Versatile-OCR-Program – An open-source multimodal OCR tool for accurately extracting complex structured data.
What is Versatile-OCR-Program? Versatile-OCR-Program is an open-source multimodal OCR tool that supp...
Sorting
MoLing – Local AI Office Automation Assistant, based on MCP server
What is MoLing? MoLing is a dependency-free local office automation assistant and an MCP server desi...
AutoRAG – A fully managed retrieval-augmented generation service launched by Cloudflare
What is AutoRAG? AutoRAG is a fully managed Retrieval-Augmented Generation (RAG) pipeline launched b...
DevDocs – An open-source tool for crawling and processing technical documentation
What is DevDocs? DevDocs is an open-source technical documentation crawling and processing tool desi...
Gemini 2.5 Flash – The latest AI inference model launched by Google
What is Gemini 2.5 Flash? Gemini 2.5 Flash is the latest high-efficiency, low-latency AI model intro...
Multi-SWE-bench – ByteDance’s open-source multi-language code repair benchmark
What is Multi-SWE-bench? Multi-SWE-bench is the first multi-language code repair benchmark open-sour...
LocAgent – An intelligent code issue localization agent jointly launched by Stanford University, Yale University, and other institutions
What is LocAgent? LocAgent is a framework jointly launched by institutions such as Stanford Universi...
A2A – Google’s First Open-Source Standard Agent Interaction Protocol
What is A2A? A2A (Agent2Agent Protocol) is the first standardized agent interaction protocol open-so...
Firebase Studio – Google’s cloud-based full-stack AI application development environment
What is Firebase Studio? Firebase Studio is a cloud-based, full-stack application development enviro...
OmniSVG – StepFun Collaborates with Fudan University to Launch an End-to-End Multimodal Vector Graphics Generation Model
What is OmniSVG? OmniSVG is the world's first end-to-end multimodal SVG (Scalable Vector Graphics) g...