Open Source AI Projects
Discover 87+ curated GitHub repositories for building with AI. Updated daily with trending projects, frameworks, and tools.
Showing 1–3 of 3 projects
markitdown
microsoft/markitdown
Microsoft's Python tool for converting various file formats (PDF, DOCX, PPTX, images) to clean Markdown. Designed for RAG pipelines and document processing workflows.
Solves a common pain point in RAG systems by providing reliable document-to-markdown conversion for better text processing.
funNLP
fighting41love/funNLP
Comprehensive Chinese NLP resource collection including datasets, models, tools, and libraries for various Chinese language processing tasks. Covers everything from word segmentation to knowledge graphs.
Invaluable resource for Chinese NLP development with extensive tools and datasets not readily available elsewhere.
pathway
pathwaycom/pathway
Python ETL framework optimized for stream processing, real-time analytics, and LLM pipelines with built-in RAG capabilities. Combines batch and streaming data processing with AI-first design.
Bridges traditional data processing with modern AI workflows, perfect for building real-time RAG systems and LLM data pipelines.