Best open-source Python projects

A self-hosted Python pipeline that collects news from many sources, scores and deduplicates it, and writes a daily briefing in English and Chinese.

Open-source document parser that converts PDF, Office, HTML and other files into structured data for generative AI pipelines.

Open-source massively multilingual zero-shot text-to-speech model supporting 600+ languages, with voice cloning and voice design.

Self-hosted, OpenAI-compatible LLM gateway that routes one endpoint to 40+ providers with virtual keys, budgets, and usage tracking.

A collection of 177 validated agent skills that teach AI coding agents to work with scientific libraries, databases and research workflows.

Turns a codebase, its docs, schemas and PDFs into a queryable knowledge graph for AI coding assistants, built locally with tree-sitter AST parsing.

Blender add-on and MCP server that let AI assistants like Claude build, modify and inspect 3D scenes in Blender through prompts.

A toolkit that generates agent-native command-line interfaces for existing software, plus a CLI-Hub registry for installing ready-made ones.

A Python framework for recursive harness optimization that refines the prompts, tools and orchestration around a fixed LLM agent on unseen tasks.

A Claude Code skill that digs into unfamiliar topics citation by citation until it reaches primary sources, then builds an annotated extract page.

A Python library for building styled, publication-quality display tables from pandas or Polars DataFrames, rendered to HTML or images.

An open-source reinforcement learning agent for competitive Guandan, a four-player partnership card game, with a playable web table.

A Claude Code skill that reads your local session logs to explain where token usage went and why you hit limits.

Desktop tool that pulls e-invoices (PDF, OFD, XML) from QQ or 163 email, recognizes them with OCR, sorts them into folders and builds an Excel expense summary.

A Streamlit web app that turns uploaded bitmap images into editable SVG vectors, built on the Vecto .NET tracing engine.

A VS Code extension that turns plain .chat.md files into editable AI chat sessions with MCP tool support across LLM providers.

Self-hosted control plane for TLS certificates that issues, renews, discovers, inventories and deploys them across your infrastructure.

Builds a complete full-text historical archive of an RSS or Atom feed by pulling past posts from the Wayback Machine.

Open-source Python library for building AI agents that control a real browser, with optional Browser Use Cloud stealth browsers and hosted agent API.

Apache Superset is a self-service business intelligence web app for exploring data, building charts, dashboards and running SQL against many databases.