Show HN: Jev Decision Layer: Save Frontier Tokens on Closed Decisions

Category: ai-ml

Tags: ai-agents, mcp, decision-routing, local-inference, privacy

Score: 6.5/10 (Innovation: 6, Technical: 6, Documentation: 8, Utility: 6)

Jev Decision Layer is a local MCP plugin that lets AI agents delegate closed-ended decisions (routing, yes/no checks, format picks) to a small hosted or on-device model, returning typed answers with confidence and a local receipt while the host retains execution authority. It stands out for its explicit consent model, folder-level approval, data-classification routing between hosted and local inference, and auditable receipts for every decision.

Target audience: AI agent developers, devops, and privacy-conscious enterprise teams integrating LLM assistants

Repository: https://github.com/qualixar/jev-decision-layer · Python · MIT · 6 stars

View on Hacker News