Developer Tools●●Solid
CPU-only fast OCR for screenshots, images, PDFs, webpages
CPU-only VLM OCR beats Tesseract accuracy without sending data to the cloud.
Solve My ProblemCozy
mrkn1
9813d ago
Back to browse
GitHub Repository
Snap any image, screenshot, or webpage into plaintext. No GPU. No cloud. One command.
100 starsPython
CPU-only OCR for screenshots, images, and webpages
by mrkn1·May 24, 2026·4 points·9 comments
AI Analysis
●●SolidSolve My ProblemCozy
CPU-only VLM OCR beats Tesseract on layout without needing CUDA or cloud APIs.
Strengths
- •Quantized ONNX model runs on CPU without CUDA dependencies or cloud API keys.
- •Extracts main content image from webpages automatically via readability parsing.
- •Single Python module with self-installing dependencies makes deployment trivial for automation.
Weaknesses
- •Webpage OCR only targets the main image, ignoring full-page text extraction.
- •Zero stars and one commit suggests early stage with unproven maintenance.
Category
Target Audience
Developers needing offline OCR, privacy-focused users, automation scripters
Similar To
EasyOCR · Tesseract · Umi-OCR
Similar Projects
Productivity●●Solid
Local CPU OCR for images, PDFs, webpages
CPU-only OCR with clipboard in/out beats Tesseract for modern screenshots.
Ship ItSolve My Problem
mrkn1
3015d ago
AI/ML●●Solid
Local-first fast CPU image to text for screenshots, PDFs, webpages
CPU-only OCR with clipboard round-trip when cloud APIs dominate the space.
CozySolve My Problem
mrkn1
19178d ago
AI/ML●●Solid
Open-source alternative to Codex Chronicle, using Apple's local OCR
Privacy-first screen capture for agents when Rewind and ScreenPipe already exist.
Big BrainNiche Gem
talsraviv
2016d ago
Developer Tools●Mid
Klovr – Convert any webpage to Markdown (Cloudflare covers only 5%)
Nice, focused product: site-specific extraction rules (CSS selectors/metadata overrides), edge-first delivery (<500ms p99) and SDKs for Node/Python make it quick to drop into an LLM pipeline and claim 40–60% token savings. That said, HTML→Markdown is a crowded niche (Pandoc, Jina, Firecrawl and dozens of scrapers already exist), so Klovr needs clearer differentiation — e.g. demonstrable extraction accuracy, enterprise-grade rule sharing, or unique model-aware trimming — to move beyond 'handy utility'.
Solve My ProblemSlick
vaibhavlodha98
213mo ago
Developer Tools●Mid
DocOCR – Convert document images to Markdown locally on macOS
Local Markdown OCR via CLI and HTTP, though macOS Live Text overlaps heavily.
Solve My ProblemCozy
riddleling
4014d ago