RepoTrending RepoTrending
Weekly digest
#558 trending today Python Apache-2.0 Created May 2020

PaddlePaddle / PaddleOCR

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Open on GitHub
Stars
91.6k
91,578 total
Today
+40
#558 today
This week
–
Data collecting since Oct 23
This month
–
Data collecting since Oct 23

Stars since we started watching

Total stars per day

91.5k 91.5k 91.5k 91.6k 91.6k 91.6k Oct 23Oct 24 Best day: +40 91.5k 91.5k 91.5k 91.6k 91.6k 91.6k Oct 23Oct 24 Best: +40

Related repos

opendatalab / MinerU+61

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Python
opendataloader-project / opendataloader-pdf+39

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Java
xerj-org / xerj+1,061

Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

Rust
Graphify-Labs / graphify+869

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

Python