[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-80318":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":16,"starSnapshotCount":16,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},80318,"agent-qa","vostride\u002Fagent-qa","vostride","The self-improving Agentic QA harness with Memory. Write tests in natural language.\u2028 Catch regressions before releases ship.","https:\u002F\u002Fvostride.com\u002Fagent-qa",null,"TypeScript",94,4,3,1,0,11,16,28,33,72.9,"Other",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"agents","ai","ai-agents","ai-testing","appium","chatgpt","claude-code","clawdbot","codex","developer-tools","end-to-end-testing","fair-source","llm","mcp","memory","moltbot","openclaw","playwright","testing","webdriverio","2026-06-12 04:01:27","\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fvostride\u002Fagent-qa\u002Fmain\u002Fdocs\u002Fassets\u002Freadme-banner.png\" alt=\"agent-qa banner\"\u002F>\n\n  [![npm](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdm\u002Fagent-qa?style=flat&colorA=13110f&colorB=196872)](https:\u002F\u002Fnpm.chart.dev\u002Fagent-qa?primary=neutral&gray=neutral&theme=dark)\n  [![npm version](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Fagent-qa.svg?style=flat&colorA=13110f&colorB=196872)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fagent-qa)\n  [![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvostride\u002Fagent-qa?style=flat&colorA=13110f&colorB=196872)](https:\u002F\u002Fgithub.com\u002Fvostride\u002Fagent-qa\u002Fstargazers)\n\n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\">Docs\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvostride\u002Fagent-qa\u002Ftree\u002Fmain\u002Fdemo-project\">Demo\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvostride\u002Fagent-qa\u002Fissues\">Issues\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n## agent-qa\nThe self-improving Agentic QA harness with Memory\n\nWrite tests in natural language for web and mobile. agent-qa learns from past runs, adapts to UI changes, and catches regressions before you ship.\n\n[Docs](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa) | [Quickstart](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\u002Fquickstart)\n\n## Features\n\n- **Write tests in natural language for web and mobile**: Define actions and assertions in human language while agents work from visible roles, labels, and screen state.\n- **Self-healing test execution**: When any sub-action, such as click, fill, or select, fails, agent-qa re-observes the UI and tries a different path in the same run. Tests recover from UI drift and flaky interactions instead of failing on the first broken action.\n- **Self-improves with Memory**: With every test run, agent-qa builds execution memory from product, suite, and test observations, then adds that context to future runs. agent-qa also curates memory from steps that were healed during execution, helping future runs avoid the same mistake.\n- **Built for humans and machines**: A polished dashboard and CLI for developers, plus MCP and skills for coding agents.\n- **Accelerate runs with smart Cache**: The action cache reuses validated plans across similar subsequent test runs, reducing planner work, token usage, and runtime overhead.\n- **Run sandboxed hooks during tests**: Run Node, Bun, Python, or Bash hooks in isolated Docker containers to set up environments, call APIs, seed fixtures, tear down state, or pass structured outputs back into the active test run.\n- **Open source, reviewable QA**: The harness is open source, and tests, configs, hooks, memory, and suite logic all live as version-controlled code, so every change can be diffed, reviewed, reused, and shared across teams.\n- **Bring your own LLM**: Run tests with the model of your choice via OpenAI- and Anthropic-compatible endpoints, Gemini, local or open-source models, and subscriptions like Codex and Claude Code.\n\n## Quickstart\n\nInstall the package:\n\n```sh\nnpm install -D agent-qa\n```\n\nFor Codex or Claude Code subscription auth, also install:\n\n```sh\nnpm install -D @vostride\u002Fagent-qa-subscription-auth\n```\n\nInstall Docker before using hooks. agent-qa runs hooks in a sandboxed runtime, and Docker is required for the Node, Bun, Python, and Bash hook containers.\n\nInitialize agent-qa and install the runtime support you need:\n\n```sh\nnpx agent-qa init\nnpx agent-qa install-browsers --chromium\n# Mobile projects:\nnpx agent-qa install-mobile-drivers --all\n```\n\nStart the dashboard, complete auth, and run tests from the UI:\n\n```sh\nnpx agent-qa dashboard --open\n```\n\nFor the full setup flow, use the [quickstart](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\u002Fquickstart).\n\n## CLI\n\nRun tests from the CLI:\n\n```sh\nnpx agent-qa run tests\u002Fhacker-news-top-story.yaml\n```\n\n## Docs\n\n- [Full docs](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa)\n- [Quickstart](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\u002Fquickstart)\n- [CLI reference](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\u002Fcli)\n- [Dashboard](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\u002Fdashboard)\n- [Configuration](https:\u002F\u002Fvostride.com\u002Fdocs\u002Fagent-qa\u002Fconfiguration)\n- [License](LICENSE.md)\n- [Notice](NOTICE.md)\n","agent-qa 是一个具有记忆功能的自优化质量保证工具，支持使用自然语言编写测试脚本。其核心功能包括通过自然语言定义Web和移动应用的测试用例、自我修复执行以应对UI变化、以及基于历史运行数据不断优化自身性能。它特别适用于需要频繁迭代且希望在发布前捕获回归错误的软件开发场景中。此外，agent-qa 还提供了智能缓存加速测试过程、沙盒化环境设置等功能，并允许用户选择不同的语言模型来运行测试。整个框架开源且易于审查，便于团队间协作与复用。",2,"2026-06-11 04:00:18","CREATED_QUERY"]