{"id":"9c412678-f3fd-45be-b48e-f17189ee2f10","entityType":"agent","slug":"crewai-raquelmfdz-qa-agent-crew-showcase","name":"qa-agent-crew-showcase","canonicalUrl":"https://www.xpersona.co/agent/crewai-raquelmfdz-qa-agent-crew-showcase","canonicalPath":"/agent/crewai-raquelmfdz-qa-agent-crew-showcase","generatedAt":"2026-10-09T21:52:46.946Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T17:16:48.600Z","emptyReason":null},"description":"[In progress] Multi-agent AI QA pipeline (CrewAI + Playwright): risk analysis, test design, automation,failure triage, release report running live in GitHub Actions on free-tier LLMs only. qa-agent-crew A multi-agent QA automation showcase: five $1 agents that read a requirements doc, design test scenarios, write and run real $1 tests against a public demo site, analyze any failures, and publish a release-quality report — end to end, live, in GitHub Actions. **Hard constraint: free tier only.** No paid APIs, no credit card, anywhere. Every LLM call goes through a small fallback chain (Gemini → Groq → l","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/raquelmfdz/qa-agent-crew-showcase","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/raquelmfdz/qa-agent-crew-showcase","kind":"source"}],"safetyScore":66,"overallRank":19,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"[In progress] Multi-agent AI QA pipeline (CrewAI + Playwright): risk analysis, test design, automation,failure triage, release report running live in GitHub Act"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:16:48.600Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:16:48.600Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:16:48.593Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T17:16:48.600Z","lastCrawledAt":"2026-10-09T17:16:48.593Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T17:16:48.593Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-09T21:52:46.946Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-raquelmfdz-qa-agent-crew-showcase/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T17:16:48.600Z","emptyReason":null},"readme":"# qa-agent-crew\n\nA multi-agent QA automation showcase: five [CrewAI](https://github.com/crewAIInc/crewAI)\nagents that read a requirements doc, design test scenarios, write and run\nreal [Playwright](https://playwright.dev/python/) tests against a public\ndemo site, analyze any failures, and publish a release-quality report —\nend to end, live, in GitHub Actions.\n\n**Hard constraint: free tier only.** No paid APIs, no credit card,\nanywhere. Every LLM call goes through a small fallback chain (Gemini →\nGroq → local Ollama) so the pipeline degrades gracefully instead of\ndying the moment one free tier rate-limits you.\n\n## The 5-agent pipeline\n\n```mermaid\nflowchart LR\n    A[\"🔍 Risk Analyst<br/>reads requirements.md,<br/>ranks highest-risk areas\"]\n    B[\"📝 Test Designer<br/>writes Given/When/Then<br/>scenarios per risk\"]\n    C[\"🤖 Automation Engineer<br/>generates Playwright tests,<br/>saves to tests/\"]\n    D[\"🩺 Failure Analyst<br/>runs the suite,<br/>root-causes failures\"]\n    E[\"📊 Release Reporter<br/>writes report + go/no-go,<br/>reports/ + docs/index.html\"]\n\n    A --> B --> C --> D --> E\n```\n\nEach agent's output is fed into the next agent's context (CrewAI\n`Process.sequential`), so the Release Reporter's final verdict is grounded\nin everything upstream: the original risks, the scenarios designed for\nthem, what got automated, and what actually passed or failed.\n\n| # | Agent | Reads | Produces |\n|---|---|---|---|\n| 1 | **Risk Analyst** | `requirements.md` | Ranked list of highest-risk areas |\n| 2 | **Test Designer** | Risk list | Given/When/Then test scenarios |\n| 3 | **Automation Engineer** | Scenarios | Playwright Python tests in `tests/` |\n| 4 | **Failure Analyst** | Test run results (JSON/JUnit) | Root-cause analysis per failure |\n| 5 | **Release Reporter** | Everything above | `reports/release_report.md` + `docs/index.html` |\n\nThe target system is the public demo store [saucedemo.com](https://www.saucedemo.com),\nusing the `standard_user` / `secret_sauce` and other seeded test accounts\nit publishes on its own login page — no private staging environment, no\nsecrets to manage beyond LLM API keys.