Open Source Python Artificial Intelligence Software - Page 83
Sort By:
Python Artificial Intelligence Software
View 17667 business solutionsBrowse free open source Python Artificial Intelligence Software and projects below. Use the toggles on the left to filter open source Python Artificial Intelligence Software by OS, license, language, programming language, and project status.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
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. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel strategies such as LASP+, varlen ring attention, and Expert Tensor Parallelism, enabling a training context of 1 million tokens and up to 4 million tokens at inference. MiniMax-VL-01 extends this core by adding a 303M-parameter Vision Transformer and a two-layer MLP projector in a ViT–MLP–LLM framework, allowing the model to process images at dynamic resolutions up to 2016×2016. -
2
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. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. The team emphasizes efficient scaling of test-time compute: at 100K-token generation lengths, M1 reportedly uses only about 25 percent of the FLOPs of some competing models, making extended “think step” traces more feasible. M1 is further trained with large-scale reinforcement learning over diverse tasks. -
3
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. The server is written in Python and distributed under the MIT license, with a pyproject.toml and uv-based workflow that makes installation and execution reproducible. Configuration is handled through JSON files that tell MCP clients how to launch the server (typically via uvx minimax-mcp) and which environment variables to use for the API key, host, and output directory. The README carefully explains region-specific API hosts for global and mainland users to avoid invalid-key errors, and documents both local stdio transport and SSE-based network transport modes. -
4
MiniMind
Train a 26M-parameter GPT from scratch in just 2h
minimind is a framework that enables users to train a 26-million-parameter GPT (Generative Pre-trained Transformer) model from scratch in approximately two hours. It provides a streamlined process for data preparation, model training, and evaluation, making it accessible for individuals and organizations to develop their own language models without extensive computational resources. -
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
MiniMind-V
"Big Model" trains a visual multimodal VLM with 26M parameters
MiniMind-V is an experimental open-source project that aims to train a very small multimodal vision–language model (VLM) from scratch with extremely low compute and cost, making research and experimentation accessible to more people. The repository showcases training workflows and code designed to produce a 26-million parameter model—including both image and text capabilities—using minimal resources in very little time, reflecting a trend toward democratizing AI research. MiniMind-V combines techniques from modern vision-language modeling but focuses on efficiency and simplicity so that individuals or small teams can explore multimodal learning without massive GPU clusters. It includes training scripts, model definitions, and associated tooling that illustrate how to build and evaluate such lightweight models. While not intended to compete with large production models, it serves as a hands-on educational resource and starting point for experimentation. -
6
MiniOneRec
Minimal reproduction of OneRec
MiniOneRec is an open-source framework designed to explore generative approaches to recommendation systems using large language model architectures. Traditional recommender systems typically rely on large embedding tables and ranking models, but MiniOneRec adopts a generative paradigm in which items are represented as sequences of semantic identifiers generated by autoregressive models. The framework provides an end-to-end pipeline for building generative recommender systems, including semantic identifier construction, supervised fine-tuning, and reinforcement learning-based optimization. Semantic IDs are created using techniques such as quantized variational autoencoders to convert item features into token sequences that can be modeled by transformer architectures. Developers can train and evaluate recommendation models using different backbone language models while benefiting from the generative framework’s parameter efficiency and scalability. -
7
MiniRAG
Making RAG Simpler with Small and Open-Sourced Language Models
MiniRAG is a lightweight retrieval-augmented generation tool designed to bring the benefits of RAG workflows to smaller datasets, edge environments, and constrained compute settings by simplifying embedding, indexing, and retrieval. It extracts text from documents, codes, or other structured inputs and converts them into embeddings using efficient models, then stores these vectors for fast nearest-neighbor search without requiring huge databases or separate vector servers. When a query is issued, MiniRAG retrieves the most relevant contexts and feeds them into a generative model to produce an answer that is grounded in the source material rather than hallucinated. Its minimal footprint makes it suitable for local research assistants, chatbots, help desks, or knowledge bases embedded in applications with limited resources. Despite its simplicity, it includes features such as chunking logic, configurable embedding models, and optional caching to balance performance and accuracy. -
