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
Foxel: Manage Private Cloud Files with AI Search
Foxel is a self-hosted file hub for individuals and teams that connects multiple storage backends in one interface. It combines file previews, access controls, sharing, and semantic search for finding content beyond filenames.
Damn-Vulnerable-RESTaurant-API-Game: Practice API Security
A deliberately insecure Python API for practicing vulnerability discovery, exploitation, and remediation. Developers, ethical hackers, and security engineers can run it locally with Docker as a controlled training environment.
gitingest: Turn Git Repositories into LLM-Ready Text
Gitingest packages a Git repository or local directory into a structured text digest designed to provide code context to language models. Use it from the command line, Python, a browser extension, or its hosted web app.
RAG-Anything: Search Documents Across Text, Images, Tables, and Equations
RAG-Anything extends LightRAG with a pipeline for parsing and querying multimodal documents. It is aimed at teams and researchers who need one retrieval system for mixed-content files rather than text-only RAG.
thefuck: Correct Failed Shell Commands
The Fuck suggests corrected versions of failed console commands, from typos to common Git and permission errors. It is a Python command-line tool for shell users who want quick, reviewable fixes without retyping commands.
docling-api: Convert Documents to Markdown Through an API
docling-api is a self-hostable FastAPI service that converts documents and images into Markdown using Docling. It suits teams that need synchronous or queued batch processing, with CPU and GPU deployment options.
giskard-oss: Test and Red-Team LLM Agents
Giskard is a Python toolkit for evaluating agent behavior and probing AI systems for vulnerabilities. It suits teams building LLM agents or RAG applications that need repeatable checks, safety testing, and adversarial evaluation.
parakeet-mlx: Transcribe Audio on Apple Silicon
parakeet-mlx runs Nvidia Parakeet speech recognition models on Apple Silicon using MLX. It provides command-line and Python interfaces for transcription, timestamps, chunking, and streaming audio.
mypy: Check Python Types Without Running Your Code
mypy is a static type checker that finds type-related issues in Python code before it runs. Add type hints incrementally, then use mypy locally or in a development workflow to catch mistakes and make code easier to maintain.
PayloadsAllTheThings: Find Web Security Payloads and Bypass Techniques
A community-maintained reference of payloads and bypass techniques for web application security testing. Use it to research vulnerability scenarios, support authorized penetration tests, and find ready-to-use Burp Intruder files.
datatrove: Build Large-Scale Text Data Pipelines
DataTrove is a Python library for processing, filtering, and deduplicating text datasets at scale. It combines reusable pipeline blocks with local and cluster executors, making it useful for data preparation workflows such as building LLM training corpora.
EasyEdit: Edit Knowledge and Steer Large Language Models
EasyEdit is a framework for changing specific knowledge or behavior in large language models and evaluating the effects. It brings together multiple editing and inference-time steering methods for researchers and developers comparing approaches or testing targeted edits.