kaggle-environments
Kaggle Environments
Decision gist · record as of 2026-08-14
Yes, if you need to run and evaluate multi-agent game simulations. The package is actively maintained, has low install friction, and provides a clean API for episode evaluation. However, verify the license terms first since they are not clearly stated in the package metadata. The 19 runtime dependencies (including JAX, transformers, and Flask) add complexity; ensure they align with your environment constraints.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later.
- Low friction: pure Python wheel with no compiled dependencies.
- Actively maintained with a recent release (7 days ago) and 446 GitHub stars.
License · maintenance · safety
(unclear) — License status is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms in the repository before use in proprietary or commercial projects.
last release 2026-08-07 (7 days) · last repo commit 2026-08-14 · 446 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 141,054 downloads/mo, #11,254 on PyPI
Alternatives
Verify before relying
from kaggle_environments import make
env = make("tictactoe")
def my_agent(obs):
return [c for c in range(len(obs.board)) if obs.board[c] == 0][0]
env.run([my_agent, "random"])- Whether the unclear license permits commercial or proprietary use without restrictions.
- Performance characteristics when running many episodes or with large environment configurations.
- Stability and compatibility of the 19 runtime dependencies (Flask, JAX, transformers, etc.) across different versions.
What it is and what it does
Kaggle Environments is a framework for defining and running multi-agent game simulations. It emphasizes episode evaluation—running complete games between agents—rather than agent training. The library provides a simple interface to create environments (like Connect X and Tic Tac Toe), define agent functions that take observations and return actions, and run episodes to completion, collecting step-by-step results and rewards.
Agents can be written as Python functions, loaded from source code or files, or selected from built-in defaults like "random". The framework supports configurable timeouts, debug modes to catch agent errors, and rendering of game replays. It integrates with Open AI Gym for training workflows and includes utilities for running the same agents across multiple episodes to gather statistics.
Use it for
- Evaluate trained RL agents against each other or built-in baselines in competitive games.
- Run tournament-style competitions between multiple agent implementations.
- Generate episode data for analysis, visualization, or dataset creation.
- Debug agent behavior by running games with verbose logging and error reporting.
- Benchmark different agent strategies across configurable game parameters.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to run and evaluate multi-agent game simulations.
The package is actively maintained, has low install friction, and provides a clean API for episode evaluation. However, verify the license terms first since they are not clearly stated in the package metadata. The 19 runtime dependencies (including JAX, transformers, and Flask) add complexity; ensure they align with your environment constraints.
Install
kaggle-environments on PyPI
Before you install
Low friction: pure Python wheel with no compiled dependencies. Actively maintained with a recent release (7 days ago) and 446 GitHub stars. Requires Python 3.11 or later.
Requires Python 3.11 or later.
License in practice
License status is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms in the repository before use in proprietary or commercial projects.
Quickstart
from kaggle_environments import make
env = make("tictactoe")
def my_agent(obs):
return [c for c in range(len(obs.board)) if obs.board[c] == 0][0]
env.run([my_agent, "random"])Verify before relying
- Whether the unclear license permits commercial or proprietary use without restrictions.
- Performance characteristics when running many episodes or with large environment configurations.
- Stability and compatibility of the 19 runtime dependencies (Flask, JAX, transformers, etc.) across different versions.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 19 packagesFlaskgymnasiumgymnaxjaxjsonschemalitellmnumpyopen_spielpettingzoopokerkitpydanticpygamepyjson5termcolorrequestsshimmytransformerstenacitygoogle-auth |
| Maintenance | Actively maintained 7 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 141,054 / month, #11,254 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: kaggle_environments-1.32.6-py3-none-any.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 › “multi-agent game simulation”
- kaggle-environmentsKaggle Environments provides a framework for creating and running…
- open-spielOpenSpiel provides game environments and reinforcement learning…
- gymnasiumGymnasium provides a standard Python API for building and testing…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also openenv-core · pettingzoo · gymnasium · gem-llm · nemo-gym · TextArena · kaggle · fhaviary · ale-py · gym-aloha