8
MiniSom
MiniSom is a minimalistic implementation of the Self Organizing Maps
MiniSom is a minimalistic and Numpy-based implementation of the Self Organizing Maps (SOM). SOM is a type of Artificial Neural Network able to convert complex, nonlinear statistical relationships between high-dimensional data items into simple geometric relationships on a low-dimensional display. Minisom is designed to allow researchers to easily build on top of it and to give students the ability to quickly grasp its details. The project initially aimed for a minimalistic implementation of the Self-Organizing Map (SOM) algorithm, focusing on simplicity in features, dependencies, and code style. Although it has expanded in terms of features, it remains minimalistic by relying only on the numpy library and emphasizing vectorization in coding style. -
9
Minigrid
Simple and easily configurable grid world environments
Minigrid is a lightweight, minimalistic grid-world environment library for reinforcement learning (RL) research. It provides a suite of simple 2D grid-based tasks (e.g., navigating mazes, unlocking doors, carrying keys) where an agent moves in discrete steps and interacts with objects. The design emphasizes speed (agents can run thousands of steps per second), low dependency overhead, and high customizability — making it easy to define new maps, new tasks, or wrappers. It supports the Gymnasium-style environment API so that RL researchers can plug it into their existing frameworks and algorithms with minimal adaptation. Because of its simplicity, it is often used for rapid prototyping, analytic experiments, curriculum learning, or pedagogical tutorials. While it is not a full 3D simulation environment, its strength lies in enabling many environment resets and steps cheaply, which is valuable for algorithmic RL research rather than high-fidelity rendering. -
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
10
Minimal text diffusion
A minimal implementation of diffusion models for text generation
A minimal implementation of diffusion models of text: learns a diffusion model of a given text corpus, allowing to generate text samples from the learned model. The main idea was to retain just enough code to allow training a simple diffusion model and generating samples, remove image-related terms, and make it easier to use. To train a model, run scripts/train.sh. By default, this will train a model on the simple corpus. However, you can change this to any text file using the --train_data argument. Note that you may have to increase the sequence length (--seq_len) if your corpus is longer than the simple corpus. The other default arguments are set to match the best setting I found for the simple corpus. -
11
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
The Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unspooling, and broadcasting operations for sparse tensors. The Minkowski Engine supports various functions that can be built on a sparse tensor. We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to speed up inference and minimize memory footprint has been studied widely. One of the popular techniques for model compression is pruning the weights in convnets, is also known as sparse convolutional networks. Such parameter-space sparsity used for model compression compresses networks that operate on dense tensors and all intermediate activations of these networks are also dense tensors. -
12
Mirascope
LLM abstractions that aren't obstructions
Mirascope is a powerful, flexible, and user-friendly library that simplifies the process of working with LLMs through a unified interface that works across various supported providers, including OpenAI, Anthropic, Mistral, Gemini, Groq, Cohere, LiteLLM, Azure AI, Vertex AI, and Bedrock. Whether you're generating text, extracting structured information, or developing complex AI-driven agent systems, Mirascope provides the tools you need to streamline your development process and create powerful, robust applications. -
13
MiroFlow
Agent framework that enables tool-use agent tasks
MiroFlow is a high-performance open-source framework designed for building intelligent AI agents capable of solving complex reasoning and research tasks. The system introduces a hierarchical architecture that organizes components into control, agent, and foundation layers, allowing developers to manage agent orchestration and tool interactions in a structured manner. One of the core innovations of MiroFlow is its use of agent graphs, which enable flexible orchestration of multiple sub-agents and tools in order to complete complex workflows. This architecture allows agents to perform advanced reasoning tasks such as deep research, future event prediction, and multi-step knowledge analysis. The framework emphasizes reliability and scalability by incorporating robust workflow execution, concurrency management, and fault-tolerant design to handle unstable APIs or network conditions. -
