Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
47,133 repositories indexed
1–24 of 275 · Most stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
A block-style editor with clean JSON output
State machines, statecharts, and actors for complex logic
The Single Sign-On Multi-Factor portal for web apps. OpenID Certified™ and Post-Quantum Cryptography Ready.
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Desktop app to manage markdown knowledge bases
Translated🚁🚀 2026 Airport Recommendations | Panda VPN (PandaVPNPro) has been confirmed to have run off with users' money! Quick Connect VPN (快连VPN) and Xiaoniu Accelerator (小牛加速器, Xiaoniu VPN) offer a poor experience and are expensive. Low-price airports, cheap airports, affordable airports, cost-effective airports, high-speed airports, stable airports, one-yuan airports, circumvention airports, paid airports, fee-charging airports, niche airports, high-quality airports, budget airports. Airport reviews, circumventing China's firewall, scientific internet access, ladders. Not permanently free ladders, official website, not permanently free VPN, not free airports! VPN China. Pay-as-you-go airports, pay-by-usage airports, no time limit airports. Airport node subscriptions, node sharing, Clash nodes, V2ray nodes, non-free nodes. Works with proxy software such as ClashForWindows, V2rayN, singbox, nekobox, and Shadowrocket (小火箭) 🚀🚁
⚡A CLI tool for code structural search, lint and rewriting. Written in Rust
Standalone man-in-the-middle attack framework used for phishing login credentials along with session cookies, allowing for the bypass of 2-factor authentication
A framework for managing and maintaining multi-language pre-commit hooks.
YouTube Music client for Android
Headless cloud-native authentication and identity management written in Go. Scales to a billion+ users. Replace Homegrown, Auth0, Okta, Firebase with better UX and DX. Passkeys, Social Sign In, OIDC, Magic Link, Multi-Factor Auth, SMS, SAML, TOTP, and more. Runs everywhere, runs best on Ory Network.
A platform to build and run apps that are elastic, agile, and resilient. SDK, libraries, and hosted environments.
Full-featured and highly configurable SFTP, HTTP/S, FTP/S and WebDAV server - S3, Google Cloud Storage, Azure Blob
🚀 gnet is a high-performance, lightweight, non-blocking, event-driven networking framework written in pure Go.
Cloud Native application framework for .NET
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Instant Upgrades and Automated Refactoring of any PHP 5.3+ code
Integrated set of Django applications addressing authentication, registration, account management as well as 3rd party (social) account authentication. 🔁 Mirror of https://codeberg.org/allauth/django-allauth/
The awesome document factory
The automatic type-safe REST library for .NET. Refit turns a REST API into a C# interface and generates the HttpClient implementation, with support for HttpClientFactory, pluggable serializers and a testing package.