New Backend (Node.js)

This repo now includes a production-oriented, stateless AI backend in backend/.

Key rules implemented:

  • Backend (Node.js Fastify) is the brain and owns memory (MongoDB)
  • AI model is stateless; it receives one final prompt only via the /api/analyze endpoint
  • Prompt builder lives in backend/src/services/promptBuilder.js
  • Memory is stored in MongoDB (ShortTerm and LongTerm collections)

See backend/README.md for setup and quickstart.

Note: The legacy PostgreSQL adapter has been removed; model-side persistence now uses the Node.js backend and MongoDB. If you previously used psycopg2 or src/storage/db.py, migrate to the backend API endpoints.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support