Open Source Python Projects
Discover 607 open source Python repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Python projects here are most often combined with Library, Developer Tools and LLM. Last updated October 4, 2026.
607 repositories · updated October 4, 2026
graphrag: Build Knowledge Graphs for LLM Question Answering
Microsoft GraphRAG is a Python pipeline that uses LLMs to turn unstructured text into structured, graph-based context for question answering. It is suited to teams exploring graph-enhanced retrieval over private data, with indexing costs and maintenance-mode status to consider.
scikit-learn: Build Machine Learning Models in Python
scikit-learn is a Python machine learning library built on SciPy. It helps developers and data practitioners build and evaluate machine learning workflows, with plotting support and documentation for installation and development.
pedalboard: Process Audio and Apply Effects in Python
Pedalboard is a Python library for reading, transforming, and rendering audio, with built-in effects and support for VST3 and Audio Unit plugins. It suits audio developers and machine-learning workflows that need programmable audio processing.
Agent-S: Automate Desktop Tasks Through a GUI Agent
Agent-S is a Python framework that uses screenshots, mouse clicks, and keyboard input to carry out natural-language tasks in desktop applications. It suits research and automation workflows that need an agent to interact with a real computer interface.
dlt: Load Data from Sources into Analytics Destinations
dlt is a Python library for building data-loading pipelines that extract data from APIs, databases, files, and Python objects, then load it into analytics destinations. It handles schema inference, normalization, and incremental loading within your existing code.
sumy: Summarize Text and HTML Documents
sumy is a Python library and command-line tool that extracts concise summaries from plain text and HTML. It offers several extractive summarization methods, language tokenization support, and tools for evaluating summaries.
cerberus: Validate Python Data Against Schemas
Cerberus is a lightweight Python library for checking data against schemas, with built-in type validation and extension points for custom rules. It suits applications that need reusable input validation without adding runtime dependencies.
opik: Trace, Evaluate, and Monitor LLM Applications
Opik is a platform for tracing and evaluating LLM applications, RAG systems, and AI agents. Teams can use it to inspect workflows, run evaluations, and monitor deployments, either self-hosted or through Comet Cloud.
StreamDiffusion: Generate Images in Real Time with Diffusion
StreamDiffusion adapts diffusion pipelines for interactive image generation, with support for text-to-image and image-to-image workflows. It targets developers building responsive GPU-powered demos and applications.
Toolkit-for-Prompt-Compression: Evaluate and Apply Prompt Compression
PCToolkit is a Python toolkit for applying and evaluating prompt-compression methods for large language models. It brings five compressors, datasets, and evaluation metrics behind modular interfaces, making it useful for comparing methods across language tasks.
magic-wormhole: Transfer Files Safely Between Computers
Magic Wormhole is a Python library and command-line tool for sending files, directories, or short text between computers using a one-time, human-readable code. It is useful when you want a simple transfer without exchanging a permanent account or memorizing credentials.
picotron: Train Llama-Like Models with Distributed Parallelism
Picotron is a compact Python framework for learning and experimenting with distributed pre-training of Llama-like models. It demonstrates data, tensor, pipeline, and context parallelism, prioritizing readable code over peak performance.