Which programming languages does Dualzo support?

Any language. Dualzo detects the ecosystem, parses the manifest, and validates using the repository's own install, lint, typecheck, test, and build commands, so support does not depend on hand-written per-language analyzers.

Does Dualzo merge code automatically?

No. Dualzo opens a pull request and stops. A human always reviews and merges. Nothing executes at all until a person approves the plan.

Which AI models can Dualzo use?

Claude, Codex, or Gemini — chosen per repository or per task, and run on your own provider credentials.

How is the generated code validated?

Each task runs your repository's own commands inside an ephemeral container with CPU, memory, and time limits, network access only during dependency install, and no Dualzo secrets in the environment. A pull request cannot be opened while validation is failing.

How much does Dualzo cost?

One plan: Team at $119 per month with 5 seats included. Free credits are occasionally offered as a signup promotion — check the app for current offers. Model provider usage is billed to you separately by that provider.

 ____                 _
|  _ \               | |
| | | | _   _   __ _ | | _____ _____
| | | || | | | / _` || ||_  / / ___ \
| |_| || |_| || (_| || | / /_ | |_| |
|____/  \___/  \__,_||_|/____| \___/
             governance for AI code

An AI development governance platform

Ship AI-written code
you can actually trust.

A GitHub issue or a prompt becomes a plan, a human approval, sandboxed validation on your repo's own tests, and a pull request — every step audited. Pick the model that does the work: Claude, Codex, or Gemini.

Get started free See how it works

No card required · your repos, your model keys

execution #218 · @kathy/flipdisc

# issue: "Add rate limiting to the public API"

plan → 3 tasks · risk: low · confidence 82/100

approve → waiting for a human ✋

validate → install · lint · test ✓ (sandbox)

pr → opened #441 ▌

More time for the code you want to write.

◆

GitHub App

Connect a repo of any language. Dualzo indexes it and opens the PR for you.

▣

Sandbox validation

Runs your repo's own install / lint / test / build in an ephemeral container.

✋

Human approval

Nothing runs until a person approves the plan. Signed links or the web view.

◈

Full audit trail

Every webhook, plan, approval, and PR is recorded, append-only.

How Dualzo ships a change

Four steps. A human stays in the loop on the one that matters.

Select a repo and describe the work.

Write a prompt in-app, or drop the dualzo label on a GitHub issue to start a task from there.

@kathy/flipdisc ▾

main ▾

Add rate limiting to the public API and cover it with a feature test.

Dualzo clones it and builds a plan.

It slices Project Memory for context and asks your chosen model — Claude, Codex, or Gemini — for an ordered, task-by-task plan.

Here is my plan:

Three tasks across the middleware and its tests.

Update 4 files ▾

You review the plan and the diff.

Approve, reject, or tell it what to change. Approval is required — code never runs on a plan no one signed off.

10 "middleware": [

11 − "throttle:60,1",

11 + "throttle:api",

12 ],

It validates, then opens a PR.

Each task is validated in a sandbox. A PR is impossible to open while validation is failing — enforced in code.

◆ Open pull request validation ✓

Pick the model that does the work

Dualzo is the governance layer — plans, approvals, validation, audit. The model underneath is yours to choose, per repository or per task. Runs on your own credentials.

Claude

Default

Claude Code, headless

›Anthropic Claude models
›Deep multi-file edits
›Your Anthropic key or CLI login

Codex

Available

OpenAI Codex CLI

›OpenAI models
›Great at focused fixes
›Same plan → approve → PR flow

Gemini

Available

Google Gemini CLI

›Gemini models
›Long-context planning
›Same governance guarantees

Simple, transparent pricing

One plan. No seat tiers, no usage surprises on Dualzo itself.

✦ EVERYTHING INCLUDED

Team plan

$119 / month

5 seats included · billed via Paddle · cancel anytime

✓Any language, any repo size
✓Claude, Codex, or Gemini — your own keys
✓Sandboxed validation on every task
✓Human approval on every plan
✓Full, append-only audit trail
✓Email support

Get started free

Model provider usage is billed separately by your provider.

Questions people ask first

Which programming languages does Dualzo support?: Any language. Dualzo detects the ecosystem, parses the manifest, and validates using the repository's own install, lint, typecheck, test, and build commands, so support does not depend on hand-written per-language analyzers.
Does Dualzo merge code automatically?: No. Dualzo opens a pull request and stops. A human always reviews and merges. Nothing executes at all until a person approves the plan.
Which AI models can Dualzo use?: Claude, Codex, or Gemini — chosen per repository or per task, and run on your own provider credentials.
How is the generated code validated?: Each task runs your repository's own commands inside an ephemeral container with CPU, memory, and time limits, network access only during dependency install, and no Dualzo secrets in the environment. A pull request cannot be opened while validation is failing.
How much does Dualzo cost?: One plan: Team at $119 per month with 5 seats included. Free credits are occasionally offered as a signup promotion — check the app for current offers. Model provider usage is billed to you separately by that provider.

Ship AI-written code you can actually trust.