Skip to main content

Aubia, beta 0.1 pre-launch: your AI agents review each other, on every output, from one model family to the next.

Pre-launch · Early access

The dawn of multi-agent code.

Claude implements, Codex reviews, Mistral tests. You arbitrate, Aubia executes.

Aubia makes your AI agents review each other.

The best reviewer isn't the agent that just wrote the code: every AI-generated change is reviewed by a different model family, and you arbitrate.

By signing up, you agree to receive waitlist emails. Our privacy policy explains how your data is used.

Free beta, no time limit. Email address used for the beta invitation and the creation of your Aubia account.

The AI agents Aubia runs and cross-reviews: Claude Code, Codex CLI, Mistral Vibe

Cross-reviews the agents from

  • Claude Code
  • Codex CLI
  • Mistral Vibe
  • Antigravity CLIsoon
  • Local enginesoon
aubia · cross-review · PDF downloaditeration 2/3
  1. Implementation, done
    Agent
    claude
    Diff
    + 28 · − 4
    Time
    T+00:47
  2. Review, done
    Agent
    codex
    State
    needs changes
    Issues
    2
  3. Feedback, done
    State
    feedback sent
    Target
    claude
    Scope
    1 file
  4. Iteration 2/3, in progress
    Agent
    claude
    State
    streaming
    Limit
    3 iterations
  5. Arbitration, to do
    Arbiter
    you
    State
    pending
Agents
6
Iteration
2/3
Diff per iteration
+ 28/ − 4
Opinions
3
Lines per iteration InvoiceController.php
iteration 2/3+ 28− 41 file
app/Http/Controllers/InvoiceController.phpImplementationReview
+ use App\Actions\GenerateInvoicePdf;-   public function show(Invoice $invoice): View+   public function download(Invoice $invoice): Response+   {+     $path = $this->pdf->handle($invoice);+     return Storage::download($path);
+ 28− 4· 1 fileT+00:47

Another customer's invoice

downloadable by changing the URL.

Review · codex

PDF regenerated on every click

instead of serving the archived file.

needs changes

feedback sent

Synthesis

youOpinions to Executable Plan Mode

"How to create PDF invoices?"

claude-sonnet-5-5
done
HTML page printed by Chromium.
gpt-6.1-sol
done
DomPDF library, rendering entirely in PHP.
mistral-medium-3-5
done
Dedicated Gotenberg service, separate from the application.
aubiaSynthesis · 3 opinions

Convergences · 2

· Archived PDF, never regenerated

· Queued generation

Divergences · 1

· Rendering:

browserDomPDFGotenberg

Executable Plan · 4 tasksauto

  1. Generate and archive the PDF of each invoice

    GenerateInvoicePdf.phpdone

  2. Create the invoice HTML template

    invoice.blade.phpdone

  3. Add the PDF download

    InvoiceController.phpfeedback

  4. Test the download

    InvoiceDownloadTest.phppending

Preview

Multiple agents, one interface.

From multi-provider synthesis to supervised execution, everything goes through the same view. You see who is doing what and who reviewed whom.

A model from another family reviews every implementation. The agent iterates until agreement, or escalates the disagreement for arbitration.

Three agents answer the same prompt. Aubia turns their answers into an Executable Plan, convergences up front and divergences marked, which you approve or adjust.

Each AI agent advances on its task, in parallel.

Features

Your AI agents review each other. Aubia synthesizes.

Aubia is a desktop application that runs multiple AI coding agents on your code, in parallel, and makes them cross-review and challenge each other.

Flagship feature

Opinions to Executable Plan Mode

Submit a technical decision to multiple models at once. Each argues its position, and Aubia turns their answers into an Executable Plan: convergences first, disagreements isolated for your arbitration. You decide, without writing a line.

An automatic cross-review loop

One agent implements, a model from another family reviews. The two exchange the diff until convergence, in 3 iterations by default, a setting you can change. If a disagreement persists, you arbitrate.

Multiple AI agents, in parallel

Multiple agents run simultaneously on the same Git repository, each in its own isolated git worktree. Claude, Codex and Mistral analyze the same problem without stepping on each other.

One pipeline, multiple providers

Aubia drives Claude Code, Codex CLI and Mistral Vibe in the same pipeline. Tomorrow Antigravity CLI, a local engine and your favorite providers. Plug in your own API keys (BYOK), no vendor lock-in.

Kanban + per-agent terminal

All your agents in a single view. Kanban for the global state, integrated terminal for the ones currently running.

Vision

Why Aubia exists.

Four convictions drive Aubia's technical choices, from the first commit to the features still to come, and a single one sums them up: AI-generated code deserves a second reading, which cannot come from the agent that wrote it.

A single model is a single blind spot.

A model does not audit its own biases. As long as the same agent implements then reviews, errors loop back. The second reading comes from another model family, hence from another angle: one agent implements, another reviews, and that is cross-review.

One prompt, multiple opinions, one Executable Plan.

A senior dev consults before deciding. AI agents should work the same way, and your role becomes arbitration: multiple proposals, one direction you choose.

A pipeline that works once must work a thousand times.

A sequence of agents that solves a problem well is an asset. It must be saveable, versionable, shareable, replayable on other projects. A well-crafted prompt is worth as much as a well-written function.

Your code stays on your machine.

Aubia runs locally, BYOK: your API keys, encrypted in the OS keychain. No Aubia server ever sees your sources, and no mandatory intermediary sits between your code and your providers.

Roadmap

Version 1.0 is built before your eyes.

From beta 0.1 to 1.0, each 0.x version brings a feature. You install Aubia once, and updates arrive with no migration to run.

Cross-review as a multi-step DAG

After beta 0.1, cross-review extends to graphs of arbitrary AI agents. Claude implements, Codex and Mistral review in parallel, Gemini arbitrates the disagreements, a final AI agent merges. Every step and every branch stay under your control.

  • Visual pipeline editor

    Branches, conditions, fan-out/fan-in. Build arbitrary pipelines with the mouse.

  • Manual plan editor

    Write an Executable Plan directly, without going through Opinions to Executable Plan Mode. Automatic cross-review per task.

  • Reusable prompts

    Your favorite templates, versioned and shareable.

  • 100% local inference

    Llama, Qwen or Gemma on the local engine of your choice, as long as it is compatible with the OpenAI API, MLX included on Apple Silicon.

  • Multi-machine sync

    Themes, shortcuts, configs and templates follow your machines: personal, work, backup laptop.

  • MCP integration

    Aubia becomes a tool inside Zed and Claude Desktop. An agent callable as an MCP tool.

  • CI auto-fix

    Pipeline that fails, an agent retrieves the logs, fixes, restarts. Notification after 3 attempts.

  • Budgets and cost alerts

    Track what your pipelines cost, by provider and by project. Alerts before overrun.

  • Gemini provider

    Google Gemini joins the providers via Antigravity CLI. One more model family for your cross-reviews.

  • Mobile companion

    Track your agents from your phone. Launch at the office, resume on the couch.

  • The other orchestrators run your AI agents. Aubia cross-reviews them, synthesizes them, composes them into shareable pipelines.

    Request early access

Creator's letter

A project that refuses to bet on a single model.

Mike, founder of Aubia

Mike

CTO · Founder · Web artisan since 2009

contact@aubia.dev

I've always been passionate about new technologies, and web development in particular: it lets you deliver your work directly to users. To me, every line of code is an expression of craft. It's in that spirit that I designed GlobalExam's information system from scratch, then CEGELEM's.

Everything shifted in February 2025, with the first preview of Claude Code. Codex CLI followed shortly after, and very quickly, having to switch between them constantly felt wasteful: two model families at hand, one viewpoint at a time.

Over time, one thing became obvious. The easiest way to miss an error is to be the one who wrote it. And it holds just as true for an agent: an agentic tool tied to a single provider is a dead end. Claude misses details Codex catches at first glance, and Codex sees an implementation through that Claude would have questioned. In a mono-provider pipeline, the same biases end up reviewing the code at every step, and errors slip silently from one agent to the next.

Aubia grew out of that frustration of not being able to make multiple LLM families work together, in the same session. At first, I built this project to help me with my own daily tasks. But if this need drives me enough to pour that much energy into it, I'm probably not the only one who feels it.

It reminds me of multi-cloud for infrastructure: multi-provider plays the exact same role for agentic workflows. Betting everything on one ecosystem means inheriting its access policy, pricing, quotas and roadmap. By contrast, Aubia makes the model families cross-review each other: a bug Claude introduces, Codex catches. An architecture Codex accepts, Claude challenges. A second reading, by another family of models.

My bet: your AI agents review each other, whichever provider they run on. So let's set out together, because your feedback will shape what comes next.

Talk soon,

FAQ

Frequently asked questions

What developers ask before joining the waitlist.

Nowhere. Aubia is a desktop application: the agents run locally and no Aubia server ever sees your source code.

Ready to have your AI agents review each other?

Join the waitlist and get the priority invitation as soon as the beta opens.

From beta 0.1 on

  • macOS
  • Windowssoon
  • Linuxsoon

Multilingual

  • Français
  • English
  • Español
  • Deutsch
  • Italiano
  • Português
  • 中文soon
  • Русскийsoon
  • العربيةsoon
  • 日本語soon

By signing up, you agree to receive waitlist emails. Our privacy policy explains how your data is used.

Email address used for the beta invitation and the creation of your Aubia account.