Skip to main content
agent-qa on GitHub,230stars

Momentic rents you AI testing. agent-qa gives you a QA agent that remembers, and it's yours.

Momentic is a hosted product surface with vendor-controlled models and pricing. agent-qa puts plain-English tests, LLM choice, hooks, memory, and run evidence in the repo you already own.

Try agent-qa, the source-available QA agent that rebuilds testing around repo memory.

Get StartedExplore Live Demo

agent-qa vs Momentic

Capabilityagent-qaMomenticDetails
Source accessMomentic is not positioned as a repo-owned framework with published source, so behaviour you disagree with is a support ticket. With agent-qa it is a pull request.
Repo-owned YAMLMomentic keeps the test intent inside its own product. agent-qa keeps intent, config, hooks, memory and suites beside the code they cover, where your engineering process already works.
Coding-agent nativeA coding agent cannot click through a hosted editor. agent-qa ships MCP tools, packaged Skills and a CLI, so the agent that changed the code writes the test, runs it and reads the failure without leaving the loop.
Bring your own LLMWhoever picks the model sets your quality ceiling and your bill. agent-qa lets you point at any provider, any compatible endpoint, or a model on your own hardware, and change it in one line.
Local and CI executionOne command on a laptop, in CI, and from an agent. No run depends on somebody else's control plane being up, and nothing queues behind another tenant.
Web and mobile QAWeb, Android and iOS from the same natural-language flow and the same evidence model. The surface is a target named in a file, not a different product tier.
Memory, cache, hooksExecution memory, a validated action cache and sandboxed hooks compound. A suite that has been running a month is faster, cheaper and better informed about your app than the day it was written.
No platform lock-inEvery durable asset stays in your repository. Cancel agent-qa tomorrow and the tests, the memory and the evidence are still there and still readable.
Browser controlagent-qa is designed for browser and mobile automation workflows where teams want the execution path visible and owned.

Why teams switch from Momentic

Your tests stop being hostages

Every test you write in Momentic makes leaving Momentic more expensive. That is not an accident, it is the business model. Every test you write with agent-qa is a YAML file in your repository: reviewed in a pull request, portable to any runner, and still yours the day you cancel.

You pick the model, not the vendor

Momentic decides which AI runs your tests, when it changes, and what it costs you. agent-qa is bring-your-own-model: swap providers in one line, put a cheap model on smoke tests and a strong one on the flow that matters, or run against the internal endpoint your security team already signed off.

The editor is not the product

Momentic's polish lives in its hosted editor, which is exactly the problem. The durable asset in QA is the test intent, and Momentic keeps it in their app. agent-qa keeps it in files your team reviews, diffs, and ships like any other code.

If you want AI testing as a subscription product, Momentic is a fine one. If you want AI testing as an engineering capability your team owns, with memory that compounds instead of a bill that does. That's agent-qa.

Frequently asked questions

Is agent-qa a good Momentic alternative?

Yes, and the reason is structural rather than a feature count. Momentic is a hosted AI testing platform where tests, execution, and AI model choice live inside the vendor's product, which means the asset you are building lives on their side of the line. agent-qa is a source-available QA agent with no paid tier, governed by FSL-1.1-ALv2: tests are plain-English YAML in your repository, runs execute on your laptop, in your CI, or from your coding agent, and every run writes back into memory committed beside the tests. The suite gets better at your app whether or not you renew anything.

How much does agent-qa cost compared to Momentic?

Momentic is priced on vendor-set subscription plans on its hosted platform, so the bill tracks how much you test. agent-qa has no paid tier, no seats and no platform fee; FSL-1.1-ALv2 governs permitted use. You pay for the model tokens and infrastructure you already control, on the provider you choose, and the validated action cache takes roughly 60% of the tokens off a matched rerun. Adding coverage does not add a line item.

How do I migrate from Momentic to agent-qa?

You are re-describing intent, not porting code, which is why this is far smaller than a normal test migration. Your Momentic tests already describe user flows in high-level terms, so translating them into agent-qa's plain-English YAML is close to copy-editing. Run npx agent-qa init, write each critical flow as a plain-English YAML test, and let the runtime work out the selectors and the recovery. Most teams move a smoke suite in an afternoon, and there is nothing to un-pick later because the output is files in your own repository.

Does agent-qa cover web and mobile like Momentic?

Yes, and from the same file. agent-qa runs end-to-end tests on web, Android and iOS with one natural-language format, one memory store and one evidence model, so a flow written once survives being pointed at another surface. Momentic is positioned primarily around web application testing; agent-qa treats mobile as a first-class target, not an add-on.

Can I use my own LLM with Momentic or agent-qa?

agent-qa is bring-your-own-LLM by design, configure any supported provider or compatible endpoint, route cheap models to smoke tests and stronger ones to complex flows. Momentic's AI execution runs on vendor-controlled models inside its platform.

Sources

This page is based on public product and documentation sources. Verify current features and pricing with each vendor before making a purchase decision.

Where agent-qa pulls ahead of Momentic

The parts of agent-qa that answer what Momentic leaves you carrying.

Execution memory

A run that passes leaves evidence: elements that resolved, a flow that worked, and timings that are real. agent-qa distils that evidence into durable facts, procedures, cautions and measurements. Each becomes a reviewable bundle committed next to your tests. Nothing steers a run until the evidence says it should, and once it does, the next run replays what already works instead of deriving it again.

Learn about memory

Bundles you can review

Each thing learned is a directory in your repository: the record, the evidence behind it, and the artifacts that justify it. Read it in a pull request.

Proven before it is used

New knowledge is born a candidate. Offline replay and attributed evidence from live runs decide whether it ever reaches a planner.

Warm runs get faster

A flow that already worked is replayed rather than re-derived, and stale facts are superseded instead of quietly served.

Self-improvement

agent-qa gets better at your app on its own. After every run it works out what actually broke, learns the part worth remembering, and proves that lesson before it acts on it. Flaky tests and broken environments are set aside, so a bad afternoon never turns into a bad habit.

Learn about the curator

Diagnosis first

Every failure is diagnosed before anything is learned from it. Flaky tests and broken environments are set aside rather than studied.

Proved, then trusted

Nothing new is believed on day one. A lesson has to hold up against past runs and earn its place on a live one before the agent uses it.

It never rewrites itself

It improves what it knows about your app and suggests rule changes. It never edits its own prompts or code, and it cannot grade its own homework.

Version controlled, built for teams

Tests, suites, hooks, and the workspace config are files you write. What it learns about your app, the bugs it files, the rules you assert, and the skills an authoring agent uses are files agent-qa writes, in a visible directory beside your tests rather than in a database you cannot read. All of it is committed, so a new memory bundle arrives as a diff in a pull request with the evidence that justified it. Only derived indexes and binary run artifacts are gitignored, because they rebuild from what is committed. A teammate, a coding agent, and CI check out one commit and get the same brief.

Learn about configuration

Files, not a database

What you author and what the agent learns sit next to each other as committed files. Nothing it knows is locked in a store you cannot open.

Learning arrives as a diff

A new memory bundle or a filed issue shows up in a pull request, with the evidence behind it, and is approved the way any other change is.

Everyone reads the same commit

A teammate, a coding agent, and CI work from one checkout, so no run is quietly using state that nobody else has.

Bring your own model

The model is a setting, not a rewrite. Point a workspace at an OpenAI or Anthropic compatible endpoint, at Gemini, at an open-weight model running on your own hardware, or at a subscription your team already pays for like Codex or Claude Code, and override it on the one test that needs something stronger than the rest. Nothing about how a test is written changes when the model does, because the test says what should happen and the model is only what works out how to get there. There is no vendor to be locked to and no key of ours to buy.

Learn about LLM providers

Swap it in one line

The provider, the endpoint, and the model are config. Change them and every test you have already written runs against the new one, unedited.

The seat you already pay for

Account-backed authentication works where the provider allows it, so a Codex or Claude Code subscription can drive runs without a second bill.

Or nothing leaves the building

Point it at an open-weight model on your own hardware when the code under test is the kind that cannot go to somebody else's API.

* This comparison is based on publicly available information. Product capabilities and pricing can change; verify details with each vendor before making a purchase decision.