Open Source Python Software - Page 95
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.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
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
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers. Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the new FullyShardedDataParallel (FSDP) wrapper provided by fairscale. Fairseq can be extended through user-supplied plug-ins. Models define the neural network architecture and encapsulate all of the learnable parameters. Criterions compute the loss function given the model outputs and targets. Tasks store dictionaries and provide helpers for loading/iterating over Datasets, initializing the Model/Criterion and calculating the loss. -
2
FastChat
Open platform for training, serving, and evaluating language models
FastChat is an open platform for training, serving, and evaluating large language model-based chatbots. If you do not have enough memory, you can enable 8-bit compression by adding --load-8bit to the commands above. This can reduce memory usage by around half with slightly degraded model quality. It is compatible with the CPU, GPU, and Metal backend. Vicuna-13B with 8-bit compression can run on a single NVIDIA 3090/4080/T4/V100(16GB) GPU. In addition to that, you can add --cpu-offloading to commands above to offload weights that don't fit on your GPU onto the CPU memory. This requires 8-bit compression to be enabled and the bitsandbytes package to be installed, which is only available on linux operating systems. -
3
FastKoko
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model
FastKoko is a self-hosted text-to-speech server built around the Kokoro-82M model and exposed through a FastAPI backend. It is designed to be easy to deploy via Docker, with separate CPU and GPU images so that users can choose between pure CPU inference and NVIDIA GPU acceleration. The project exposes an OpenAI-compatible speech endpoint, which means existing code that talks to the OpenAI audio API can often be pointed at a Kokoro-FastAPI instance with minimal changes. It supports multiple languages and voicepacks and allows phoneme based generation for more accurate pronunciation and prosody. The server also offers per-word timestamped captions, which makes it useful for creating subtitles or aligning audio with text. A built in web UI, API documentation, and debug endpoints for monitoring system status help users explore voices, test requests, and integrate the service into larger systems. -
4
FastVLM
This repository contains the official implementation of FastVLM
FastVLM is an efficiency-focused vision-language modeling stack that introduces FastViTHD, a hybrid vision encoder engineered to emit fewer visual tokens and slash encoding time, especially for high-resolution images. Instead of elaborate pruning stages, the design trades off resolution and token count through input scaling, simplifying the pipeline while maintaining strong accuracy. Reported results highlight dramatic speedups in time-to-first-token and competitive quality versus contemporary open VLMs, including comparisons across small and larger variants. The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
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
FeelUOwn
Trying to be a robust, user-friendly and hackable music player
FeelUOwn is a user-friendly, and hackable music player. -
6
FinalRecon
All-in-one Python web reconnaissance tool for fast target analysis
FinalRecon is an all-in-one web reconnaissance tool written in Python that helps security professionals gather information about a target website quickly and efficiently. It combines multiple reconnaissance techniques into a single command-line utility so users do not need to run several separate tools to collect similar data. FinalRecon focuses on providing a fast overview of a web target while maintaining accuracy in the collected results. It includes modules for gathering server information, analyzing SSL certificates, performing WHOIS lookups, and crawling website resources. FinalRecon can also enumerate DNS records, discover subdomains, search for directories and files, and scan common network ports. Historical URLs and resources can be retrieved from archived sources to help analyze changes in a website over time. Designed primarily for penetration testers and security researchers, FinalRecon simplifies the reconnaissance phase of security assessments. -
7
Fingerprint Pro Server Python SDK
Python SDK for Fingerprint Pro Server API
Fingerprint Pro Server API allows you to get information about visitors and about individual events in a server environment. It can be used for data exports, decision-making, and data analysis scenarios. Server API is intended for server-side usage, it's not intended to be used from the client side, whether it's a browser or a mobile device. -
8
FitTrackee
Self-hosted outdoor activity tracker
FitTrackee is a self-hostable fitness tracking and workout management platform designed to help individuals and small groups monitor physical activity, set goals, and review performance over time with clarity and flexibility. It provides an organized environment for logging workouts, recording metrics like sets, reps, durations, and weights, and visualizing progress through charts and summaries that detail trends in strength, endurance, and consistency. Instead of locking users into proprietary ecosystems or paid plans, FitTrackee lets you keep your own data on your server, giving full control over privacy and longevity of your fitness history. The interface is designed to be flexible enough for everyday gym routines, home workouts, and personalized training plans, supporting a variety of exercise types and custom attributes for different training styles. -
9
Flax
Flax is a neural network library for JAX
Flax is a flexible neural-network library for JAX that embraces functional programming while offering ergonomic module abstractions. Its design separates pure computation from state by threading parameter collections and RNGs explicitly, enabling reproducibility, transformation, and easy experimentation with JAX transforms like jit, pmap, and vmap. Modules define parameterized computations, but initialization and application remain side-effect free, which pairs naturally with JAX’s staging and compilation model. Flax emphasizes composability: optimizers, training loops, and checkpointing are provided as examples or utilities rather than monolithic frameworks, encouraging research-friendly customization. The library is widely used in vision, language, and reinforcement learning, often serving as a thin layer atop NumPy-like JAX primitives. Tutorials and examples show patterns for multi-host training, mixed precision, and advanced input pipelines that scale from laptops to TPUs. -
$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.
-
10
Flower
Flower: A Friendly Federated Learning Framework
A unified approach to federated learning, analytics, and evaluation. Federate any workload, any ML framework, and any programming language. Federated learning systems vary wildly from one use case to another. Flower allows for a wide range of different configurations depending on the needs of each individual use case. Flower originated from a research project at the University of Oxford, so it was built with AI research in mind. Many components can be extended and overridden to build new state-of-the-art systems. Different machine learning frameworks have different strengths. Flower can be used with any machine learning framework, for example, PyTorch, TensorFlow, Hugging Face Transformers, PyTorch Lightning, scikit-learn, JAX, TFLite, MONAI, fastai, MLX, XGBoost, Pandas for federated analytics, or even raw NumPy for users who enjoy computing gradients by hand. -
11
Flowly AI
Flowly is 100x faster than OpenClaw
Flowly is an open-source personal AI assistant that runs locally on your machine and connects to multiple communication platforms like Telegram, WhatsApp, Discord, and Slack. It acts as a centralized AI system that can perform tasks such as web browsing, file management, command execution, scheduling, and more—all while keeping your data private. Designed for flexibility, Flowly supports multiple AI providers and models through LiteLLM, allowing users to customize how their assistant behaves. It features a multi-agent architecture where different specialized agents can collaborate, delegate tasks, and operate in parallel. Flowly also includes voice capabilities, enabling real-time phone interactions using speech-to-text and text-to-speech systems. Overall, it provides a powerful, extensible, and privacy-focused alternative to cloud-based AI assistants. -
12
Frontend Slides
Create beautiful slides on the web using Claude's frontend skills
Frontend Slides is a lightweight tool that enables users to create visually appealing, animation-rich web presentations without requiring knowledge of CSS or JavaScript by leveraging a guided, interactive workflow. It operates on a “show, don’t tell” philosophy, generating visual previews of styles so users can select their preferred design rather than describing it abstractly. The system produces fully self-contained HTML presentations with inline CSS and JavaScript, eliminating the need for external dependencies, build tools, or frameworks. It also supports converting existing PowerPoint files into web-based presentations while preserving content such as images, text, and structure. The tool includes curated design presets that avoid generic AI-generated aesthetics, ensuring presentations feel distinctive and intentional. Its architecture uses progressive disclosure, loading only necessary components at each step to keep the workflow efficient and intuitive. -
13
FuXi
FuXi is a fast, self-contained AI coding agent
FuXi is a terminal-first AI coding agent designed to read code, edit files, run commands, and operate development tools from a rich TUI. Built in Go, it ships as a self-contained static binary with no runtime dependencies. Its agent loop follows a Think, Act, and Verify pattern so models can reason about a task, make changes, and check the results. It supports cost-aware routing and automatic failover across multiple LLM providers, including OpenAI-compatible services and other supported backends. More than 50 built-in tools cover file operations, shell access, search, diagnostics, Jupyter, browser use, background tasks, and parallel sub-agents. Sessions are persistent, extensible through MCP, hooks, skills, and plugins, and protected by command classification, permissions, and audit logging. -
14
FuseSoC
Package manager and build abstraction tool for FPGA/ASIC development
FuseSoC is a package manager and build abstraction tool for hardware description language (HDL) code, aimed at simplifying the development and reuse of IP cores. It provides a standardized way to describe, manage, and build hardware projects, facilitating collaboration and reducing duplication of effort in FPGA and ASIC development. -
15
GEF
Modern experience for GDB with advanced debugging capabilities
GEF is a set of commands for x86/64, ARM, MIPS, PowerPC and SPARC to assist exploit developers and reverse-engineers when using old-school GDB. It provides additional features to GDB using the Python API to assist during the process of dynamic analysis and exploit development. Application developers will also benefit from it, as GEF lifts a great part of regular GDB obscurity, avoiding repeating traditional commands or bringing out the relevant information from the debugging runtime. -
16
GIF for CLI
Takes in a GIF, short video, or a query to the Tenor GIF API
gif-for-cli is a small, playful utility that brings animated GIFs to the command line by rendering frames directly in a terminal. It takes an input GIF (or a URL) and converts each frame into a terminal-friendly representation, timing updates to approximate the original animation. Depending on terminal capabilities, it can use ANSI color blocks or image protocols to achieve surprisingly faithful playback. The tool includes conveniences such as looping control, scaling to fit your terminal, and caching to avoid repeated downloads. It’s useful for quick visual feedback, lightweight demos, or just adding some personality to scripts and readmes. Despite its whimsical nature, the project is a tight example of frame decoding, timing, and terminal rendering glued together in a single command. -
17
GLM-4.1V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.1V — often referred to as a smaller / lighter version of the GLM-V family — offers a more resource-efficient option for users who want multimodal capabilities without requiring large compute resources. Though smaller in scale, GLM-4.1V maintains competitive performance, particularly impressive on many benchmarks for models of its size: in fact, on a number of multimodal reasoning and vision-language tasks it outperforms some much larger models from other families. It represents a trade-off: somewhat reduced capacity compared to 4.5V or 4.6V, but with benefits in terms of speed, deployability, and lower hardware requirements — making it especially useful for developers experimenting locally, building lightweight agents, or deploying on limited infrastructure. Given its open-source availability under the same project repository, it provides an accessible entry point for testing multimodal reasoning and building proof-of-concept applications. -
18
GLM-4.5V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.5V is the preceding iteration in the GLM-V series that laid much of the groundwork for general multimodal reasoning and vision-language understanding. It embodies the design philosophy of mixing visual and textual modalities into a unified model capable of general-purpose reasoning, content understanding, and generation, while already supporting a wide variety of tasks: from image captioning and visual question answering to content recognition, GUI-based agents, video understanding, and long-document interpretation. GLM-4.5V emerged from a training framework that leverages scalable reinforcement learning (with curriculum sampling) to boost performance across tasks ranging from STEM problem solving to long-context reasoning, giving it broad applicability beyond narrow benchmarks. When it was released, it achieved state-of-the-art results on a large collection of public multimodal benchmarks for open-source models. -
19
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.6V represents the latest generation of the GLM-V family and marks a major step forward in multimodal AI by combining advanced vision-language understanding with native “tool-call” capabilities, long-context reasoning, and strong generalization across domains. Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and can output or act via tools seamlessly, bridging perception and execution. Its architecture supports a very large context window (on the order of 128K tokens during training), which lets it handle complex multimodal inputs like long documents, multi-page reports, or video transcripts, while maintaining coherence across extended content. In benchmarks and internal evaluations, GLM-4.6V achieves state-of-the-art (SoTA) performance among models of comparable parameter scale on multimodal reasoning. -
20
GPT Discord
A robust, all-in-one GPT interface for Discord
GPTDiscord is an all-in-one AI bot that brings ChatGPT-style workflows directly into Discord. It supports long-running conversations, model settings, multimodal image understanding, and generated images. The bot can answer questions using custom documents, websites, PDFs, and Discord channel history as context. It also includes internet-connected chat, AI moderation, translation, usage tracking, and automatic retries when upstream requests fail. More advanced setups can use code interpretation, data analysis, vector search, and document indexes for richer server workflows. GPTDiscord is best suited for communities that want a powerful AI assistant inside Discord rather than a simple prompt-and-response bot. -
21
