[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-93509":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":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":15,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":16,"rankGlobal":10,"rankLanguage":10,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":18,"hasPages":18,"topics":20,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":10,"trendingCount":15,"starSnapshotCount":15,"syncStatus":14,"lastSyncTime":28,"discoverSource":29},93509,"market-pilot","Dgeloe4-yb\u002Fmarket-pilot","Dgeloe4-yb","Evidence-grounded market research prototype with traceable AI workflows.","https:\u002F\u002Fmarketpilot.worldon.ai\u002F",null,"JavaScript",101,1,2,0,40.9,"Apache License 2.0",false,"main",[21,22,23,24,25],"ai-product-management","fastapi","llm","market-research","react","2026-07-22 04:02:09","# Market Pilot\n\nMarket Pilot is an evidence-grounded market research prototype that turns public market signals into traceable research workflows.\n\n[Live product](https:\u002F\u002Fmarketpilot.worldon.ai\u002F) · [中文说明](README.zh-CN.md)\n\n## Why it exists\n\nAI can summarize large amounts of market conversation quickly, but a polished summary is not the same as inspectable evidence. Market Pilot explores a stricter workflow: preserve source-grounded signals, separate direct evidence from inference, mask personal identifiers, and make uncertainty visible in the final report.\n\n## Current capabilities\n\n- Build research panels from collected public signals.\n- Generate de-identified persona cards for analysis.\n- Route and answer research questions through evidence-aware prompts.\n- Summarize consensus, disagreement, limitations, and supporting signals.\n- Provide a React product interface backed by a FastAPI service.\n\nThis repository is a product prototype. Demo data must be labeled as sanitized, and data connectors or model-backed runs require your own authorized provider credentials.\n\n## Architecture\n\n- Frontend: React 18, Vite 6, Tailwind CSS 4\n- Backend: FastAPI\n- Local routing: the frontend calls `\u002Fapi`; Vite proxies requests to `http:\u002F\u002Flocalhost:8001`\n- Research pipeline: collection, masking, panel construction, evidence-aware answering, aggregation, and report rendering\n\nSee [docs\u002Farchitecture.md](docs\u002Farchitecture.md) for the component map.\n\n## Local setup\n\nRequirements: Node.js 24+, npm 11+, Python 3.13+, and Git.\n\n```powershell\ngit clone https:\u002F\u002Fgithub.com\u002FDgeloe4-yb\u002Fmarket-pilot.git\nSet-Location market-pilot\nnpm.cmd ci\npython -m venv .venv\n.\\.venv\\Scripts\\python.exe -m pip install -r collector\\requirements.txt\n```\n\nReview `.env.example`, then export only the variables you need into the process environment. The application does not auto-load `.env` files.\n\nStart the API:\n\n```powershell\nSet-Location collector\n..\\.venv\\Scripts\\python.exe -m uvicorn api.app:app --port 8001\n```\n\nStart the frontend from the repository root in another terminal:\n\n```powershell\nnpm.cmd run dev\n```\n\nThe frontend runs on `http:\u002F\u002Flocalhost:5173`. Some research workflows remain unavailable until you provide your own authorized API credentials through the process environment.\n\n## Tests\n\n```powershell\nnpm.cmd run build\nGet-ChildItem collector\\test_*.py | ForEach-Object {\n  Push-Location collector\n  try { ..\\.venv\\Scripts\\python.exe $_.Name } finally { Pop-Location }\n  if ($LASTEXITCODE -ne 0) { throw \"Failed: $($_.Name)\" }\n}\n```\n\n## Data and privacy\n\nDo not commit credentials, raw scraped data, user images, local databases, or production run outputs. Use only data you are authorized to collect and process. Public examples must be synthetic or explicitly sanitized.\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md). Security reports should follow [SECURITY.md](SECURITY.md).\n\n## License\n\nApache-2.0. See [LICENSE](LICENSE).\n","2026-07-20 02:30:03","CREATED_QUERY"]