jev-system-one GitHub avatar by haseeb-heaven

haseeb-heaven /

Voice & Conversation

jev-system-one

A terminal Q&A app where OpenAI writes answers and Jev sets response policy and reviews drafts.

License: MITLanguage: TypeScriptLast push: 9/17/2026#voice-conversation#evaluation-benchmarks#typed-decisions

What Jev Does in this Architecture

Judges response mode, depth, uncertainty and draft quality inside a LangGraph workflow.

Key Architecture Benefit

Displays the answer alongside a structured decision report.

Review & Benchmark Note: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
Clone Repository
git clone https://github.com/haseeb-heaven/jev-system-one.git

Inspect on GitHub

Check out the upstream repository README, issues, and commit log.

haseeb-heaven/jev-system-one

Architecture Category

Voice & Conversation

Voice turn-taking, interruption detection, and real-time dialogue routing.

View all in this category →

Related Projects in Voice & Conversation

Voice & ConversationMITPython

A Home Assistant conversation integration routing simple lighting commands to services and other requests to Grok.

What Jev does here

Jev classifies the utterance and exposed devices; code chooses a lighting service or conversation path.

Provides a bounded lighting fast path rather than support for every smart-home command.

#domain-workflows#voice-conversation#llm-routing-cost
14 evidence links
Inspect details
Voice & ConversationApache-2.0TypeScript

An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.

What Jev does here

Assesses utterance completeness and whether the user is likely to continue speaking.

Adds a semantic signal to silence-based turn detection.

#voice-conversation#typed-decisions
663 evidence links
Inspect details
OpenWhisper repository icon by Knuckles92

Knuckles92

OpenWhisper

185
Voice & ConversationMITPython

A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.

What Jev does here

Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.

Keeps model probabilities separate from local thresholds, switches and failure fallbacks.

#voice-conversation#security-guardrails#classification-ranking
254 evidence links
Inspect details