Decision Making Python Packages

torchrl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

emukit

A Python-based toolbox of various methods in decision making, uncertainty quantification and statistical emulation: multi-fidelity, experimental design, Bayesian optimisation, Bayesian quadrature, etc.

torchrl-nightly

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

scikit-decide

AI framework for Reinforcement Learning, Automated Planning and Scheduling

flatland-rl

The Flatland Framework is a multi-purpose environment to tackle problems around resilient resource allocation under uncertainty. It is designed to be a flexible and method agnostic to solve a wide range of problems in the field of operations research and reinforcement learning.

asktheboard

A board of expert personas whose every decision is a pre-registered, time-anchored, reality-graded bet. BYOK; the board that keeps score, before the fact.

foghorn-ai

Fact-level staleness detection for AI agent memory

arbitration-graphs

Hierarchical behavior models for complex decision-making and behavior generation in robotics

abtree

Asynchronous behavior tree framework with behavior forest collaboration,built on Python asyncio for multi-agent systems and autonomous decision-making.

georank

Generic weighted-criteria ranking engine — score and rank places by normalized, weighted factors. Zero deps, JS + Python. Powers georank.place.

ns-gym

A framework for modeling non-stationary Markov decision processes and the key decision making problems in these environments

znum

Z number for fuzzy calculations

octochains

A lightweight, zero-dependency Python framework for parallel, isolated, collaborative AI reasoning.

maze-rl

MazeRL is a development framework for building applied reinforcement learning systems, addressing real-world decision problems. It supports the complete development life cycle of RL applications, ranging from simulation engineering up to agent development, training and deployment.

llm-parliament

Multi-agent debate for better AI decisions. Research-backed, local-first.

magi-core

Multi-Agent Group Intelligence: orchestrate a council of LLMs to deliberate on complex questions

mobile-env-rl

A Universal Platform for Training and Evaluation of Mobile Interaction

spice-runtime

Spice core runtime framework

scikit-psl

Probabilistic Scoring List classifier

artemis-agents

A production-ready framework for structured multi-agent debates with adaptive evaluation, causal reasoning, and built-in safety monitoring.

eospython

A set of functions encompassing a centralized Earth Observation Satellite scheduling system

morphsat

Structured cognitive control for LLM agent loops. External shadow monitor holds decision authority. 9-version proof chain. Soar/ACT-R/active-inference term mapping included.

qaekwy

Qaekwy, a modern, open-source Python framework for declarative constraint programming and combinatorial optimization

fast-safe-rl

🚀 A fast safe reinforcement learning library in PyTorch