-
Tools: RAG-Anything (HKUDS)
Reference: https://github.com/HKUDS/RAG-Anything What it is An all-in-one multimodal RAG framework built on top of LightRAG (also from HKUDS) that handles text, images, tables, and mathematical equations within a single unified pipeline — instead of needing separate tools for each content type. 15.1k stars, actively maintained, with a technical report on arXiv. Use…
-
Tools: ade-python (LandingAI)
Reference: https://github.com/landing-ai/ade-python What it is The official Python SDK for LandingAI’s Agentic Document Extraction (ADE) REST API — a fully-typed library with Pydantic response models, sync and async clients, and support for pluggable HTTP backends (httpx or aiohttp). Install with pip install landingai-ade Use case This is the programmatic layer that…
-
Tools: ADE Document Processing Skills (LandingAI)
Reference: https://github.com/landing-ai/ade-document-processing-skills What it is Agent skills that teach coding assistants like Claude Code, Cursor, and Roo Code how to write Python scripts using LandingAI’s Agentic Document Extraction (ADE) — a vision-first document AI that parses complex, real-world documents into structured, auditable data without templates or ML training. Use case Instead…
-
Tools: OpenWiki (langchain-ai)
Reference – https://github.com/langchain-ai/openwiki What it is OpenWiki is a CLI that writes and maintains documentation for your codebase, built specifically for AI coding agents. Use case If you’re working with coding agents (Claude Code, Copilot, etc.) that need context on a codebase, OpenWiki auto-generates a structured openwiki/ docs folder from your…