Survival LLM
A free AI assistant and survival library (1.5 million offline articles) that runs on your own computer, with no internet. Shows the source of every answer. Mac and Windows.
翻譯準備中
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證Multi Hazard Classification with severity indexing AI
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Multi-hazard early warning for Bangladesh agriculture. HazardNet publishes dated
7- and 15-day hazard outlooks for all 64 districts of Bangladesh — eight hazard classes,
a severity value and a confidence score per district and forecast date, in two honestly
labelled severity tracks.
This repository and the website publish results and outputs only:檢視完整 README ↗Multi-hazard early warning for Bangladesh agriculture. HazardNet publishes dated 7- and 15-day hazard outlooks for all 64 districts of Bangladesh — eight hazard classes, a severity value and a confidence score per district and forecast date, in two honestly labelled severity tracks.
Live site: https://www.hazardnet.live
This repository and the website publish results and outputs only:
The following are research-private and are deliberately not published here or on the
site (see docs/PUBLICATION_POLICY.md):
Trained model files in Models/ are retained unadvertised; they are not part of the
published surface, and nothing in this repository offers them for download.
| Path | Purpose |
|---|---|
frontend/ | The public web application (results surfaces, maps, blog, auth) |
api/ | Serverless API: stored forecast reads, alerts, chat assistant, weather widget |
backend/ | Self-host Express backend (same result-serving surfaces) |
Models/ | Trained artifacts (unadvertised — not part of the public surface) |
docs/ | Publication policy, ops runbooks, attribution |
scripts/ | Site build, result publishing and QA tooling only |
# 1. Install and run the frontend (Vite dev server on :3000)
cd frontend && npm install && npm run dev
# 2. (Optional) the self-host API beside it. The Vite dev server proxies
# /api, /metrics and /health to :3001, so the API must listen there.
cd .. && npm install && npm run dev:api
# One process, one port instead: `npm run build` then `npm start` — the backend
# serves the built frontend and the API together on :3000.
Build for production: npm run build at the repository root (or cd frontend && npm run build).
Source code: MIT. If you use HazardNet outputs in academic work or an
operational product, please cite the repository (CITATION.cff).
HazardNet is a Master's thesis project, Department of Agrometeorology, Bangladesh Agricultural University. It is not an official warning service: official warnings come from the Bangladesh Meteorological Department and the Flood Forecasting and Warning Centre. For emergencies, call 999.