runs commands, makes edits
  4. Verifies — runs tests, checks file integrity, confirms changes
  5. Reports — summarizes what was done and what passed

Modes

Mode What it does
normal Single-agent loop: read → plan → execute → verify
orchestrate Multi-agent: Researcher → Coder → Reviewer
architect High-level design and planning before implementation
verify Post-task checks with automatic retry on failure
analyze Scan session history for failure patterns 
aura 'fix the bug'                                      # normal
aura --orchestrate 'add error handling to all endpoints' # orchestrate
aura --architect 'design the new auth system'            # architect
aura --verify --test-command "npm test" 'fix the tests'  # verify
aura --analyze                                           # analyze

Providers

Provider Models
Claude (Anthropic) Opus, Sonnet, Haiku
GPT (OpenAI) gpt-4o, gpt-4o-mini
Gemini (Google) gemini-2.5-pro, gemini-2.5-flash
MiMo (Xiaomi) mimo-v2.5-pro, mimo-v2.5
DeepSeek (OpenRouter) deepseek-v4-pro, deepseek-v4-flash:free
Ollama (Local) Any local model — no API key needed

Any OpenAI-compatible endpoint also works via openrouter/<model>.

Stats

Metric Value
Tests 734+ passing, 0 failures
Version v0.3.0
Language TypeScript (strict)
License MIT

Repository

GitHub: https://github.com/milodule3-debug/aura-code (Repo renamed from milodule3-debug/rubyness — existing clone URLs redirect automatically)

Built by Lean Progress IQ