Ralph-agy

Ralph-agy is an autonomous AI agent loop that drives the Google Antigravity CLI (agy) to implement user stories from a prd.json file until every task is…

  • Tools & Utilities
Ralph-agy is an autonomous AI agent loop that drives the Google Antigravity CLI (agy) to implement user stories from a prd.json file until every task is complete. It is built for developers and homelab users who want a hands-off, repeatable coding agent for turning a product backlog into working code.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

34/100 Low

Maintained
60last commit 157 days ago
Popular
61 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
1016 GB minimum RAM

Availability: platform listings confirmed today, links checked 18 days ago

GitHub stars
1
Open issues
0
Last commit
2026-06-17
License
MIT
Activity
stale

Checked 6 days ago - source: GitHub (Zeyso/ralph-agy)

Resources & Compatibility

Minimum requirements: 16 GB RAM, 50 GB disk.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Install Node.js/npm and Ralph CLI First make sure Node.js (the program that runs JavaScript) and npm (its package manager) are installed, then run `npm install -g @ralph-orchestrator/ralph-cli`. Without Node/npm, the install command will not work and the Ralph command won't be available on your system. source
  • Add an AI backend and API key Ralph needs at least one AI CLI tool, so install and configure one before starting. For Gemini, run `npm install -g @google/gemini-cli`, then set the `GEMINI_API_KEY` environment variable with a secret code for the service, for example `export GEMINI_API_KEY=your-key`, and verify with `gemini --version`; without that, Ralph can't call the AI. source
  • Initialize Ralph with a preset Before your first project, run a command like `ralph init --preset tdd-red-green` to create Ralph's project settings from a preset (a pre-made workflow). If you skip this, Ralph may not start with the setup you expected, and you can list options with `ralph init --list-presets`. source
  • Docker/Unraid deployment The repository includes a Dockerfile, docker-compose.yml, and unraid-template.xml for container/Unraid setup. source

Fetched today - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Which local directories should I create before running the Docker setup?

Create project, agy-config, and logs in the project folder. They are mounted into the container for the repo, agy configuration, and persistent logs.

What do I need to put in the Docker .env file before starting Ralph-agy?

Copy .env.example to .env and enter your GOOGLE_API_KEY.

How do I authenticate the agy CLI after the container starts?

Enter the container with docker exec -it ralph-agy bash, then run agy auth login. You can authenticate with OAuth or an API key.

How do I add the provided Unraid template?

Copy unraid-template.xml into /boot/config/plugins/dockerMan/templates-user/ and select the ralph-agy template in Unraid's Docker Add Container screen.

Can I build the Docker image locally instead of pulling it?

Yes. Run docker compose up -d --build to build the image and start the container in the background.

Answers sourced from github.com

Community

Collected 49 days ago - public community threads