Awesome GitHub RepositoriesLLM-Based Analysis

Marker is an LLM-powered document parser and OCR pipeline designed to convert PDFs and unstructured files into structured markdown, JSON, and HTML. It functions as a data preprocessor that transforms complex documents into machine-readable formats while preserving tables, equations, and layout structures. The system utilizes large language models to refine OCR accuracy, clean mathematical notation, and merge fragmented tables across multiple pages. It employs model-based layout analysis to predict block types and bounding boxes, ensuring a more precise conversion of document elements. Capabi

PR Agent is an AI-powered code analysis tool and pull request reviewer that uses large language models to automate version control workflows. It functions as a programmatic agent that integrates with version control platforms to provide automated quality checks, explain code changes, and manage pull request documentation. The system distinguishes itself by enforcing organizational engineering standards through a customizable rule-based system. It leverages retrieval-augmented generation to inject repository context and organizational guidelines into its analysis, ensuring that feedback remain

SkillSpector 是一款安全扫描器，旨在在 AI 代理插件和扩展安装之前检测其中的漏洞和恶意模式。它作为一个运行时护栏，计算数值风险评分并分配严重性标签，以提供安装建议或阻止有风险的外部扩展。 该项目的独特之处在于使用语言模型执行语义代码分析，评估代码意图和上下文以减少误报。它还采用基于指纹的问题抑制技术，在重复扫描周期中跟踪并忽略已接受的风险。 该工具通过针对公共安全数据库的依赖项扫描来涵盖软件供应链安全，并支持从本地目录、远程 URL 和仓库进行多源资产摄取。它以多种机器可读和人类可读的格式提供漏洞报告，以便集成到 CI/CD 流水线中。

ai-goofish-monitor is an AI-driven marketplace monitor and containerized web scraper designed to track online listings. It uses multimodal large language models and natural language prompts to analyze product text and images, determining if items meet specific requirements. The system employs an anti-detection workflow that rotates network proxies and authenticated accounts to bypass rate limits. It captures browser cookies and session states to mimic real user behavior during automated requests. The project includes a task scheduler using cron expressions and an embedded SQLite database for

k8sgpt 是一套专注于 Kubernetes 的工具，旨在进行 AI 驱动的调试、集群诊断和自我修复。它作为一个自动化分析器和调试器，使用大语言模型来解释集群错误、建议修复步骤并识别资源故障。 该项目以其可扩展的分析框架脱颖而出，支持自定义诊断插件和模型上下文协议（MCP）服务器，后者将集群诊断作为 AI 助手的工具暴露出来。它包括一个能够自动生成并应用修复程序以解决检测到的异常的自我修复代理，以及在传输到外部 AI 提供商之前屏蔽敏感信息的数据匿名化中间件。 该工具集涵盖了广泛的操作能力，包括通过 Operator 进行持续健康监控、针对策略引擎的合规性审计，以及识别广泛故障模式的多集群编排。它还提供可观测性功能，如诊断结果导出、可观测性指标集成和 Pod 故障排查。