Open-Source Agentic QA Harness with Memory

In plain words

This is an open-source testing framework designed for quality assurance of AI agents. It provides a harness system with memory capabilities that allow testers to build and run automated QA tests for agentic systems. The tool is intended for developers and QA teams working with AI agents who need structured testing and validation. Live demos are available on the project website, and the complete codebase is available on GitHub for inspection and contribution.

written from the facts on this page · September 2026

From the sources

Agent QA is an AI-powered testing extension that records user journeys, provides visual comparisons, and automates API test coverage—all in one place. Let AI detect issues and guide fixes with auto prompts. Capture real interactions, run screenshot-based tests, and analyze screens, components, and APIs in seconds. No scripts. No setup. Just test as you code and reduce regressions and manual QA effort.

Give coding agents a self-improving QA agent. Run natural-language web and mobile tests through CLI or MCP, with reviewable memory and evidence in your repo.

Give your coding agents a QA agent that learns your app. Run natural-language tests across web and mobile, build memory with every run, and catch regressions before you ship. Write actions and assertions in plain English; agent-qa resolves them against the live interface. Describe the behavior once; it stays as reviewable YAML in your repository. Name visible controls and labels instead of brittle selectors. Turn successful runs into reviewable, evidence-backed memory that makes every future run faster. Every learned fact ships with its evidence as files in your repository. New knowledge must pass replay and live evidence before guiding a run. Reuse proven flows and supersede stale facts…from vostride.com

• 
  QA.tech 1.02025 · qa.tech · ▲413

  Hi, I'm Daniel, CEO of QA.tech. We've spent the past 18 months developing a cool tool that allows you to run end-to-end tests on any web application using natural language. Check it out and let us know what you think! I used to be a CTO at a B2C marketplace and was taken aback that all qa agencies we talked to wanted to create a custom suite of tests from scratch. Even though we were essentially a e-com with the same functionality as everyone else. Why weren't there any best practices? Some time later my co-founders and I had moved on and were looking for the next thing to do. AI agents…

• 
  TestSprite 1.02025 · testsprite.com · ▲753

  First AI agent automating entire software testing process

• 
  AgentaNov 2025 · agenta.ai · ▲362

  Open-source prompt management & evals for AI teams

• 
  QAgentSep 2026 · qagent.in · ▲82

  Automated QA for AI agents. Stop shipping on vibes.

• 
  Open Bias – proxy that enforces agent behavior at runtimeApr 2026 · github.com · ▲21

  Open Source Reliability Harness: Make your agents follow rules. One line of code to‎ ‎enforce, trace, and improve. ‎ ‎ - GitHub - open-bias/open-bias: Open Source Reliability Harness: Make your agents follow rules. One line of code to‎ ‎enforce, trace, and improve. ‎ ‎

• 
  I Built a Sandbox for AgentsJan 2026 · github.com · ▲31

  Contribute to vrn21/bouvet.com development by creating an account on GitHub.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 16d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 18d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  Onepin▲384

  AI voiceover with every name, price and date said right

  AI · 30d ago · onepin.ai

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 28d ago · world.pixverse.video

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com