Developer Tools●●Solid
Ocrbase.dev – pdf→.md/.json OCR for developers
94.5% accuracy, self-hostable, open source—beats Textract on cost and accuracy.
Solve My ProblemNiche GemSlick
adammajcher
323mo ago
Back to browse
GitHub Repository
📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable.
21 starsTypeScript
ocrbase – PDF/IMG –>.MD/JSON Model-Agnostic OCR API
by adammajcher·Apr 16, 2026·1 point·0 comments
AI Analysis
●MidShip It
Yet another OCR API wrapper when JinaAI and Firecrawl already exist.
Strengths
- •Model-agnostic design lets you swap PaddleOCR and GLM-OCR via env vars.
- •Optional S3 staging and BullMQ queue for async processing at scale.
Weaknesses
- •Models must be self-hosted separately—ocrbase is just a thin routing layer.
- •Document parsing APIs already solved by established players with better docs.
Category
Target Audience
Developers building document parsing pipelines
Similar To
JinaAI Reader · Firecrawl · LlamaParse
Similar Projects
Security●●Solid
HideMyData – macOS PII Removal with Local AI and OCR
Local MLX model redacts PII without sending documents to the cloud.
Solve My ProblemCozy
maciejonos
2028d ago
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
983d ago
Data●●Solid
Irpapers – Visual embeddings vs. OCR trade-offs in scientific PDFs
Empirical OCR vs. image embeddings shootout for scientific PDFs reveals complementary bottlenecks.
Big BrainRabbit Hole
pvpv
503mo ago
Developer Tools●Mid
Budibase Agents Beta – model-agnostic AI agents for internal workflows
Feature launch from established 27.5K-star platform, not a standalone project.
Ship It
mjashanks
712mo ago
Productivity●●Solid
Built a model-agnostic, desktop-native, research studio for local files
Human-in-the-loop citation verification for local research files.
Niche GemSolve My Problem
ieuanking
301mo ago