Search Results for "minimax"
Sort By:
Showing 43 open source projects for "minimax"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
MiniMax H3
MiniMax H3 is a general-purpose, omni-modal generative system
MiniMax H3 is an omni-modal generative system for creating synchronized video and native stereo audio from complex multimodal instructions. It can understand combinations of text, images, video, and audio as generation context. Outputs range from four to fifteen seconds at 24 frames per second, with multiple aspect ratios and resolutions up to 2K. -
2
MiniMax-M2.5
State of the art LLM and coding model
MiniMax-M2.5 is a state-of-the-art foundation model extensively trained with reinforcement learning across hundreds of thousands of real-world environments. It delivers leading performance in coding, agentic tool use, search, and complex office workflows, achieving top benchmark scores such as 80.2% on SWE-Bench Verified and 76.3% on BrowseComp. -
3
MiniMax-M2.1
MiniMax M2.1, a SOTA model for real-world dev & agents.
MiniMax-M2.1 excels in real-world software engineering tasks, including multilingual development and complex workflow automation. It demonstrates strong generalization across agent frameworks and consistently improves upon its predecessor, MiniMax-M2. Benchmarks show that it rivals or approaches top proprietary models while remaining fully open for local deployment and customization. -
4
MiniMax Skills
Development skills for AI coding agents
MiniMax skills is a modular system designed to provide structured development capabilities for AI coding agents, enabling them to perform complex engineering tasks with guided workflows and domain-specific knowledge. It defines a set of reusable “skills” that encapsulate best practices, architectural patterns, and step-by-step processes for building applications across multiple platforms. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
MiniMax-M1 is presented as the world’s first open-weight, large-scale hybrid-attention reasoning model, designed to push the frontier of long-context, tool-using, and deeply “thinking” language models. It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. -
6
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
MiniMax-01 is the official repository for two flagship models: MiniMax-Text-01, a long-context language model, and MiniMax-VL-01, a vision-language model built on top of it. MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. -
7
MiniMax-M2
MiniMax-M2, a model built for Max coding & agentic workflows
MiniMax-M2 is an open-weight large language model designed specifically for high-end coding and agentic workflows while staying compact and efficient. It uses a Mixture-of-Experts (MoE) architecture with 230 billion total parameters but only 10 billion activated per token, giving it the behavior of a very large model at a fraction of the runtime cost. -
8
MiniMax-MCP
Official MiniMax Model Context Protocol (MCP) server
MiniMax-MCP is the official Model Context Protocol (MCP) server for accessing MiniMax’s multimodal generative APIs from MCP-compatible clients. It acts as a bridge between tools like Claude Desktop, Cursor, Windsurf, OpenAI Agents, and the MiniMax platform, exposing capabilities such as text-to-speech, voice cloning, image generation, text-to-image, video generation, image-to-video, text-to-video, and music generation. -
9
h3-metal
MiniMax H3 inference engine for Mac computers
h3-metal is a native MiniMax-H3 inference engine for Apple Silicon focused on generating video and audio locally with Metal. It supports prompt-to-video and prompt-to-audio workflows as well as first-frame, last-frame, image, video, and audio references. An interactive terminal session keeps prompt conditioning, the diffusion transformer, and the video decoder in memory for faster repeated generations. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
Kun
AI agent workspace with Code and Write modes built into your apps
...The application includes a Code workspace for real repositories and a Write workspace for Markdown writing, editing, previewing, and exporting. It uses DeepSeek, Xiaomi MiMo, and MiniMax as its default model combination while still allowing custom providers. Kun includes a local runtime through kun serve, local session storage, tool approvals, permission modes, inline diffs, and change review panels. It is useful for users who want an AI coding environment that treats planning, documentation, implementation, and acceptance review as one continuous workflow. -
11
Mini Agent
A minimal yet professional single agent demo project
Mini-Agent is a minimal yet production-minded demo project that shows how to build a serious command-line AI agent around the MiniMax-M2 model. It is designed both as a reference implementation and as a usable agent, demonstrating a full execution loop that includes planning, tool calls, and iterative refinement. The project exposes an Anthropic-compatible API interface and fully supports interleaved thinking, letting the agent alternate between reasoning steps and tool invocations during long, complex tasks. ... -
12
Kirara AI
DIY multimodal AI chatbot
