Jev in production › Agent guardrails and approvals
Vendor claims Jev classifies risk, irreversibility and injection-suspicion for every DeepSeek Harness tool call at about $0.00002 per request (author).

⚡ Millisecond judgement for every tool call and every recalled message — for about two millionths of a dollar each. Your agent's most expensive habits: asking a poetry-writing LLM yes/no questions, and amputating your context by age. This plugin wires Jev — the non-generative "System One" model that broke everyone's feed — into the decision points of DeepSeek Harness where an LLM is overkill and rules are blind.
The Web panel (sidebar ⚡ → Jev 决策): live KPIs and net-benefit card, a filterable decision log with full evidence per row, shadow-data threshold advice that tracks whether you adopted it, and one-click connection test. Every screenshot above is the real plugin running real decisions.
For the project's own README, linking back here: