Stars
🔥 [ICLR 2025] FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
answer card, 答题卡检测、试题切分、学生考号识别、选择题自动批改
Python A2A is a powerful, easy-to-use library for implementing Google's [Agent-to-Agent (A2A) protocol](https://google.github.io/A2A/). It enables seamless communication between AI agents, creating…
FlowGram is a node-based flow building engine that helps developers quickly create workflows in either fixed layout or free connection layout modes
Resolves severe noise in the widely spread CASIA2.0 dataset ground-truth for Image Manipulation Detection
Unofficial implementation of ManTra-Net (CVPR 2019) with Pytorch including training code. The original paper is a model implemented by keras-Tensorflow
Implementation of the famous Camera Noise Fingerprint "NoisePrint" in Pytorch
推荐使用最新的大模型，合同审查/判决书摘要 提示词
欢迎来到“筱可AI研习社”的实战项目仓库！这个仓库主要用于存储和展示为公众号撰写的各类实战项目。我们会不断优化和迭代这些项目，以探索AI的无限可能。
PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
An open protocol enabling communication and interoperability between opaque agentic applications.
8000 n8n-io / n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS…
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
No fortress, purely open ground. OpenManus is Coming.
The official Python library for the OpenAI API
Build your personal knowledge base with Trilium Notes
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Making large AI models cheaper, faster and more accessible
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!