Open Source Python Software - Page 62
Sort By:
Python Software
Browse free open source Python Software and projects below. Use the toggles on the left to filter open source Python Software by OS, license, language, programming language, and project status.
-
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.
-
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.
-
1
LINE Messaging API SDK for Python
LINE Messaging API SDK for Python
The LINE Messaging API SDK for Python makes it easy to develop bots using LINE Messaging API, and you can create a sample bot within minutes. You must upload a rich menu image and link the rich menu to a user for the rich menu to be displayed. You can create up to 1000 rich menus for one LINE Official Account with the Messaging API. The LINE Messaging API SDK for Python includes experimental asyncio support. (API may change without notice in a future version). Send push messages to multiple users at any time. Messages cannot be sent to groups or rooms. Get progress status of narrowcast messages sent. Gets the user IDs of the members of a room that the bot is in. This includes the user IDs of users who have not added the bot as a friend or has blocked the bot. Get the number of users who have added the bot on or before a specified date. -
2
LLM Colosseum
Benchmark LLMs by fighting in Street Fighter 3
LLM-Colosseum is an experimental benchmarking framework designed to evaluate the capabilities of large language models through gameplay interactions rather than traditional text-based benchmarks. The system places language models inside the environment of the classic video game Street Fighter III, where they must interpret the game state and decide which actions to perform during combat. This setup creates a dynamic environment that tests reasoning, situational awareness, and decision-making abilities in real time. Instead of relying purely on reward signals as in reinforcement learning agents, the models analyze contextual information and generate strategic actions based on the game environment. Performance is evaluated using a competitive ranking system that assigns models an ELO rating based on their results across matches against other models. -
3
LLM Foundry
LLM training code for MosaicML foundation models
Introducing MPT-7B, the first entry in our MosaicML Foundation Series. MPT-7B is a transformer trained from scratch on 1T tokens of text and code. It is open source, available for commercial use, and matches the quality of LLaMA-7B. MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k. Large language models (LLMs) are changing the world, but for those outside well-resourced industry labs, it can be extremely difficult to train and deploy these models. This has led to a flurry of activity centered on open-source LLMs, such as the LLaMA series from Meta, the Pythia series from EleutherAI, the StableLM series from StabilityAI, and the OpenLLaMA model from Berkeley AI Research. -
4
Learn Claude Code
Bash is all you need, write a claude code with only 16 line code
Learn Claude Code is an educational repository that teaches how modern AI coding agents work by walking learners through a sequence of progressively more complex agent implementations, starting with a minimal Bash-based agent and culminating in agents with explicit planning, subagents, and skills. It emphasizes a hands-on learning path where each version (from v0 to v4) adds conceptual building blocks like the core agent loop, todo planning, task decomposition, and domain knowledge skills, illuminating the patterns behind what makes a true AI agent tick. The goal is to demystify agent architectures like Claude Code by having learners build simplified versions themselves and observe how tools, memory management, planning constraints, and context isolation contribute to reliable agent behavior. Along the way, the project teaches fundamentals such as how to let models call external tools, maintain clean memory for long tasks, and inject domain expertise without retraining the model. -
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
5
Lepton AI
A Pythonic framework to simplify AI service building
A Pythonic framework to simplify AI service building. Cutting-edge AI inference and training, unmatched cloud-native experience, and top-tier GPU infrastructure. Ensure 99.9% uptime with comprehensive health checks and automatic repairs. -
6
LitServe
Minimal Python framework for scalable AI inference servers fast
LitServe is a minimal Python framework designed for building custom AI inference servers with full control over how models are executed and served. It allows developers to define their own inference logic, making it suitable for complex systems such as multi-model pipelines, agents, and retrieval-augmented generation workflows. Unlike traditional serving tools that enforce rigid abstractions, LitServe focuses on flexibility by letting users control request handling, batching strategies, and output processing directly in Python. LitServe is built on top of FastAPI and extends it with AI-specific optimizations such as efficient multi-worker execution, which can significantly improve throughput. It includes built-in capabilities for batching, streaming responses, and automatic scaling across CPUs and GPUs, enabling high-performance deployments. -
7
MCP Server Home Assistant
A Model Context Protocol Server for Home Assistant
The Home Assistant MCP Server is an MCP server that integrates with Home Assistant, enabling AI assistants to interact with smart home devices and systems. It exposes Home Assistant voice intents through the Model Context Protocol for enhanced home control. -
8
MLE-Agent
Intelligent companion for seamless AI engineering and research
