[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9761":3},{"id":4,"name":5,"fullName":6,"owner":5,"repo":5,"description":7,"homepage":8,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":11,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":15,"stars30d":16,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":20,"defaultBranch":21,"hasWiki":19,"hasPages":20,"topics":22,"createdAt":9,"pushedAt":9,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":14,"starSnapshotCount":14,"syncStatus":13,"lastSyncTime":33,"discoverSource":34},9761,"SerpentAI","SerpentAI\u002FSerpentAI","Game Agent Framework. Helping you create AIs \u002F Bots that learn to play any game you own!","http:\u002F\u002Fserpent.ai",null,"Python",6986,802,2,0,3,13,39.71,"MIT License",true,false,"dev",[23,24,25,26,27,28,29],"artificial-intelligence","computer-vision","deep-learning","framework","machine-learning","python","video-games","2026-06-12 02:02:12","![](https:\u002F\u002Fs3.ca-central-1.amazonaws.com\u002Fserpent-ai-assets\u002FSerpentFBCover.png)\n\n# Serpent.AI - Game Agent Framework (Python)\n\n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fproject-website-brightgreen.svg?colorB=1bcc6f&longCache=true)](http:\u002F\u002Fserpent.ai)\n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fproject-blog-brightgreen.svg?colorB=1bcc6f&longCache=true)](http:\u002F\u002Fblog.serpent.ai)\n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fproject-wiki-brightgreen.svg?colorB=1bcc6f&longCache=true)](https:\u002F\u002Fgithub.com\u002FSerpentAI\u002FSerpentAI\u002Fwiki)    \n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpypi-v2018.1.2-brightgreen.svg?colorB=007ec6&longCache=true)]()\n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.6-brightgreen.svg?colorB=007ec6&longCache=true)]()\n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-brightgreen.svg?colorB=007ec6&longCache=true)]()  \n[![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ftwitter-@Serpent__AI-brightgreen.svg?colorB=1da1f2&longCache=true)](https:\u002F\u002Ftwitter.com\u002FSerpent_AI)\n\n## Update: Revival (May 2020)\n\nDevelopment work has resumed on the framework with the aim of bringing it into 2020: Python 3.8+, Less Dependencies, Ease of Use (Installer, GUI) and much more! Still open-source with a permissive license and looking into a Steam distribution for non-technical users. 🐍\n\n## ~~Warning: End of life (November 2018)~~\n\nSerpent.AI is a simple yet powerful, novel framework to assist developers in the creation of game agents. Turn ANY video game you own  into a sandbox environment ripe for experimentation, all with familiar Python code. The framework's _raison d'être_ is first and foremost to provide a valuable tool for Machine Learning & AI research. It also turns out to be ridiculously fun to use as a hobbyist (and dangerously addictive; a fair warning)!\n\nThe framework features a large assortment of supporting modules that provide solutions to commonly encountered scenarios when using video games as environments  as well as CLI tools to accelerate development. It provides some useful conventions but is absolutely NOT opiniated about what you put in your agents: Want to use the latest, cutting-edge deep reinforcement learning algorithm? ALLOWED. Want to use computer vision techniques, image processing and trigonometry? ALLOWED. Want to randomly press the Left or Right buttons? _sigh_ ALLOWED. To top it all off, Serpent.AI was designed to be entirely plugin-based (for both game support and game agents) so your experiments are actually portable and distributable to your peers and random strangers on the Internet.\n\nSerpent.AI supports Linux, Windows ~~& macOS~~.\n\n_The next version of the framework will officially stop supporting macOS. Apple's aversion to Nvidia in their products means no recent macOS machine can run CUDA, an essential piece of technology for Serpent.AI's real-time training. Other decisions like preventing 32-bit applications from running in Catalina and deprecating OpenGL do not help make a case to support the OS._ \n\n![](https:\u002F\u002Fs3.ca-central-1.amazonaws.com\u002Fserpent-ai-assets\u002Fdemo_isaac.gif)\n\n_Experiment: Game agent learning to defeat Monstro (The Binding of Isaac: Afterbirth+)_\n\n## Background\n\nThe project was born out of admiration for \u002F frustration with [OpenAI Universe](https:\u002F\u002Fgithub.com\u002Fopenai\u002Funiverse). The idea is perfect, let's be honest, but some implementation details leave a lot to be desired. From these, the core tennets of the framework were established:\n\n1. Thou shall run natively. Thou shalt not use Docker containers or VNC servers.\n2. Thou shall allow a user to bring their own games. Thou shalt not wait for licensing deals and special game APIs.\n3. Thou shall encourage diverse and creative approaches. Thou shalt not only enable AI flavors of the month.\n\n_Want to know more about how Serpent.AI came to be? Read [The Story Behind Serpent.AI](http:\u002F\u002Fblog.serpent.ai\u002Fthe-story-behind-serpent-ai\u002F) on the blog!_\n\n## Documentation\n\nGuides, tutorials and videos are being produced and added to the [GitHub Wiki](https:\u002F\u002Fgithub.com\u002FSerpentAI\u002FSerpentAI\u002Fwiki). It currently is the official source of documentation.\n\n![](https:\u002F\u002Fs3.ca-central-1.amazonaws.com\u002Fserpent-ai-assets\u002Fdemo_ymbab.gif)\n\n_Experiment: Game agent learning to match tiles (You Must Build a Boat)_\n\n_Business Contact: info@serpent.ai_\n","Serpent.AI 是一个游戏代理框架，旨在帮助开发者创建能够学习玩任何你拥有的游戏的AI或机器人。该项目采用Python语言开发，具备强大的计算机视觉、深度学习和机器学习功能，支持用户通过熟悉的Python代码将任意视频游戏转换为实验环境。它不仅适用于专业的机器学习与人工智能研究领域，也非常适合业余爱好者用来探索和娱乐。Serpent.AI 提供了丰富的辅助模块及命令行工具以加速开发过程，并且其设计完全基于插件架构，使得用户的实验成果可以轻松地与其他开发者分享。此外，该框架鼓励创新，允许使用从最前沿的深度强化学习算法到基础的图像处理技术等多种方法来构建游戏代理。","2026-06-11 03:24:37","top_topic"]