Real-Time Classification with JEV

Lokesh Bohra says he built and deployed a JEV and local Ollama system for real-time classification. It categorizes quickly and falls back to local inference when confidence is low.

View on X time70-500ms

Lokesh Bohra@7okesh𝕏

Built it. Deployed it. It works. JEV + local Ollama beats generative LLMs for real-time classification: - Social posts: 70-500ms - Email triage: classified instantly - Trading signals: sub-second decisions - Low confidence? Fallback to local inference No API calls. No token burn. No latency. The trick: Fast categorization upfront. Only escalate to deeper reasoning when confidence drops. This is ho

Sep 21, 2026X postsView on X

The system handles social posts, email triage, and trading signals. Bohra says social post classification takes 70–500ms.

Also filed under Triage & routing

Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using Jev AI. It is designed to speed up agent loops by routing decisions without relying on large generative LLMs at every step.
Local Candidate Scoring with Jev
Bev performs local Jevfire-style candidate scoring using ternary models and a System One API. Its probabilities are candidate-relative.
Team Agent Workspace for Routing and Model Selection
Agentconnect is a team agent workspace that uses Jev typed decisions for response routing and model selection.
Desktop AI Assistant with Jev Plugin
PyGPT is a desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.