14
MiroThinker
MiroThinker is an open source deep research agent
MiroThinker is an open-source deep research AI agent designed to perform complex reasoning, information gathering, and predictive analysis tasks. The system focuses on enabling long-horizon research workflows by allowing the agent to interact repeatedly with external tools, search systems, and data sources while refining its reasoning through iterative steps. Rather than simply generating responses from a single prompt, the agent performs structured multi-step reasoning processes that involve searching for information, analyzing evidence, and synthesizing conclusions. The platform is optimized for research tasks such as financial forecasting, knowledge discovery, and large-scale information synthesis. MiroThinker has been evaluated on several agent benchmarks and has demonstrated strong performance on tests designed to measure deep research capabilities. -
15
Mistral Finetune
Memory-efficient and performant finetuning of Mistral's models
mistral-finetune is an official lightweight codebase designed for memory-efficient and performant finetuning of Mistral’s open models (e.g. 7B, instruct variants). It builds on techniques like LoRA (Low-Rank Adaptation) to allow customizing models without full parameter updates, which reduces GPU memory footprint and training cost. The repo includes utilities for data preprocessing (e.g. reformat_data.py), validation scripts, and example YAML configs for training variants like 7B base or instruct models. It supports function-calling style datasets (via "messages" keys) as well as plain text formats, with guidelines on formatting, tokenization, and vocabulary extension (e.g. extending vocab to 32768 for some models) before finetuning. The project also provides tutorial notebooks (e.g. mistral_finetune_7b.ipynb) to walk through the steps. -
16
Mistral Inference
Official inference library for Mistral models
Open and portable generative AI for devs and businesses. We release open-weight models for everyone to customize and deploy where they want it. Our super-efficient model Mistral Nemo is available under Apache 2.0, while Mistral Large 2 is available through both a free non-commercial license, and a commercial license. -
17
Mistral Small 4
Model that fuses instruct, reasoning and agentic skills
The Mistral Small 4 collection is a set of open-weight large language models developed by Mistral AI that aim to unify multiple capabilities, including instruction following, reasoning, and coding, within a single efficient architecture. These models are part of the broader Mistral Small family, which is designed to deliver strong performance across a wide range of everyday AI tasks while maintaining relatively low latency and efficient deployment requirements. The collection reflects an evolution toward hybrid mixture-of-experts architectures that dynamically activate subsets of parameters during inference, allowing large models to remain computationally efficient. Mistral Small 4 models are built to handle tasks such as conversational AI, software development assistance, and reasoning-heavy problem solving, making them versatile tools for both developers and enterprise applications. -
18
Mito
AI-powered Jupyter spreadsheet that converts workflows into Python
Mito is an open source set of Jupyter extensions designed to speed up Python workflows and data analysis. It combines a spreadsheet-style interface with AI-assisted coding, allowing users to explore, clean, and transform data without switching tools. Mito includes a context-aware AI assistant that helps generate code, debug errors, and guide workflows directly inside Jupyter. Its spreadsheet layer supports familiar functions such as filters, pivot tables, and formulas, while automatically converting every action into production-ready Python code. This removes the need to manually translate spreadsheet logic into scripts. Mito also integrates with tools like Streamlit and Dash, enabling users to embed interactive spreadsheet functionality into apps with minimal setup. Built for analysts, developers, and teams, it simplifies automation, reduces repetitive tasks, and accelerates the transition from data exploration to reusable code. -
19
Mixtral offloading
Run Mixtral-8x7B models in Colab or consumer desktops
Mixtral-Offloading is an open-source project designed to enable efficient inference of large Mixture-of-Experts language models such as Mixtral-8x7B on hardware with limited GPU memory. The project implements techniques that allow model components to be dynamically moved between CPU memory and GPU memory during inference, significantly reducing the amount of GPU VRAM required to run the model. This approach takes advantage of the sparse activation properties of mixture-of-experts architectures, where only a subset of expert networks are used for each token during generation. By selectively loading and caching the required experts, the system avoids keeping the entire model in GPU memory at once. The repository includes notebooks and code examples that demonstrate how to run large language models on consumer hardware such as personal GPUs or cloud notebook environments. -