GPTImage2Skill
GPT Image 2 prompt gallery, image prompt library, agentic skill
GPTImage2Skill is a curated prompt gallery, agent skill, and command-line workflow for working with GPT Image 2 generation and editing. It provides reusable image prompts across creative, technical, academic, interface, design, photography, typography, gaming, anime, map, tattoo, and reference-editing use cases. The project is designed to help agents and users produce stronger visual outputs without starting from a blank prompt every time. Its gallery is organized into category files so an agent can load only the relevant prompt references instead of overwhelming the context window. It also includes installation paths for skill-capable environments such as Claude Code, Codex, OpenClaw, and other agent runtimes. Overall, it is useful as both a learning resource for prompt structure and a practical toolkit for repeatable image generation workflows. -
22
GR00T Whole-Body Control (WBC)
Welcome to GR00T Whole-Body Control (WBC)
GR00T Whole-Body Control is NVIDIA’s unified platform for training, evaluating, and deploying advanced humanoid robot controllers. It includes the decoupled controller used with GR00T N1.5 and N1.6, combining reinforcement learning for the lower body with inverse kinematics for the upper body. The GEAR-SONIC system learns a broad set of natural motor skills from large-scale human motion data through a unified tracking policy. Released Unitree G1 checkpoints support motion references, whole-body teleoperation, planning, and vision-language-action workflows. A C++ and TensorRT inference stack provides real-hardware deployment, while PyTorch checkpoints support Isaac Lab evaluation and continued training. The repository also includes VR teleoperation, data collection, kinematic planning, and low-latency control configurations. MotionBricks adds real-time latent motion generation for interactive animation and robotics applications. -
23
GemGIS
Spatial data processing for geomodeling
GemGIS is a Python-based, open-source geographic information processing library. It is capable of preprocessing spatial data such as vector data (shape files, geojson files, geopackages,…), raster data (tif, png,…), data obtained from online services (WCS, WMS, WFS) or XML/KML files (soon). Preprocessed data can be stored in a dedicated Data Class to be passed to the geomodeling package GemPy in order to accelerate the model-building process. Postprocessing of model results will allow export from GemPy to geoinformation systems such as QGIS and ArcGIS or to Google Earth for further use. -
24
Gemini Fullstack LangGraph Quickstart
Get started w/ building Fullstack Agents using Gemini 2.5 & LangGraph
gemini-fullstack-langgraph-quickstart is a fullstack reference application from Google DeepMind’s Gemini team that demonstrates how to build a research-augmented conversational AI system using LangGraph and Google Gemini models. The project features a React (Vite) frontend and a LangGraph/FastAPI backend designed to work together seamlessly for real-time research and reasoning tasks. The backend agent dynamically generates search queries based on user input, retrieves information via the Google Search API, and performs reflective reasoning to identify knowledge gaps. It then iteratively refines its search until it produces a comprehensive, well-cited answer synthesized by the Gemini model. The repository provides both a browser-based chat interface and a command-line script (cli_research.py) for executing research queries directly. For production deployment, the backend integrates with Redis and PostgreSQL to manage persistent memory, streaming outputs, & background task coordination. -
25
GenMedia Creative Studio
AI generative media user experience highlighting use of APIs
GenMedia Creative Studio is a Google Cloud reference application for experimenting with generative media workflows on Vertex AI. It provides a user experience for working with models and APIs such as Gemini, Veo, Imagen, Gemini Image, Gemini TTS, Chirp 3, and Lyria. The project is built to showcase multimodal creation across text, image, video, speech, and music from one deployable interface. It is useful for creators, marketers, developers, and technical teams that want to prototype media-generation experiences using Google Cloud services. The repository also includes experiments and MCP-related materials for connecting generative media capabilities to agent workflows. It is not an officially supported Google product, so it is best treated as a reference implementation and creative sandbox rather than a managed commercial service.
