Download EIDARA

AI-guided install

Your AI handles everything — personalization, git setup, first compile, watcher configuration. You don't type a single terminal command.

Download the ZIP

Unzip on your Desktop

Open any AI with file access. Give it the INSTALL file.

The AI does everything else — 11 steps, fully automated.

Download ZIP (v1.0) →

Works with Claude, GPT, Gemini, DeepSeek, TypingMind, or any model with file access.

Or clone from GitHub

If you prefer git, clone the repo directly. Same INSTALL file inside — give it to your AI and it handles the rest.

git clone https://github.com/jrotllant/eidara.git

View on GitHub →

Try the demo first

Want to see DARA fully populated before personalizing? The Sample Vault is a fictional indie maker's complete system — 17 neurons, 6 enablers, populated changelog, INBOX feedback. Download it, tell your AI it's there, and explore the system in action.

Download Sample Vault (.zip) →

Get notified of new releases

We'll email you when a new version ships. Each update comes with an UPDATE.md file — give it to your AI and it applies the changes automatically.

Only new releases. Nothing else.

FAQ

Do I need to know Python?

No. You need Python installed (the INSTALL guide helps with that), but you never write Python code. The compiler is a black box — you feed it markdown, it produces BRAIN.md.

Does it work with my AI model?

If the model can read a markdown file and follow written instructions, it works with DARA. We've tested Claude, GPT, DeepSeek, and Opus 4.7. The protocol is model-agnostic by design.

How much context does BRAIN.md use?

Starts at ~900 tokens with the starter vault. Scales efficiently — a typical setup with 20+ entries fits in ~3,500 tokens. Budget warnings at 50K/100K/150K. Designed to fit any modern context window.

What if I break something?

Git tracks every change. RECOVERY.md has 6 emergency scenarios. The compiler creates timestamped backups automatically. Worst case: git checkout the previous commit.

Is my data private?

100%. Your files never leave your machine. No telemetry. No cloud sync. No analytics on your content. Local-first, always.

Can I try it before personalizing?

Yes. Download the Sample Vault — a pre-loaded demo with example neurons, enablers, and a pre-compiled BRAIN.md. Run compile.py and see it rebuild. Takes 2 minutes.

Built in the open

EIDARA is free. MIT licensed. No telemetry. No cloud. Your data never leaves your machine.

Built by Javier Rotllant — 13 years in consulting, 9 at Bain & Company, not a software engineer. Someone with a problem and the stubbornness to solve it properly.

Star on GitHub →