pithings/advocaat

Jeeves – Reasoning improves Jev-like decision models

The open, local take on Jev: typed decisions from an LLM, without generating a single token

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

System One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, D1, CLM and Laya

AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

Enable AI to ask anyone anything 🤝

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.

Algorithmic Impact Assessment - Évaluation de l'incidence algorithmique (TS/JS)