MLE-Agent is designed as a pairing LLM agent for machine learning engineers and researchers. A library designed for managing machine learning experiments, tracking metrics, and model deployment. -
9
MLRun
Machine Learning automation and tracking
MLRun is an open MLOps framework for quickly building and managing continuous ML and generative AI applications across their lifecycle. MLRun integrates into your development and CI/CD environment and automates the delivery of production data, ML pipelines, and online applications, significantly reducing engineering efforts, time to production, and computation resources. MLRun breaks the silos between data, ML, software, and DevOps/MLOps teams, enabling collaboration and fast continuous improvements. In MLRun the assets, metadata, and services (data, functions, jobs, artifacts, models, secrets, etc.) are organized into projects. Projects can be imported/exported as a whole, mapped to git repositories or IDE projects (in PyCharm, VSCode, etc.), which enables versioning, collaboration, and CI/CD. Project access can be restricted to a set of users and roles. -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
10
Maestral
Open-source Dropbox client for macOS and Linux
Maestral is a lightweight Dropbox client for macOS and Linux. It provides powerful command line tools, supports gitignore patterns to exclude local files from syncing, and allows syncing multiple Dropbox accounts. The CLI allows configuring an unlimited number of Dropbox accounts. Just pass a new config name when linking a new account. More fine-grained controls in the GUI and command line interface allow excluding individual files with selective sync. Maestral is not an official Dropbox App. It therefore does not count towards the three-device limit for Basic Dropbox accounts. Exclude local items from syncing by placing a .mignore file in the Dropbox root with patterns matching any number of items. -
11
Map-Anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Map-Anything is a universal, feed-forward transformer for metric 3D reconstruction that predicts a scene’s geometry and camera parameters directly from visual inputs. Instead of stitching together many task-specific models, it uses a single architecture that supports a wide range of 3D tasks—multi-image structure-from-motion, multi-view stereo, monocular metric depth, registration, depth completion, and more. The model flexibly accepts different input combinations (images, intrinsics, poses, sparse or dense depth) and produces a rich set of outputs including per-pixel 3D points, camera intrinsics, camera poses, ray directions, confidence maps, and validity masks. Its inference path is fully feed-forward with optional mixed-precision and memory-efficient modes, making it practical to scale to long image sequences while keeping latency predictable. -
12
Materials Discovery: GNoME
AI discovers 520000 stable inorganic crystal structures for research
Materials Discovery (GNoME) is a large-scale research initiative by Google DeepMind focused on applying graph neural networks to accelerate the discovery of stable inorganic crystal materials. The project centers on Graph Networks for Materials Exploration (GNoME), a message-passing neural network architecture trained on density functional theory (DFT) data to predict material stability and energy formation. Using GNoME, DeepMind identified 381,000 new stable materials, later expanding the dataset to include over 520,000 materials within 1 meV/atom of the convex hull as of August 2024. The repository provides datasets, model definitions, and interactive Colabs for exploring these materials, computing decomposition energies, and visualizing chemical families. Additionally, it includes JAX-based implementations of GNoME and Nequip—the latter being used to train interatomic potentials for dynamic simulations. -
13
Maya
Datetimes for Humans
Maya is a Python library that simplifies working with datetime objects. It provides a human-friendly API for parsing, formatting, and manipulating dates and times, addressing common frustrations with Python's built-in datetime module. -
14
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training
MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training. -
15
Menagerie
A collection of high-quality models for the MuJoCo physics engine
MuJoCo Menagerie, developed by Google DeepMind, is a curated collection of high-quality simulation models designed for use with the MuJoCo physics engine. It serves as a comprehensive library of accurate and ready-to-use robotic, biomechanical, and mechanical models, ensuring users can perform reliable simulations without having to build or tune models from scratch. The repository aims to improve reproducibility and quality across robotics research by providing verified models that adhere to consistent design and physical standards. Each model directory contains its 3D assets, MJCF XML definitions, licensing information, and example scenes for visualization and testing. The collection spans a wide range of categories including robotic arms, humanoids, quadrupeds, mobile manipulators, drones, and biomechanical systems. Users can access models directly via the robot_descriptions Python package or by cloning the repository for use in interactive MuJoCo simulations. -
16
Mercury
Convert Python notebook to web app and share with non-technical users
