Skip to content

iamvaibhavmehra/Haven

Repository files navigation

Haven – Local AI Co-Teacher

Haven is a local AI assistant designed to help teachers with some of the work that usually takes up far too much time: marking, worksheets, lesson planning, and general admin. The main idea behind Haven is simple — schools should be able to use AI without sending student data to the cloud.

Everything runs locally, and Parallax handles the compute across whatever machines are available on the network.

Why I Built This

Teachers are often overloaded with tasks that AI could easily help with, but most AI tools can’t be used in schools because they rely on external servers and third-party processing. Haven is meant to show that a fully local, privacy-safe alternative is possible.

What Haven Can Do

Essay marking

Upload a student’s work and Haven produces structured feedback, key strengths and weaknesses, and a score with justification. Conversations stay saved locally.

Worksheet generation

Give Haven a topic and it creates a clean, ready-to-use worksheet with questions and answers.

Lesson planning

Haven generates a full slide deck with simple, organised formatting and properly credited images.

Multiple chat threads

Teachers can keep separate conversations, and each one is stored locally so nothing is lost after refreshing.

Local memory

A small RAG setup (using Chroma) lets Haven remember useful details to improve responses over time.

Usage metrics

Haven shows token usage, most-used features, and how much cost is saved by running everything locally instead of paying for cloud inference.

How It Works

  1. The user opens Haven in a browser.
  2. Parallax detects available devices on the network.
  3. Each tool (marking, worksheets, planning) runs on local models.
  4. Outputs are stored on the machine, not on an external server.
  5. The system stays completely inside the school network.

Tech Stack

  • Frontend: Next.js, Tailwind
  • Backend: FastAPI, SQLAlchemy
  • Database / Memory: ChromaDB
  • AI Runtime: Parallax for local inference and device coordination

About

Haven - Parallax Hackathon Entry

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published