TreeMap
A free, open-source disk-space visualizer. Squarified treemap, duplicate hunting, disk-full forecasting, and cleanup that only ever moves files to the Trash.
A personal RAG chatbot that answers questions using your own uploaded documents, with cited sources.
ProductivityTypeScript · CSSGitHub @SAAD-HAYATOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Loading the full README. The saved excerpt is shown below.
A personal knowledge-base chatbot: upload your notes (PDF/Markdown), ask
questions, get answers grounded in your own documents.
• Frontend: Next.js (App Router) + TypeScript + Tailwind v4 + shadcn/ui —
originally generated via Lovable, now migrated into this repo (see
docs/api-contract.md for the exact prompt and the contract it expects)
• Backend: Next.js API routes (app/api/)
• Database + vector store: Supabase (Postgres + pgvector)
• LLM + embeddings: OpenRouter (free-tier models)Read the full README ↗A personal knowledge-base chatbot: upload your notes (PDF/Markdown), ask questions, get answers grounded in your own documents.
docs/api-contract.md for the exact prompt and the contract it expects)app/api/)The backend is built in phases, each documented in docs/phase-N-*.md.
Every phase doc has a goal, a task list, files to touch, and acceptance
criteria. Build them in order. Phases 1-6 were the original roadmap;
Phase 7 (auth) was added afterward as new scope.
| Phase | Focus |
|---|---|
| 1 | Basic RAG loop (ingest → embed → store → retrieve → generate) |
| 2 | Testing foundation (Vitest + CI) |
| 3 | Tool calling |
| 4 | Agentic loop (ReAct-style retrieval) |
| 5 | Advanced retrieval (hybrid search, query rewriting, citations) |
| 6 | Eval harness |
| 7 | Auth (Google-only SSO, per-user data isolation) |
If you're using an AI coding agent (Claude Code, Cursor, etc.) to help build
this, point it at AGENTS.md first — it has the ground rules.
app/
layout.tsx, page.tsx, globals.css frontend (client-rendered)
error.tsx, not-found.tsx
login/ Phase 7: sign-in page
auth/callback/ Phase 7: OAuth code exchange
api/ backend route handlers
components/ ui/ (shadcn), ai-elements/, notes-rag/
hooks/
lib/ utils.ts, notes-rag-api.ts (frontend) + backend logic
supabase.ts (admin/service-role client)
supabase-server.ts, supabase-browser.ts (Phase 7: @supabase/ssr clients)
middleware.ts Phase 7: session refresh + page-route auth redirect
db/ schema.sql
docs/ api-contract.md + phase docs
tests/ Vitest suites
scripts/ eval.ts
npm install.env.example to .env and fill in your Supabase + OpenRouter keys
(including the Phase 7 NEXT_PUBLIC_SUPABASE_* ones — see Supabase's
dashboard under Project Settings > API)db/schema.sql against your Supabase project (SQL editor, or supabase db push)npm run dev, then sign in with Google at /login