Awesome GitHub RepositoriesIntelligent Document Processing

Marker is a comprehensive document processing platform designed to automate the conversion, extraction, and structuring of data from complex files. It functions as an orchestration engine that chains modular processing steps into versioned, reusable pipelines, allowing organizations to standardize document handling and automate repetitive business tasks at scale. The platform distinguishes itself through its support for secure, private infrastructure deployment, enabling users to run containerized services within their own environments to maintain strict data privacy. It features specialized

This project is a comprehensive framework and toolkit for developing, optimizing, and deploying transformer-based models across multimodal, document intelligence, and natural language processing tasks. It provides a unified neural architecture that processes text, vision, audio, and document layout data through a shared set of weights, enabling researchers and developers to build foundational models that align cross-modal representations. The platform distinguishes itself through advanced training and inference strategies designed for large-scale deep learning. It incorporates specialized mec

h2oGPT is a self-hosted platform designed for running large language models and executing retrieval-augmented generation workflows locally. It provides a comprehensive web interface that allows users to index private document collections into searchable databases, enabling context-aware question answering and summarization without exposing sensitive data to external services. The platform distinguishes itself by offering a modular architecture that supports both local model execution and connections to external inference servers. It facilitates the development of autonomous agents capable of

Sparrow 是一个 LLM 文档提取平台和基于视觉的推理引擎，旨在将图像和 PDF 转换为经过验证的结构化数据。它作为代理工作流编排器，将分类、提取和验证任务串联成多步流水线。 该系统的特色在于其后端无关的推理层，可管理本地 GPU、Apple Silicon 和云服务商上的模型。它利用基于坐标的视觉定位将提取的文本映射到精确的边界框坐标，并使用基于提示的模型引导来引导注意力并规范化数据格式。 该平台涵盖了文档智能工作流，包括用于保持结构完整性的专业图像表格处理，以及用于验证提取字段正确性的模式驱动验证。它还提供了一个用于监控 API 性能、使用分析和系统健康状况的文档分析仪表板。 架构包含一个基于插件的扩展系统，用于集成索引和编排中使用的第三方库。

Zeebe 是一个云原生工作流引擎和分布式状态机，旨在通过 BPMN 和 DMN 标准进行业务流程编排。它作为一个高性能 gRPC 工作流运行时，通过分区事件流架构执行复杂的业务流程。该系统还作为大语言模型代理的编排器，在确定性业务流程中协调 AI 推理和工具使用。 该引擎通过其点对点代理网络和确保高可用性和容错性的基于共识的数据复制模型而脱颖而出。它采用分区代理集群来实现水平扩展，并利用自适应请求背压来调节传入的命令流并防止系统过载。 该平台涵盖了广泛的操作功能，包括带有性能热力图的实时执行监控、通过决策表的自动化业务决策，以及通过基于轮询的作业工作者模型进行的分布式任务执行。它还提供用于多租户资源隔离、基于身份的访问控制以及集成外部 Web API 和无服务器函数的工具。 该系统可部署在 Kubernetes 和 Docker 等各种环境中，并通过命令行界面和程序化 REST API 的组合进行管理。

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

PromptX is an LLM agent orchestration framework designed to execute multi-step workflows using autonomous agents. It features a sandboxed tool execution environment for secure filesystem operations and external API integrations, alongside a persona management system that defines professional roles and domain expertise to control agent behavior. The system implements a semantic memory network for persistent knowledge storage, utilizing graph-based memory and engrams to retain information across sessions. This cognitive memory includes specialized tools for knowledge graph visualization, allowi