\n\n## Why the LLM fallback chain\n\nFree tiers rate-limit aggressively and can deprecate models without\nnotice. Rather than hardcode one provider, [`llm/factory.py`](llm/factory.py)\nbuilds a chain from whichever providers have credentials in the\nenvironment and retries the next one on auth/rate-limit/model-not-found\nerrors:\n\n1. **Gemini** (`gemini-flash-latest`) via the free Google AI Studio tier — primary. The \"-latest\" alias auto-updates to Google's current recommended Flash model, so a dated model ID (e.g. `gemini-2.5-flash`) doesn't quietly break when Google sunsets it for new users.\n2. **Groq** (`llama-3.3-70b-versatile`) free tier — secondary.\n3. **Ollama** (local `llama3.1`) — last-resort, local-only fallback (no daemon in CI).\n\nAll model IDs live in one place, [`config/models.py`](config/models.py), since\nfree-tier model names change fairly often.\n\n## Run locally\n\n```bash\ngit clone <this-repo-url>\ncd qa-agent-crew\n\npython3.11 -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt\nplaywright install --with-deps chromium\n\ncp .env.example .env\n# edit .env and add at least one of GEMINI_API_KEY / GROQ_API_KEY\n# (or install Ollama and `ollama pull llama3.1` for a fully local run)\n\npython main.py\n```\n\nGet free keys, no credit card:\n- **Gemini:** [aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)\n- **Groq:** [console.groq.com/keys](https://console.groq.com/keys)\n\nOn success, check `reports/release_report.md` and `docs/index.html` for\nthe final report, and `tests/` for whatever the Automation Engineer wrote.\n\nYou can also just run the checked-in sample tests without the agents:\n\n```bash\npytest tests/ -v\n```\n\n### Testing the pipeline itself\n\n`tests/` is the generated Playwright suite *against SauceDemo* -- what\nthe agents produce and analyze. The pipeline's own code (the LLM\nfallback chain, the report renderer) has a separate unit test suite that\nneeds no API keys or browsers, and runs first in CI so a plumbing\nregression fails in seconds:\n\n```bash\npytest tests_unit/ -v\n```\n\n## Run in CI (GitHub Actions)\n\n[`.github/workflows/qa-crew.yml`](.github/workflows/qa-crew.yml) runs the\nwhole pipeline live on every push to `main` and on manual trigger:\n\n1. Fork or push this repo, **and make sure it's Public** — public repos\n   get free/unlimited Actions minutes, private repos only get a limited\n   monthly quota.\n2. Add repo secrets: Settings → Secrets and variables → Actions → New\n   repository secret:\n   - `GEMINI_API_KEY`\n   - `GROQ_API_KEY`\n   (either one is enough to run; both gives you the fallback safety net.)\n3. Push to `main`, or trigger manually from the Actions tab\n   (\"QA Agent Crew\" → Run workflow).\n4. Watch the 5 agents think and act live in the Actions log. When the run\n   finishes, open the **Summary** tab of that run (not the log) to read\n   each agent's answer in its own collapsible section, labeled by agent\n   name, without digging through logs. The generated report is also\n   uploaded as a build artifact, and `docs/index.html` is updated in the\n   repo.\n\n### Publish the report with GitHub Pages (optional)\n\nSettings → Pages → Deploy from a branch → `main` / `/docs`. Your report\nwill be live at `https://<you>.github.io/qa-agent-crew/` and updates every\ntime the workflow runs.\n\n## Repo structure\n\n```\nqa-agent-crew/\n  agents/            Agent role/goal/backstory definitions + custom tools\n  tasks/              CrewAI task definitions wiring agents into a pipeline\n  tests/              Sample + agent-generated Playwright tests (target: SauceDemo)\n  tests_unit/         Unit tests for the pipeline's own code (fallback chain, renderer)\n  config/             Model IDs and provider fallback order (edit here)\n  reports/            Generated reports (gitignored except a checked-in sample)\n  docs/index.html     Published report, served via GitHub Pages\n  llm/                The fallback LLM factory\n  requirements.md     Sample requirements doc the Risk Analyst reads\n  main.py             Entrypoint — runs the full crew\n  .env.example        Copy to .env for local runs\n```\n\n## Notes / limitations\n\n- This is a **showcase**, not a production QA harness: error handling is\n  intentionally lightweight, and the \"risk analysis\" is only as good as\n  the free-tier model that produces it on a given run.