ai-agent

AWESOME-OCR-LLM: Text Extraction

Name: AWESOME-OCR-LLM: Text Extraction
Author: Yuliang-Liu

Extract text from images with AWESOME-OCR-LLM, a tool for startup founders, with 665 GitHub stars.

726 stars+5★ this week54 forksGuide quality 8/10 · reviewed Jul 8Updated 10/8/2026100% free · open source

What it does

AWESOME-OCR-LLM extracts text from images using the power of large language models, allowing startup founders to automate data extraction from visual documents.

When to use it

•When you need to extract text from invoices, receipts, or other financial documents
•When you want to automate data entry from business cards, contracts, or other formal documents
•When you need to extract information from images of whiteboard notes, handwritten notes, or other visual brainstorming sessions

Ready-to-paste prompt

python ocr.py --img_path ./images/example_image.jpg --lang en --output_path ./output/extracted_text.txt

Heads up: Make sure you have the necessary Python version (>=3.8) and the required libraries installed, including PyTorch and transformers, to avoid compatibility issues

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/awesome-ocr-llm && curl -fsSL https://workflowstacks.com/api/skills/awesome-ocr-llm/claude-skill -o ~/.claude/skills/awesome-ocr-llm/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How AWESOME-OCR-LLM: Text Extraction works

Codeflow

Free to inspect

AWESOME-OCR-LLM: Text Extraction is a documents-only repository (7 doc files) — something you read, not something you run. There is nothing to install. Last commit this month, MIT license.

Size

Documents only

7 documents · ~3 h to skim

Setup

Nothing to install

A guide / curated list. Just read it and follow the links.

Runs on

Nowhere — you read it

A reading resource, not a program.

Where to start reading

1
README.md
Start here — what it does and how to install it

What's in each folder

figs/Folder33 files

full-lists/Folder5 files

READMEDocumentedMIT licenseUpdated this month