// Agent profile
MinerU is an open-source document parsing tool from OpenDataLab that converts PDFs, DOCX, PPTX, XLSX, and images into structured Markdown and JSON formats optimized for LLM consumption. It uses a dual VLM+OCR engine supporting 109 languages, with automatic table detection and HTML conversion. MinerU integrates via CLI, Python/Go/TypeScript SDKs, and MCP protocol, making it suitable for agentic workflows that need to ingest unstructured documents.
MinerU is an open-source document parsing tool developed by OpenDataLab that converts unstructured documents into formats optimized for LLM processing. It handles the full spectrum of business document types — PDFs, Office documents, and images — producing clean Markdown or structured JSON output suitable for RAG pipelines and agentic workflows.
MinerU’s dual-engine approach combines vision language models with traditional OCR for robust extraction across 109 languages. The tool automatically detects and converts tables to HTML format, handles scanned documents, and processes garbled PDFs that simpler parsers fail on.
Integration options include CLI for batch processing, SDKs for Python, Go, and TypeScript, and native MCP protocol support for direct use by AI agents.
Open-source multi-agent framework for AI-driven financial analysis — simulates a hedge fund with specialized analyst agents and a portfolio manager agent.
Incremental data framework for AI agents — ingestion and indexing with Rust-grade performance and propagation of changes across joins.
TypeScript deep financial research agent that produces investor-grade equity research reports — autonomously gathering data, modeling, and writing analyst-quality output.