Open Source Python Software - Page 51
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.
-
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.
-
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
Happy-LLM
Large Language Model Principles and Practice Tutorial from Scratch
Happy-LLM is an open-source educational project created by the Datawhale AI community that provides a structured and comprehensive tutorial for understanding and building large language models from scratch. The project guides learners through the entire conceptual and practical pipeline of modern LLM development, starting with foundational natural language processing concepts and gradually progressing to advanced architectures and training techniques. It explains the Transformer architecture, pre-training paradigms, and model scaling strategies while also providing hands-on coding examples so readers can implement and experiment with their own models. The tutorial emphasizes practical understanding by walking users through building and training small language models, including tokenizer construction, pre-training workflows, and fine-tuning methods. -
2
Harpoon
Command line OSINT and threat intelligence automation tool
Harpoon is a command line tool designed to assist with open source intelligence (OSINT) and threat intelligence investigations. It helps security professionals and researchers collect and analyze publicly available information from a wide range of online sources. Harpoon is written in Python and organized around a modular plugin system, where each plugin is responsible for querying a specific platform, API, or intelligence service. This design allows users to automate many reconnaissance and intelligence gathering tasks directly from the terminal. Harpoon integrates with numerous security and data services such as Shodan, VirusTotal, AlienVault OTX, and many other intelligence providers to retrieve information about domains, IP addresses, emails, and other indicators. Many commands rely on API keys that can be configured through a central configuration file, allowing users to connect their own intelligence accounts and data sources. -
3
Heretic
Fully automatic censorship removal for language models
Heretic is an open-source Python tool that automatically removes the built-in censorship or “safety alignment” from transformer-based language models so they respond to a broader range of prompts with fewer refusals. It works by applying directional ablation techniques and a parameter optimization strategy to adjust internal model behaviors without expensive post-training or altering the core capabilities. Designed for researchers and advanced users, Heretic makes it possible to study and experiment with uncensored model responses in a reproducible, automated way. The project can decensor many popular dense and some mixture-of-experts (MoE) models, supporting workflows that would otherwise require manual tuning. Beyond simple decensoring, Heretic includes research-oriented options for analyzing model internals and interpretability data. -
4
Hindsight
Hindsight: Agent Memory That Learns
Hindsight is an advanced, open-source memory system for AI agents designed to enable long-term learning, reasoning, and consistency across interactions by treating memory as a first-class component of intelligence rather than a simple retrieval layer. It addresses one of the core limitations of modern AI agents, which is their inability to retain and meaningfully use past experiences over time, by introducing a structured, biomimetic memory architecture inspired by how human memory works. Instead of relying solely on vector similarity or basic retrieval techniques, Hindsight organizes information into distinct categories such as facts, experiences, beliefs, and observations, allowing agents to differentiate between raw data and inferred knowledge. The system operates through three core mechanisms—retain, recall, and reflect—which respectively handle storing information, retrieving relevant context, and generating new insights based on accumulated experience. -
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.
-
5
Hiring Agent
AI agent to evaluate and score resumes
Hiring Agent is an AI-powered resume evaluation pipeline for screening technical candidates. It reads a resume PDF and converts the content into Markdown-like text. It then uses a local or hosted language model to extract structured candidate information into sectioned JSON. The system can enrich that resume data with GitHub profile and repository signals when a profile is available. After the data is collected, it produces an explainable evaluation with category scores, supporting evidence, bonus points, and deductions. It can run locally with Ollama or use Google Gemini, which makes it flexible for teams that want either private local processing or hosted model access. -
6
Howdy For Linux
Windows Hello style facial authentication for Linux
Howdy provides Windows Hello™ style authentication for Linux. Use your built-in IR emitters and camera in combination with facial recognition to prove who you are. Using the central authentication system (PAM), works everywhere you would otherwise need your password: Login, lock screen, sudo, su, etc. -
7
HumanEval
Code for the paper "Evaluating Large Language Models Trained on Code"
human-eval is a benchmark dataset and evaluation framework created by OpenAI for measuring the ability of language models to generate correct code. It consists of hand-written programming problems with unit tests, designed to assess functional correctness rather than superficial metrics like text similarity. Each task includes a natural language prompt and a function signature, requiring the model to generate an implementation that passes all provided tests. The benchmark has become a standard for evaluating code generation models, including those in the Codex and GPT families. Researchers can use the dataset to run reproducible comparisons across models and track improvements in functional code synthesis. By focusing on correctness through execution, human-eval provides a rigorous and practical way to evaluate programming capabilities in AI systems. -
8
Hummingbot
Build trading bots that run on any exchange or blockchain
Hummingbot is an open-source project that integrates cryptocurrency trading on both centralized exchanges and decentralized protocols. It allows users to run a client that executes customized, automated trading strategies for cryptocurrencies. Hummingbot is software that helps you build and run automated trading strategies or bots. Its codebase is free and publicly available on Github under the Apache 2.0 open source license. Hummingbot Foundation is a not-for-profit foundation that facilitates decentralized maintenance and governance of the Hummingbot codebase, powered by the Hummingbot Governance Token (HBOT). Help us democratize high-frequency trading and give sophisticated algorithms to everyone in the world! We created hummingbot to promote decentralized market-making, enabling members of the community to contribute to the liquidity and trading efficiency in cryptocurrency markets. -
9
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
HunyuanOCR is an open-source, end-to-end OCR (optical character recognition) Vision-Language Model (VLM) developed by Tencent‑Hunyuan. It’s designed to unify the entire OCR pipeline, detection, recognition, layout parsing, information extraction, translation, and even subtitle or structured output generation, into a single model inference instead of a cascade of separate tools. Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a wide variety of OCR tasks, outperforming many traditional OCR systems and even other multimodal models on benchmark suites. HunyuanOCR handles complex documents: multi-column layouts, tables, mathematical formulas, mixed languages, handwritten or stylized fonts, receipts, tickets, and even video-frame subtitles. The project provides code, pretrained weights, and inference instructions, making it feasible to deploy locally or on a server, and to integrate with applications. -
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
10
IOS13-SimulateTouch
iOS Automation Framework iOS Touch Simulation Library
A system-wide touch event simulation library for iOS 11.0 - 14. This library enables you to simulate touch events on iOS 11.0 - 14 with just one line of code! Currently, the repository is mainly for programmers. In the future, I will make it suitable for people who do not understand how to code. -
11
Improved GAN
Code for the paper "Improved Techniques for Training GANs"
Improved-GAN is the official code release from OpenAI accompanying the research paper Improved Techniques for Training GANs. It provides implementations of experiments conducted on datasets such as MNIST, SVHN, CIFAR-10, and ImageNet. The project focuses on demonstrating enhanced training methods for Generative Adversarial Networks, addressing stability and performance issues that were common in earlier GAN models. The repository includes training scripts, evaluation methods, and pretrained configurations for reproducing experimental results. By offering structured experiments across multiple datasets, it allows researchers to study and replicate the improvements described in the paper. Although the project is archived and not actively maintained, it remains a reference point in the history of GAN research, influencing subsequent model training approaches. -
12
InstantCharacter
Personalize Any Characters with a Scalable Diffusion Transformer
InstantCharacter is a tuning-free diffusion transformer framework created by Tencent Hunyuan / InstantX team, which enables generating images of a specific character (subject) from a single reference image, preserving identity and character features. Uses adapters, so full fine-tuning of the base model is not required. Demo scripts and pipeline API (via infer_demo.py, pipeline.py) included. It works by adapting a base image generation model with a lightweight adapter so that you can produce character-preserving generations in various downstream tasks (e.g. changing pose, clothing, scene) without needing full model fine-tuning. Works with huggingface/transformers/diffusers ecosystems. -
13
Inter
The Inter font family
Inter is a typeface carefully crafted & designed for computer screens. Inter features a tall x-height to aid in readability of mixed-case and lower-case text. Several OpenType features are provided as well, like contextual alternates that adjusts punctuation depending on the shape of surrounding glyphs, slashed zero for when you need to disambiguate "0" from "o", tabular numbers, etc. Using Inter is as easy as downloading & installing the font files. There's of course no absolute right or wrong when it comes to expressing yourself with typography, but Inter Dynamic Metrics provides guidelines for good typography. You simply provide the optical font size, and the tracking and leading is calculated for you to produce the best results. Inter is a free and open source font family. You are free to use this font in almost any way imaginable. Inter comes with many OpenType features that can be used to tailor functionality and aesthetics to your specific needs. -
14
JoyAI-Echo
Pushing the Frontier of Long Audio-Visual Generation
JoyAI-Echo is an inference-focused framework for long-form audio-video generation. It is designed to create minute-level, multi-shot video stories from structured prompts while preserving continuity across scenes. The system uses a paired cross-modal memory bank to maintain visual identity and voice consistency over longer sequences. It also uses a distilled DMD generator to reduce inference cost and improve generation speed compared with heavier multi-step pipelines. JoyAI-Echo focuses on text-to-video and multi-shot long-video generation, while image-to-video support is not part of the current release scope. It is most useful for research and experimental video workflows that need synchronized audio, coherent characters, and editable story-level generation. -
15
Kaggle CLI
The official CLI to interact with Kaggle
Kaggle CLI is Kaggle’s official command-line interface for interacting with the Kaggle platform from a terminal. It lets users authenticate, search resources, download files, submit competition entries, manage datasets, work with models, run notebooks, and read discussion content without relying only on the web interface. The tool is useful for data scientists who want to automate Kaggle workflows inside scripts, CI jobs, notebooks, or reproducible local environments. It supports both traditional API-token authentication and an OAuth login flow, which makes it more flexible for different usage patterns. kaggle-cli is especially practical when working with large datasets or repeated competition submissions that would be slow to handle manually. Its main value is turning Kaggle’s web-based data science platform into a scriptable developer workflow. -
16
Kale
Kubeflow’s superfood for Data Scientists
KALE (Kubeflow Automated pipeLines Engine) is a project that aims at simplifying the Data Science experience of deploying Kubeflow Pipelines workflows. Kubeflow is a great platform for orchestrating complex workflows on top Kubernetes and Kubeflow Pipeline provides the mean to create reusable components that can be executed as part of workflows. The self-service nature of Kubeflow make it extremely appealing for Data Science use, at it provides an easy access to advanced distributed jobs orchestration, re-usability of components, Jupyter Notebooks, rich UIs and more. Still, developing and maintaining Kubeflow workflows can be hard for data scientists, who may not be experts in working orchestration platforms and related SDKs. Additionally, data science often involve processes of data exploration, iterative modelling and interactive environments (mostly Jupyter notebook). -
17
Knowledge Work Plugins
Open source repository of plugins intended for knowledge workers
Knowledge Work Plugins is Anthropic’s open-source repository of plugin-style Markdown packs for knowledge-work use cases in Claude Cowork and related Claude Code workflows. It is designed to give AI assistants structured domain instructions rather than relying on generic chat behavior. The repository includes plugins for practical office, research, legal, and business workflows, with each plugin stored as editable Markdown. This makes the system easy to inspect, fork, customize, and adapt to an organization’s own process. Its goal is to help agents perform repeatable knowledge work with clearer expectations, domain constraints, and workflow patterns. The project is best suited for teams that want reusable AI work instructions without building a full application around them. -
18
LAMDA
Android reverse engineering & automation framework
Android reverse engineering & automation framework. The most powerful Android capture/reverse/HOOK & cloud phone/remote desktop/automation framework in history, your work has never been so easy and fast. LAMDA is an auxiliary framework for reverse engineering and automation. It is designed to reduce the time and trivial problems of security analysts and application testers. It replaces a large number of manual operations with a programmed interface. It is not a single-function framework. To give you a general idea of its usefulness: Do you install various agents, plug-ins, or point-and-click settings on your phone to complete your work? Do you want to operate a mobile phone thousands of miles away in a different place? Do you have the need to programmatically control your phone? Are you still paying for expensive IP switching , remote ADB debugging , RPA automation and even logcat logs from some cloud mobile phone manufacturers? If so, then yes, just one LAMDA can solve all this. -
19
LLM Action
Technical principles related to large models
LLM-Action is a knowledge/tutorial/repository that shares principles, techniques, and real-world experience related to large language models (LLMs), focusing on LLM engineering, deployment, optimization, inference, compression, and tooling. It organizes content in domains like training, inference, compression, alignment, evaluation, pipelines, and applications. Sections covering infrastructure, engineering, and deployment. Repository templates, sample code, and resource links. Articles/code on LLM compression (quantization, pruning). -
20
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
LLMs-from-scratch is an educational codebase that walks through implementing modern large-language-model components step by step. It emphasizes building blocks—tokenization, embeddings, attention, feed-forward layers, normalization, and training loops—so learners understand not just how to use a model but how it works internally. The repository favors clear Python and NumPy or PyTorch implementations that can be run and modified without heavyweight frameworks obscuring the logic. Chapters and notebooks progress from tiny toy models to more capable transformer stacks, including sampling strategies and evaluation hooks. The focus is on readability, correctness, and experimentation, making it ideal for students and practitioners transitioning from theory to working systems. By the end, you have a grounded sense of how data pipelines, optimization, and inference interact to produce fluent text. -
21
LangChain Open Deep Research
Fully open source deep research agent
Open Deep Research is a configurable, fully open-source agent for producing detailed research reports from complex questions. It separates work across models used for summarization, active research, information compression, and final report generation. Users can select from multiple language model providers as long as the chosen models support tool calling and structured outputs. Search can be powered by several APIs, native provider search, or external tools connected through MCP. The agent runs on LangGraph and can be explored locally through LangGraph Studio, an API, and generated API documentation. Environment settings control model choices, search services, MCP servers, and other research behavior. The repository also includes evaluation scripts for Deep Research Bench, enabling reproducible comparisons across difficult multilingual tasks. -
22
LingBot-World 2.0
Infinite Worlds with Versatile Interactions
LingBot-World v2, also called LingBot-World-Infinity, is a world-modeling project for long-horizon interactive video generation. It extends the original LingBot-World with a causal pretraining approach for maintaining quality over ongoing interaction. The project supports richer interactive elements such as attacks, archery, spell-casting, shooting, and text-driven scene events. A distilled real-time variant is designed for rapid response and 720p, 60 FPS interactive streams. It also introduces an agentic harness where a pilot agent plans character behavior and a director agent creates evolving environmental elements. The repository provides inference code and released 14B causal-fast model access for research and non-commercial use. -
23
Linkedin Scraper
A library that scrapes Linkedin for user data
Linkedin Scraper is a library that scrapes Linkedin for user data. Version 2.0.0 and before is called linkedin_user_scraper and can be installed via pip3 install --user linkedin_user_scraper. The reason is that LinkedIn has recently blocked people from viewing certain profiles without having previously signed in. So by setting scrape=False, it doesn't automatically scrape the profile, but Chrome will open the linkedin page anyways. You can login and logout, and the cookie will stay in the browser and it won't affect your profile views. Then when you run person.scrape(), it'll scrape and close the browser. A driver using Chrome is created by default. However, if a driver is passed in, that will be used instead. -
24
List of Free Learning Resources
Freely available programming books
List of Free Learning Resources is a curated open-source collection of free programming resources, including books, tutorials, and courses across many languages and disciplines. Maintained by the community, it organizes materials by topic, language, and skill level, making it easy to discover learning resources. The repository includes content on software development, computer science, data science, and more. It is continuously updated with new resources contributed by developers worldwide. The project emphasizes accessibility and open education, providing high-quality materials without cost. It serves as a central hub for self-learners and professionals alike. Its structured organization makes it a widely used reference for learning programming. -
25
LuxTTS
A high-quality rapid TTS voice cloning model
LuxTTS is an open-source text-to-speech (TTS) system focused on delivering high-quality, rapid voice synthesis and voice cloning that runs extremely fast and efficiently on consumer hardware. It implements a lightweight architecture based on ZipVoice and optimized sampling techniques so that it can generate speech at speeds up to roughly 150 times real-time on a single GPU and faster than real-time on CPU, all while producing audio at high fidelity with 48 kHz quality. The project supports zero-shot voice cloning, meaning it can adapt to a reference speaker’s voice with minimal example data, enabling realistic and personalized synthetic speech. Intended for developers, hobbyists, and creators, the repository includes installation instructions, usage examples, and Python APIs that make it feasible to integrate the model in local workflows, web demos, or production systems. Its design emphasizes efficiency and practicality, fitting within modest GPU memory footprints.
