AI-powered cold outreach for students applying to startups and research labs.
Upload a resume, paste a target URL (company site, lab page, founder profile), and get a short, personalized cold email that references the target's recent work and connects it to the sender's background.
- Next.js 15 (App Router) + React 19 + TypeScript
- Tailwind CSS + shadcn/ui (Radix primitives)
- Supabase — auth (Google OAuth) + Postgres for user profiles
- OpenAI — resume parsing, research synthesis, draft generation
- Firecrawl — scrape target URLs into clean markdown
- Hunter.io — email lookup
- Vercel AI SDK
app/
api/ route handlers (auth, parse, research, draft, generate, profile)
layout.tsx
page.tsx single-page command center UI
components/ui/ shadcn primitives
lib/
prompts.ts prompt templates for parse/research/draft
supabase/ client, server, and service-role helpers
utils.ts
supabase/
migrations/ SQL schema
git clone https://github.com/<you>/cold-monster.git
cd cold-monster
npm install
cp .env.example .env.local # fill in keys
npm run devSee .env.example. You'll need:
NEXT_PUBLIC_SUPABASE_URL,NEXT_PUBLIC_SUPABASE_PUBLISHABLE_KEY,SUPABASE_SERVICE_ROLE_KEYOPENAI_API_KEYFIRECRAWL_API_KEYHUNTER_API_KEYNEXT_PUBLIC_SITE_URL(optional — auto-detected on Vercel)
Run the SQL in supabase/migrations/ against your Supabase project before first use.
npm run dev— local dev servernpm run build— production buildnpm run start— run the production buildnpm run lint— eslint
Work-in-progress side project. No stability guarantees; APIs and schema may change without notice.