GitHub repo leaderboard by stars, growth rate and activity.

• neo4j-labs

  #1neo4j-labs/llm-graph-builder

  Neo4j graph construction from unstructured data using LLMs

  Jupyter Notebook5,239 starslast pushed 3 days ago
• ucbepic

  #2ucbepic/docetl

  A system for agentic LLM-powered data processing and ETL

  Python4,083 starslast pushed 5 days ago
• milvus-io

  #3milvus-io/bootcamp

  Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

  Jupyter Notebook2,445 starslast pushed 3 days ago
• instill-ai

  #4instill-ai/instill-core

  🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications

  Python2,319 starslast pushed 3 months ago
• NanoNets

  #5NanoNets/docext

  An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

  Python2,083 starslast pushed 6 months ago
• yobix-ai

  #6yobix-ai/extractous

  Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.

  Rust1,773 starslast pushed 2 years ago
• tstanislawek

  #7tstanislawek/awesome-document-understanding

  A curated list of resources for Document Understanding (DU) topic

  —1,538 starslast pushed 3 years ago
• graphlit

  #8graphlit/graphlit-mcp-server

  Model Context Protocol (MCP) Server for Graphlit Platform

  TypeScript379 starslast pushed 8 months ago

#	Repo	Language	Stars	30-day trend	Last updated
1	neo4j-labs neo4j-labs/llm-graph-builder Neo4j graph construction from unstructured data using LLMs	Jupyter Notebook	5,239		last pushed 3 days ago
2	ucbepic ucbepic/docetl A system for agentic LLM-powered data processing and ETL	Python	4,083		last pushed 5 days ago
3	milvus-io milvus-io/bootcamp Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.	Jupyter Notebook	2,445		last pushed 3 days ago
4	instill-ai instill-ai/instill-core 🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications	Python	2,319		last pushed 3 months ago
5	NanoNets NanoNets/docext An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)	Python	2,083		last pushed 6 months ago
6	yobix-ai yobix-ai/extractous Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.	Rust	1,773		last pushed 2 years ago
7	tstanislawek tstanislawek/awesome-document-understanding A curated list of resources for Document Understanding (DU) topic	—	1,538		last pushed 3 years ago
8	graphlit graphlit/graphlit-mcp-server Model Context Protocol (MCP) Server for Graphlit Platform	TypeScript	379		last pushed 8 months ago

All · 11,658