OPERA: Open-Source Prediction Evaluation and Real-Time Analysis

Documentation

OPERA is a modular ecosystem aimed at streamlining forecasting tasks for economists and fostering open collaboration. Model logic - estimation, forecasting, forecast decomposition - is separated from the real-time workflow, making it easier to compare models in replicable environments and leverage open source contributions. The ecosystem is currently composed of seven blocks which cover the full pipeline from raw data to evaluation. Its architecture, interfaces and design principles reflect the specific constraints of macro analysis: data revision, ragged edge, mixed-frequency, conditional projections, uncertainty quantification, narrative accounting and nested models. By making these modules open-source, OPERA provides a platform for central bankers, academics and other forecasters to share infrastructure and collaborate.

Architecture

Modules

Install all ecosystem packages with pip install "opera-eco[modules]".

Authors

The package authors listed in each repository's pyproject.toml are:

Quick Start

pip install opera-eco              # Install the CLI and skills only.
pip install "opera-eco[modules]"  # Install the CLI and all ecosystem packages.
pip install "opera-eco[notebooks]" # Install Marimo notebook tooling.
opera install skills               # Install AI skills in .claude/skills/.

Then ask Copilot or Claude to use an installed skill:

Tell me about @opera and how I can use it with my model.

OPERA Skills for Claude and Copilot

The package includes seven skills for AI coding assistants:

Project Layout

docs/                            # Documentation site.
examples/illustration.py        # Runnable end-to-end example.
examples/illustration_marimo.py # Native Marimo version of the example.
src/opera/                      # Package source, bundled skills, and tests.
  cli.py                        # Command-line interface.
  skills_manager.py             # Skill discovery and installation.
  skills/                       # Bundled Markdown skill files.
pyproject.toml                  # Python package configuration.
zensical.toml                   # Documentation site configuration.

Data Classification

Bank of England Data Classification: OFFICIAL BLUE