LogosAI is a source-grounded AI reading workspace for difficult texts. Import a text, select a passage for help, run a close reading, and keep notes and AI outputs attached to the source context.
- Import pasted text and local
.txtor.mdfiles. - Explain, translate, define vocabulary, and annotate selected passages.
- Create close readings for a paragraph or full document.
- Keep reading sessions, notes, and AI entries with the signed-in user.
The recommended path uses Docker Compose:
make upOpen http://localhost:5173. Use make logs to follow service output and
make down to stop the stack.
For hot reload, run the backend, Cloudflare gateway, and frontend separately. The gateway setup, required local secrets, and commands are in Cloudflare Operations.
The Docker stack seeds this account with a sample reading session:
Email: local-test@logosai.invalid
Password: LogosAI-local-test-2026!
Restarting make up resets its data. Use a separate account for personal local
work.
Backend:
cd backend
uv run pytest
uv run ruff check .Frontend:
cd frontend
npm run lint
npx tsc --noEmit
npm test
npm run buildCloudflare gateway:
cd cloudflare
npm run check- Cloudflare Operations: local gateway setup, deployment, OAuth, and secrets.
- Project Reference: product boundaries, architecture, and runtime contracts.
- Roadmap: priorities and evidence gates.
- Cloud architecture ADR: auth, data ownership, and credential boundaries.