20
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA, short for Mixture of Block Attention, is an open-source research implementation of a novel attention mechanism designed to improve the efficiency of large language models processing extremely long contexts. The architecture adapts ideas from Mixture-of-Experts networks and applies them directly to the attention mechanism of transformer models. Instead of forcing each token to attend to every other token in the sequence, MoBA divides the context into blocks and dynamically routes queries to only the most relevant segments of information. This routing strategy reduces the computational cost associated with traditional attention while preserving performance on reasoning and long-context tasks. The approach allows language models to scale to significantly longer input contexts without the quadratic computational cost normally associated with transformer attention mechanisms. -
21
MoCo (Momentum Contrast)
Self-supervised visual learning using momentum contrast in PyTorch
MoCo is an open source PyTorch implementation developed by Facebook AI Research (FAIR) for the papers “Momentum Contrast for Unsupervised Visual Representation Learning” (He et al., 2019) and “Improved Baselines with Momentum Contrastive Learning” (Chen et al., 2020). It introduces Momentum Contrast (MoCo), a scalable approach to self-supervised learning that enables visual representation learning without labeled data. The core idea of MoCo is to maintain a dynamic dictionary with a momentum-updated encoder, allowing efficient contrastive learning across large batches. The repository includes implementations for both MoCo v1 and MoCo v2, the latter improving training stability and performance through architectural and augmentation enhancements. Training is optimized for distributed multi-GPU environments, using DistributedDataParallel for speed and simplicity. -
22
MoCo v3
PyTorch implementation of MoCo v3
MoCo v3 is a PyTorch reimplementation of Momentum Contrast v3 (MoCo v3), Facebook Research’s state-of-the-art self-supervised learning framework for visual representation learning using ResNet and Vision Transformer (ViT) backbones. Originally developed in TensorFlow for TPUs, this version faithfully reproduces the paper’s results on GPUs while offering an accessible and scalable PyTorch interface. MoCo v3 introduces improvements for training self-supervised ViTs by combining contrastive learning with transformer-based architectures, achieving strong linear and end-to-end fine-tuning performance on ImageNet benchmarks. The repository supports multi-node distributed training, automatic mixed precision, and linear scaling of learning rates for large-batch regimes. It also includes scripts for self-supervised pretraining, linear classification, and fine-tuning within the DeiT framework. -
23
MAF (Mobile Agent Framework) is a research prototype which aims to facilitate the development and evaluation of mobile agent by providing a set of handy primitatives and simulation tools.
-
24
MobileCLIP
Implementation of "MobileCLIP" CVPR 2024
MobileCLIP is a family of efficient image-text embedding models designed for real-time, on-device retrieval and zero-shot classification. The repo provides training, inference, and evaluation code for MobileCLIP models trained on DataCompDR, and for newer MobileCLIP2 models trained on DFNDR. It includes an iOS demo app and Core ML artifacts to showcase practical, offline photo search and classification on iPhone-class hardware. Project notes highlight latency/accuracy trade-offs, with MobileCLIP2 variants matching or surpassing larger baselines at notably lower parameter counts and runtime on mobile devices. A companion “mobileclip-dr” repository details large-scale, distributed data-generation pipelines used to reinforce datasets across billions of samples on thousands of GPUs. Overall, MobileCLIP emphasizes end-to-end practicality: scalable training, deployable models, and consumer-grade demos. -
25
MobileLLM
MobileLLM Optimizing Sub-billion Parameter Language Models
MobileLLM is a lightweight large language model (LLM) framework developed by Facebook Research, optimized for on-device deployment where computational and memory efficiency are critical. Introduced in the ICML 2024 paper “MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases”, it focuses on delivering strong reasoning and generalization capabilities in models under one billion parameters. The framework integrates several architectural innovations—SwiGLU activation, deep and thin network design, embedding sharing, and grouped-query attention (GQA)—to achieve a superior trade-off between model size, inference speed, and accuracy. MobileLLM demonstrates remarkable performance, with the 125M and 350M variants outperforming previous state-of-the-art models of the same scale by up to 4.3% on zero-shot commonsense reasoning tasks.
