This MCP plugin enables communication with multiple apps and their endpoints within a single view and conversation, accessible through desktop or web applications.
added by @MeJohnC
In an evening I got a unified MCP plugin built that can serve and speak to multiple apps and their own MCP endpoints across a single view, single agent conversation, in the desktop or web app for ChatGPT.
View similar
Ranked from stored criteria vectors. No live classification on this page.
The Jev adapter classifies prompts before they reach the LLM, reducing token consumption and costs. It provides classification and confidence scores, marking prompts for review when confidence is near the threshold.
Jev offers a new intelligent decision-making primitive that enhances model routing and classification tasks. It allows for quick and cost-effective decision-making, improving the efficiency of LLM calls in applications.
Easy-Jev is a demo that allows users to change inputs and see real-time classification changes. Developed by a master's thesis researcher in classification models, it showcases a modern approach to combining different models for problem-solving.
A benchmark was conducted comparing Jev by TypeSafe and Claude Code agents for filling out web forms. The test involved three real forms, with no submissions made.