...It supports multi-turn conversation, persona presets, keyword-triggered replies, administrator commands, and conditional automation. The project can work with model providers such as OpenAI, DeepSeek, Claude, Gemini, Qwen, Mistral, Kimi, Minimax, and others. It also supports image generation models, voice replies, cross-platform message sending, and custom workflows. A WebUI helps users manage models, workflows, plugins, and platform settings without editing every detail manually. Kirara AI is especially useful for users who want a configurable AI bot that can run across multiple messaging environments. -
13
Bookbuilder opensource, based on old version Bookbuilder 3.5 (with full minimax but no opening names) and Bookbuilder 4.3 with openings names, and line minimax
-
14
claude-multi
A tool to have multiple claude-code instance with deepseek, minimax, and z.ai glm models
-
15
Algerian/Spanish Checkers
Algerian / Spanish checkers with Minimax and Alpha–beta pruning
Algerian / Spanish Checkers Variant is a digital implementation of the classic board game with unique features and rules. Currently, the program integrates an AI opponent using the Minimax algorithm with alpha-beta pruning. The previous versions just favours moves that result in the fewest captures for the opponent. Future versions will include more sophisticated AI to enhance gameplay. The program currently handles all kind of regular piece and dama moves and captures. -
16
Kaata Zero (Tic tac toe)
Tic-Tac-Toe game for Windows (also known as Kaata Zero)
.... ### Game modes - **Player vs Computer** — You play **X**, the computer plays **O** - **2 Player** — Two people take turns on the same keyboard and screen ### AI difficulty - **Easy** — Random moves - **Medium** — Mix of tactical and random play - **Hard** — Minimax strategy (strong opponent) ### Scoring - Easy win: **+50** points - Medium win: **+100** points - Hard win: **+200** points - Draw: **−50** points - Loss: score resets to **0** ### What makes it enjoyable - Five color **skins**: Classic, Midnight, Ocean, Forest, Cand -
17
Basic Blind Chess
Blind Chess using Taiwan rules
Blind Chess also known as "Dark Chess" (暗棋) or "Banqi" or Half Chess , is a two-player Chinese board game played on a 4x8 grid, or half of the xiangqi (Chinese Chess) board. This application is using Taiwan rule. AI is using basic minimax tree structure and some rules. Advanced algorithm such as Upper Confidence bounds applied to Trees and Monte Carlo Tree Search are NOT used. This app is single player vs computer only. For English user, Christakis Giorgios made Software Requirements Specification(pdf file), it will help anyone that downloads this application to understand basic blind chess and use it. ... -
18
MiniMax Timer
Customizable countdown timer
The MiniMax Timer is a simple timer application which, for now, only counts downward. It has the following customizable features: - always on top - fullscreen - timer font, text color and background color - display a customizable text when the timer ends - timer's size and location - timer control shortcuts The settings (positions, colors, sizes) are automatically saved upon exiting the program. -
19
neurochess
Self chess learning process by artificial neural network
Self chess learning process by artificial neural network white random attribution to of values of chess game, before to pass opposed value to neural network and the desire successor of board with various part of game chess generated with minimax algorithm. -
20
TicTacToe
Tic Tac Toe game with clever computer player
...Players can be human or AI. The AI has two settings: dumb and intelligent. The dump setting places tokens by random, the intelligent setting plays the best possible move by running a MiniMax algorithm. The executable requires the LabVIEW Run-Time Engine 2014 - (32-bit) available for download here: http://ftp.ni.com/support/softlib/labview/labview_runtime/2014/Windows/f2/LVRTE2014f2std_downloader.exe -
21
Nand2Tetris - TicTacToe
Tic Tac Toe Game for the Nand2Tetris Project
This is an implementation of the classic Tic Tac Toe game on the Hack computer as part of the Nand2Tetris project. The game features a 1 or 2-player mode with a computer-controlled player for single player games. The computer AI uses a 'minimax' algorithm and has 3 levels of difficulty - the Impossible mode is unbeatable! -
22
ChessAT
one more chess engine in the barn
This simple chess engine employs a minimax algorithm to calculate two moves ahead. -
23
Artificial Intelligence Connect 4 Game
Artificial Intelligence Connect 4 Game
Artificial Intelligence Connect 4 Game using minimax search algorithm -
24
Dots and Boxes Standalone
Dots and boxes game to practice vs your computer
Dots&Boxes is becoming a super-charged multiplayer game based on the traditional Dot Game first published in 1889 by Édouard Lucas. This standalone version uses the minimax algorithm with alpha-beta pruning to enhance the computer game difficulty. -
25
Connect Four
A simple connect four game in C#
This is a small and simple project which i used to work on creating a minimax algorithm. In its current state, the algorithm is finished. Future updates will try to: 1. Add heuristics instead of just checking for wins 2. Introduce alpha-beta pruning Other updates not concerning the AI will be: 1. Coins will fall down into place, instead of appearing 2. You can set if you want to play with 2 humans, 2 computers or an AI and a human. 3.
