Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
-
Updated
Oct 9, 2025 - TypeScript
Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
[AISTATS2021] Official implementation of "Sample Elicitation"
Security Expert Elicitation of Risks
MCP as a Judge is a behavioral MCP that strengthens AI coding assistants by requiring explicit LLM evaluations
A modern CLI tool for generating production-ready Model Context Protocol (MCP) servers
Methods for mathematically aggregating expert judgements
Running UK AISI's Inspect in the Cloud
UMLet ISTAR-palette for goal oriented requirements engineering (GORE)
elicitr is an R package, used to aggregate elicitation data. The package is in active development and implements functions based on two formal elicitation methods. You provide the data, and elicitr transforms them into easily readable graphics.
This is a minimal Model Context Protocol (MCP) server that showcases how to build MCP tools with elicitation capabilities
Shiny app visualiser of four point elicitation data
tPRiors: Bayesian prevalence estimation
Add a description, image, and links to the elicitation topic page so that developers can more easily learn about it.
To associate your repository with the elicitation topic, visit your repo's landing page and select "manage topics."