Skip to content
store
qa

Self-hosted alternatives to qa

5 self-hosted AI Skills apps to use instead, best rated first.

Top picks

  1. C

    claude-to-deerflow

    Launch

    claude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code

    Self-hosted

  2. O

    open-notebook

    Launch

    open-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O

    Self-hosted

  3. R

    Reactive Resume

    Launch

    Reactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish

    Open sourceSelf-hosted

  4. S

    self-hosted-funnel-launch

    Launch

    Self-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a

    Self-hosted

  5. G

    get-convex/convex-backend

    Launch

    Convex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca

    Self-hosted

About qa

Q

qa

QA-test a website or web app and return a 1-5 quality score

qa-browser-use is an agent skill from the Browser Use project that tests a website or web app by driving it with a real browser. It judges how well the site does what the user asked about and returns a score from 1 to 5, where 5 is flawless and 1 is broken, with the evidence behind the verdict. The output is a verdict rather than a dump of screenshots. The user supplies a target, either a URL or a local development server such as localhost:5173, and may name a flow or focus such as signup or search with filters. If no focus is given, the skill tests the most obvious happy path and says so in its report. Because the verdict is visual, the skill first checks whether the agent running it can see images. If it can, it drives the site, looks at the screenshots, and chooses between a single flow and a fan-out of several flows based on scale. If it cannot see images, it hands the judgment to Browser Use v2 cloud agents, whose own model reviews the page on the server and returns a pass or fail with a 1 to 5 score. When unsure, the skill assumes it cannot see images. It suits anyone who wants an evidence-backed read on how a site or flow works.

View qaAll AI Skills apps
Price
Free
Made by
browser-use
Category
AI Skills
Website
github.com/browser-use/browser-use/qa