Orbis QA v1.0.0 has launched — free during launch

QA tests you describe in English. Run by an agent that actually thinks.

Orbis QA turns plain-English scenarios into real browser runs — clicks, types, recovers, asserts. No selectors. No fixtures. No cloud. Your scenarios stay on your laptop and the LLM bill goes to your own key.

  • No selectors. Works on any framework or UI change.
  • Bring your own LLM key — runs entirely on your machine.
  • Multi-role flows, recovery, suites, run-vs-run diffs.
Apache 2.0macOS · Windows · LinuxNo account required
Live Runrunning
run_8a3b94…
navigate→ app.example.com/login0.4¢
type@email ← "qa@example.com"0.6¢
click@signin-button0.5¢
asserttext_visible :: "Welcome back"0.3¢
click@checkout-cta
5/25 steps1.8¢ spent
beta
On your machine

No cloud, no telemetry by default. Scenarios, runs, screenshots — all live in your data folder, only on your laptop.

Bring your own LLM

Anthropic, OpenAI, Gemini, DeepSeek, xAI, Mistral, OpenRouter, Ollama, or any OpenAI-compatible endpoint. The key is encrypted in your OS keychain — Orbis never sees it.

Built for trust

Custom protocol sandbox for screenshots, locked DevTools in production, error-message scrubbing, and integrity-checked asar bundle.

How it works

Four steps. No selectors.

You describe what to test. The agent observes, reasons, acts, and asserts in a loop until your scenario is done — or it tells you why it couldn't be.

  1. 1
    Perceive

    Snapshot the page — ARIA tree, screenshot, recent network slice.

  2. 2
    Reason

    The planner LLM picks the next action + assertions, with the scenario prose in context.

  3. 3
    Act

    Click, type, scroll, navigate — driven through the real browser, not a headless simulation.

  4. 4
    Assert + recover

    Check assertions. If something failed, the recoverer LLM diagnoses + decides retry/skip/abort.

Features

Everything an SQA needs. Nothing they don't.

See full feature list

Plain-English scenarios

Describe the user journey in two sentences. The planner LLM figures out clicks, types, and assertions step-by-step.

Reasoning recovery

When a step fails, a dedicated diagnosis call decides whether to retry, skip, or abort — not a brittle 'retry 3 times'.

Suites

Group scenarios into named batches. Run nightly smoke tests as one command; aggregate pass/fail at the end.

Run-vs-run compare

Side-by-side diff with drift highlighting. Spot what actually changed between yesterday's run and today's.

Live progress + cost cap

Watch every step stream live with screenshots. Per-run cents cap stops a runaway scenario from draining your key.

Flake detection

Pass-rate per scenario over the last 20 runs. Real flake telemetry without setting up dashboards.

Why Orbis

Playwright + Cypress are great. If you have engineers to maintain them.

The selectors-and-fixtures way
  • Write a script. UI ships. Selectors break. Rewrite.
  • Every new flow needs a new test, fixtures, and CI plumbing.
  • Flakes get retried until they're 'green' enough.
  • QA people who can't code wait for engineers.
The Orbis way
  • "Sign in, approve the pending subscription, verify status." → it runs.
  • No selectors. UI redesigns don't break your scenarios.
  • Recovery sub-loop diagnoses failures; flakes get flagged with %.
  • SQAs ship scenarios on their own. Engineers stay focused.
v1.0Free during launch · Paid plans coming soon

Start running scenarios in under a minute.

Download Orbis QA, paste your LLM key (Gemini 2.0 Flash is a cheap fast default), and describe your first test. No account. No tracking.

macOS · Windows · Linux Boots in ~15s