Skip to content

Jev directory

Uno AI Speak

An audio-first Socratic language-tutoring web app whose lessons stay on track with a TypeSafe/Jev Governor: System 1 evaluates every turn for topic drift, FSM state and Socratic compliance, never generating content. FastAPI backend, Next.js frontend.
Stars
0
Language
Python
Reading time
2 min
Published by
Community
Author
haseebqureshii
Last verified
Oct 2026

Highlights

  • Pairs a low-latency full-duplex speech engine with a deterministic System 1 guardrail the README calls the TypeSafe / Jev Governor.
  • The governor evaluates every turn in under 150 ms for topic drift, FSM state correctness and Socratic compliance, per the README.
  • System 1 does not generate content: it validates boundaries and emits INTERRUPT_SIGNAL or STATE_CHANGE commands to keep lessons on track.
  • Backend is FastAPI with WebSockets; frontend is Next.js, Tailwind and TypeScript; prerequisites are Python 3.11+, Node 20+ and pnpm or npm.

Watch out

README reviewed 2026-10-17 from the round-eleven capture, which is truncated mid-command in the backend setup block: the full install steps, speech API choice and any evaluation results are not in the digest, and the under-150 ms figure is the README's own claim.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai