Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Image to Text OCR
MCP serversExtract text from images, photos and screenshots with OCR in 100+ languages, with line positions.
-
Image to Text OCR
MCP serversExtract text from PNG, JPEG, TIFF, WebP, BMP and GIF images with OCR in 27 languages.
-
Inkscry: Image to Text OCR
MCP serversInkscry: OCR for screenshots, scans and photos in 100+ languages; text, confidence, line boxes.
-
MINT-1T-HTML
Datasets & benchmarksHugging Face dataset by mlfoundations
mlfoundations/MINT-1T-HTML -
Image to Text OCR
MCP serversOCR text from image URLs, 30 languages, lines with boxes. One flat row per image. Billed on text.
-
Extract text from images with OCR: plain text plus every line or word with its box
-
Llama-Nemotron-VLM-Dataset-v1
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Llama-Nemotron-VLM-Dataset-v1 -
mirage
Modelsimage text to text model by Cactus-Compute · cactus-compute
Cactus-Compute/mirage -
Recap-DataComp-1B
Datasets & benchmarksHugging Face dataset by UCSC-VLAA
UCSC-VLAA/Recap-DataComp-1B -
pixelprose
Datasets & benchmarksHugging Face dataset by tomg-group-umd
tomg-group-umd/pixelprose -
xperience-10m
Datasets & benchmarksHugging Face dataset by ropedia-ai
ropedia-ai/xperience-10m -
open-schematics
Datasets & benchmarksHugging Face dataset by bshada
bshada/open-schematics -
CT-RATE
Datasets & benchmarksHugging Face dataset by ibrahimhamamci
ibrahimhamamci/CT-RATE -
modlens
SkillsThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
git clone https://github.com/liustack/modlens.git -
Vaani
Datasets & benchmarksHugging Face dataset by ARTPARK-IISc
ARTPARK-IISc/Vaani -
coyo-700m
Datasets & benchmarksHugging Face dataset by kakaobrain
kakaobrain/coyo-700m -
nemotron-3.5-120b-cq
Modelsimage text to text model by Cactus-Compute · mlx
Cactus-Compute/nemotron-3.5-120b-cq -
synthetic-dataset-1m-dalle3-high-quality-captions
Datasets & benchmarksHugging Face dataset by ProGamerGov
ProGamerGov/synthetic-dataset-1m-dalle3-high-quality-captions -
MathVision
Datasets & benchmarksHugging Face dataset by MathLLMs
MathLLMs/MathVision -
GRIT
Datasets & benchmarksHugging Face dataset by zzliang
zzliang/GRIT -
Hirak OCR
Public APIsImage to text -text recognition- from image more than 100 language, accurate, unlimited requests
-
doc-convert-mcp
MCP serversDocument conversion and OCR for AI agents: PDF, Office docs, images to text.
-
OCR scanned PDFs and images to text, one row per page, 9 languages. Runs on Apify.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.