DALI provides a modular, extensible SDK for building document AI agents capable of ingesting images, PDFs, and scanned files. It integrates OCR engines and vision-language models to detect layout elements, extract tables, and answer user queries. Developers can customize pipelines, plug in different LLMs, and deploy interactive web or command-line interfaces. With built-in support for caching, batching, and multi-model orchestration, DALI accelerates document understanding tasks with minimal code.

Deerflow provides a visual interface where users can assemble AI workflows from modular components—input processors, LLM or model executors, conditional logic, and output handlers. Out of the box connectors allow you to pull data from databases, APIs, or document stores, then pass results through one or more AI models in sequence. Built-in tools handle logging, error recovery, and metric tracking. Once configured, workflows can be tested interactively and deployed as REST endpoints or event-driven triggers. A dashboard gives real-time insights, version history, alerts, and team collaboration features, making it simple to iterate, scale, and maintain AI agents in production.