\n- Free-tier LLM output isn't deterministic — the exact test scenarios and\n  report wording will vary run to run. The checked-in `tests/*.py` and\n  `reports/sample_release_report.md` show a representative baseline.\n- If every provider in the fallback chain fails (e.g. all free tiers\n  exhausted at once), the pipeline exits with a clear error rather than\n  hanging or silently producing garbage.\n","readmeExcerpt":"qa-agent-crew A multi-agent QA automation showcase: five $1 agents that read a requirements doc, design test scenarios, write and run real $1 tests against a public demo site, analyze any failures, and publish a release-quality report — end to end, live, in GitHub Actions. **Hard constraint: free tier only.** No paid APIs, no credit card, anywhere. Every LLM call goes through a small fallback chain (Gemini → Groq → l","codeSnippets":[],"executableExamples":[{"language":"mermaid","snippet":"flowchart LR\n    A[\"🔍 Risk Analyst<br/>reads requirements.md,<br/>ranks highest-risk areas\"]\n    B[\"📝 Test Designer<br/>writes Given/When/Then<br/>scenarios per risk\"]\n    C[\"🤖 Automation Engineer<br/>generates Playwright tests,<br/>saves to tests/\"]\n    D[\"🩺 Failure Analyst<br/>runs the suite,<br/>root-causes failures\"]\n    E[\"📊 Release Reporter<br/>writes report + go/no-go,<br/>reports/ + docs/index.html\"]\n\n    A --> B --> C --> D --> E"},{"language":"bash","snippet":"git clone <this-repo-url>\ncd qa-agent-crew\n\npython3.11 -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt\nplaywright install --with-deps chromium\n\ncp .env.example .env\n# edit .env and add at least one of GEMINI_API_KEY / GROQ_API_KEY\n# (or install Ollama and `ollama pull llama3.1` for a fully local run)\n\npython main.py"},{"language":"bash","snippet":"pytest tests/ -v"},{"language":"bash","snippet":"pytest tests_unit/ -v"},{"language":"text","snippet":"qa-agent-crew/\n  agents/            Agent role/goal/backstory definitions + custom tools\n  tasks/              CrewAI task definitions wiring agents into a pipeline\n  tests/              Sample + agent-generated Playwright tests (target: SauceDemo)\n  tests_unit/         Unit tests for the pipeline's own code (fallback chain, renderer)\n  config/             Model IDs and provider fallback order (edit here)\n  reports/            Generated reports (gitignored except a checked-in sample)\n  docs/index.html     Published report, served via GitHub Pages\n  llm/                The fallback LLM factory\n  requirements.md     Sample requirements doc the Risk Analyst reads\n  main.py             Entrypoint — runs the full crew\n  .env.example        Copy to .env for local runs"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"[In progress] Multi-agent AI QA pipeline (CrewAI + Playwright): risk analysis, test design, automation,failure triage, release report running live in GitHub Actions on free-tier LLMs only. qa-agent-crew A multi-agent QA automation showcase: five $1 agents that read a requirements doc, design test scenarios, write and run real $1 tests against a public demo site, analyze any failures, and publish a release-quality report — end to end, live, in GitHub Actions. **Hard constraint: free tier only.** No paid APIs, no credit card, anywhere. Every LLM call goes through a small fallback chain (Gemini → Groq → l","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":416,"uniquenessScore":65,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:16:48.600Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:16:48.600Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T21:52:46.946Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}