Turn Python notebooks to web applications with open-source Mercury framework. Hide code and add interactive widgets. Non-technical users can tweak widgets and execute notebook with new parameters. The core of Mercury is Open Source under AGPLv3. We provide Mercury Pro with additional features, dedicated support and friendly commercial license. Mercury is a perfect tool to convert Python notebook to interactive web application and share with non-programmers. You define interactive widgets for your notebook with the YAML header. Your users can change the widgets values, execute the notebook and save result (as PDF or html file). You can hide your code to not scare your (non-coding) collaborators. Easily deploy to any server. Mercury is dual-licensed. Looking for dedicated support, a commercial-friendly license, and more features? The Mercury Pro is for you. -
17
Merlion
A Machine Learning Framework for Time Series Intelligence
Merlion is a Python library for time series intelligence. It provides an end-to-end machine learning framework that includes loading and transforming data, building and training models, post-processing model outputs, and evaluating model performance. It supports various time series learning tasks, including forecasting, anomaly detection, and change point detection for both univariate and multivariate time series. This library aims to provide engineers and researchers a one-stop solution to rapidly develop models for their specific time series needs, and benchmark them across multiple time series datasets. -
18
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. -
19
Mirrorcast
Open Source Alternative to Chromecast, Mirror Desktop and Play media r
The idea is to replicate what Chromecast can do in regards to screen mirroring and streaming media to a remote display. Google chromes screen mirroring feature works well when used with a receiver such as Chromecast but this is a proprietary solution and audio does not work for desktop mirroring on some operating systems. At the moment, there is only a client for Debian/Ubuntu Operating systems and a server/receiver application for Raspberry pi. Mirrorcast aims to be a low latency screen mirroring solution with high-quality video and audio at 25-30fps, the later is why we will not use something like VNC. Mirrorcast uses up about the same amount of system resources as google chromes cast feature. The delay is less than 1 second on most networks. To achieve this we will use existing FOSS software such as ffmpeg, mpv, and omxplayer. -
20
Mist Cloud Management Platform
Mist is an open source, multicloud management platform
Mist CE is an open-source multi-cloud management platform, offering unified control and monitoring for hybrid and multi-cloud environments. -
21
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. -
22
MozDef
MozDef: Mozilla Enterprise Defense Platform
MozDef aims to bring real-time incident response and investigation to the defensive toolkits of security operations groups in the same way that Metasploit, LAIR, and Armitage have revolutionized the capabilities of attackers. We use MozDef to ingest security events, alert us to security issues, investigate suspicious activities, handle security incidents, and visualize and categorize threat actors. The real-time capabilities allow our security personnel all over the world to work collaboratively even though we may not sit in the same room together and see changes as they occur. The integration plugins allow us to have the system automatically respond to attacks in a preplanned fashion to mitigate threats as they occur. -
23
Mozc Devices
Circuit diagrams and firmware source code for Gboard DIY keyboards
mozc-devices is an open source collection of circuit diagrams, firmware, and technical documentation for a series of experimental and often humorous Gboard and Google Japanese Input hardware keyboards, many of which were originally released as April Fools’ projects by Google Japan. Each subproject in the repository corresponds to a unique input device prototype, including versions such as the Drum Set, Morse Code, Patapata, Magic Hand, Piropiro, Physical Flick, Puchi Puchi, Nazoru, Mageru, Yunomi, Bar, Caps, Double Sided, and Dial editions. These devices creatively reinterpret how users can interact with Japanese text input, blending humor, engineering, and physical computing. The repository serves as an archive of the schematics, firmware, and PCB designs for these inventive input mechanisms, with many projects including promotional videos and technical references. -
24
NExfil
Fast OSINT tool for discovering web profiles by username
NExfil is an open source OSINT (Open Source Intelligence) tool designed to locate user profiles across the web based on a given username. Developed in Python, the tool automates the process of checking hundreds of websites to determine whether a specific username exists on those platforms. By performing automated queries across numerous services, NExfil helps investigators, researchers, and security professionals quickly identify potential accounts associated with a particular username. The tool focuses on delivering results rapidly while minimizing false positives during the search process. Users can supply a single username, multiple usernames, or a file containing a list of usernames for bulk scanning. NExfil processes these inputs and attempts to detect matching profiles across more than 350 websites within seconds. Because it is command-line based and open source, it can be easily integrated into OSINT workflows and cybersecurity research environments. -
25
NVIDIA AgentIQ
The NVIDIA AgentIQ toolkit is an open-source library
NVIDIA AgentIQ is an open-source toolkit designed to efficiently connect, evaluate, and accelerate teams of AI agents. It provides a framework-agnostic platform that integrates seamlessly with various data sources and tools, enabling developers to build composable and reusable agentic workflows. By treating agents, tools, and workflows as simple function calls, AgentIQ facilitates rapid development and optimization of AI-driven applications, enhancing collaboration and efficiency in complex tasks.
