Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。

glm 5.2 free z.ai zhipu ai large language model llm mixture of experts moe 744b parameters indexshare deepseek sparse attention dsa 1m context window open weights mit license hugging face zenmux api cloudflare workers ai opencode connection free tier quota open source github repository download weights local llm inference vllm sglang

GLM-OCRを使ったローカルOCRサーバー（FastAPI + Web UI / 画像・PDF対応）

Simple optical character recognition based on GLM-OCR with fewer dependencies.

Swift/MLX port of zai-org/GLM-OCR

Pure Rust OCR inference engine powered by GLM-OCR vision-language model. No Python. No PyTorch. Just cargo build and go.

Fast and lightweight GLM-OCR inference on Modal with an OpenAI-compatible endpoint for OCR.

Local OCR for Images & PDFs

ComfyUI custom node to run GLM-OCR locally — text, formula, and table recognition from images

GLM-OCR model run locally at auto cpu gpu

Demonstration for the zai-org/GLM-OCR multimodal OCR model. Supports text, formula, and table recognition from uploaded images, with outputs in plain text and markdown formats.

A local macOS AI-based OCR utility for converting PDFs and images into Markdown with glm-ocr running through Ollama.

Extract hardcoded (burned-in) subtitles from videos with high precision using GLM-OCR and Ollama

Upload a PDF or image, get an Anki deck. Locally, on your own system.

captcha solver for antibotlinks challenges

Trasforma PDF sporchi, scansioni e immagini in Markdown pulito e strutturato, usando il modello GLM-OCR in esecuzione tramite Ollama tutto sul tuo host locale.

GLM-OCR Web

Local-first PDF/Markdown/HTML toolkit with streaming OCR (GLM-OCR via Ollama) and document anonymization (OpenAI Privacy Filter). Chain 19 tools into pipelines. Files never leave your machine.