open-spiel
A Framework for Reinforcement Learning in Games
Decision gist · record as of 2026-08-14
Yes, if you are conducting research in multi-agent reinforcement learning, game theory, or game-playing AI. The framework is actively maintained, permissively licensed, has no known vulnerabilities, and offers a comprehensive suite of game environments and algorithms. Install friction is moderate due to compiled components, but wheels are available for common platforms. Not recommended for production game servers or applications requiring real-time performance without careful profiling.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later; compiled wheels available for common platforms but may require build tools on unsupported architectures.
- Medium install friction due to compiled C++ components; wheels are available for Python 3.11–3.14 on Linux, macOS (ARM), and Windows.
- Active maintenance with a recent release (2 days old) and 5411 repository stars.
License · maintenance · safety
Apache-2.0 (permissive) — Licensed under Apache-2.0 (permissive), allowing commercial and private use with minimal restrictions.
last release 2026-08-12 (2 days) · last repo commit 2026-08-12 · 5,411 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 139,198 downloads/mo, #11,304 on PyPI
Alternatives
Verify before relying
pip install open-spiel
import open_spiel- Specific game environments available and their names for import examples.
- Whether the C++ core is performant enough for large-scale multi-agent training without custom compilation.
- Availability of pre-built wheels for Python 3.14 on all advertised platforms or fallback build requirements.
What it is and what it does
OpenSpiel is a research framework for game-based reinforcement learning and game theory, built on a C++ core with Python bindings. It provides a collection of game environments—ranging from classic games to grid worlds and social dilemmas—along with algorithms for learning and planning. The framework represents games as procedural extensive-form games and supports n-player scenarios with varying information structures (perfect and imperfect information), move timing (turn-taking and simultaneous), and payoff structures (zero-sum, cooperative, general-sum).
The package is designed for researchers studying multi-agent learning dynamics, game-theoretic algorithms, and reinforcement learning in complex interactive settings. It includes tools for analyzing learning dynamics and standard evaluation metrics. Games and core APIs are implemented in C++ for performance, while algorithms and analysis tools are available in both C++ and Python, allowing researchers to prototype in Python or optimize critical paths in C++.
Use it for
- Implement and test multi-agent reinforcement learning algorithms on standardized game benchmarks.
- Study game-theoretic properties and learning dynamics in cooperative, competitive, and mixed-motive games.
- Develop and evaluate AI agents for imperfect-information games.
- Prototype game environments and reward structures for multi-agent research without building from scratch.
- Analyze equilibria and convergence behavior in n-player games with varying information and move structures.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are conducting research in multi-agent reinforcement learning, game theory, or game-playing AI.
The framework is actively maintained, permissively licensed, has no known vulnerabilities, and offers a comprehensive suite of game environments and algorithms. Install friction is moderate due to compiled components, but wheels are available for common platforms. Not recommended for production game servers or applications requiring real-time performance without careful profiling.
Install
open-spiel on PyPI
Before you install
Medium install friction due to compiled C++ components; wheels are available for Python 3.11–3.14 on Linux, macOS (ARM), and Windows. Active maintenance with a recent release (2 days old) and 5411 repository stars.
Requires Python 3.11 or later; compiled wheels available for common platforms but may require build tools on unsupported architectures.
License in practice
Licensed under Apache-2.0 (permissive), allowing commercial and private use with minimal restrictions.
Quickstart
pip install open-spiel
import open_spielVerify before relying
- Specific game environments available and their names for import examples.
- Whether the C++ core is performant enough for large-scale multi-agent training without custom compilation.
- Availability of pre-built wheels for Python 3.14 on all advertised platforms or fallback build requirements.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 5 packagesabsl-pyattrsnumpyscipyml-collections |
| Maintenance | Actively maintained 2 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 139,198 / month, #11,304 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: Science/ResearchOperating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: C++Programming Language :: Python :: 3Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Games/EntertainmentTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Python Modules |
Evidence: open_spiel-2.0.2-cp311-cp311-macosx_11_0_arm64.whl; open_spiel-2.0.2-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; open_spiel-2.0.2-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; open_spiel-2.0.2-cp311-cp311-win_amd64.whl; open_spiel-2.0.2-cp312-cp312-macosx_11_0_arm64.whl; open_spiel-2.0.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; open_spiel-2.0.2-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; open_spiel-2.0.2-cp312-cp312-win_amd64.whl; open_spiel-2.0.2-cp313-cp313-macosx_11_0_arm64.whl; open_spiel-2.0.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; open_spiel-2.0.2-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; open_spiel-2.0.2-cp313-cp313-win_amd64.whl; open_spiel-2.0.2-cp314-cp314-macosx_11_0_arm64.whl; open_spiel-2.0.2-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; open_spiel-2.0.2-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; open_spiel-2.0.2-cp314-cp314-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “reinforcement learning game environments”
- open-spielOpenSpiel provides game environments and reinforcement learning…
- gymnasiumGymnasium provides a standard Python API for building and testing…
- pettingzooPettingZoo provides multi-agent reinforcement learning environments…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also nashpy · pettingzoo · gem-llm · chess · openskill · gymnasium · glicko2 · TextArena · tianshou · sb3-contrib