Policy Evaluation Python Packages

statspai

StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.

robot-reel

Review Physical AI with original evidence: compare VLM explanations against recorded robot outcomes, replay SmolVLA failures, and inspect Newton/Genesis simulations offline.

verdict-rules

A small, zero-dependency, async-native rule-evaluation engine — structural typing, real short-circuiting, and a verdict that always explains itself.

orbit-eval

You have a robot. orbit tells you what to do next, and how you will know it worked. Zero-dependency CLI for LeRobot datasets and evaluations: what the recording got wrong, what it never covered, whether a change survived the noise.

syntheticcontrolmethods

A Python package for causal inference using Synthetic Controls

insurance-causal-policy

SDID for causal rate change evaluation in insurance pricing — event study, HonestDiD sensitivity, FCA evidence pack (170 tests)

praxis-eval

A simple, efficient, and extensible evaluation framework for robot policies across diverse benchmarks, supporting both local and remote execution

verdikt-eval

A CPU-only decision layer for robot-policy evaluation - reads the eval JSON you already have and refuses to let you draw a conclusion the data does not support.

robometric-frame

TorchMetrics-based evaluation metrics for robotics policies and robot learning