隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
RAGFlow addresses the challenge of building accurate, context-aware AI applications by providing a robust RAG pipeline that handles document chunking, retrieval, and generation with high fidelity. It simplifies the integration of RAG with agent workflows, reducing the complexity of building enterprise-grade AI systems from unstructured data.
部署现实
当前可用的安装信号是：docker pull infiniflow/ragflow:v0.26.4。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 Apache-2.0。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build enterprise-scale RAG applications such as document Q&A systems, knowledge assistants, and agent-based workflows that leverage custom data sources. The framework supports deep document understanding, flexible chunking, and pre-built agent templates, enabling the creation of production-ready AI systems with high accuracy and efficiency. The ceiling includes complex multi-step reasoning and integration with various LLMs and data sources.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
infiniflow/ragflow 被追踪为 Go 项目，主要属于 LLM Tool, AI Agent 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 88k Star，今日 +473，本周 +0，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 61 天，未关闭 Issue 为 1.8k，约占总 Star 的 2.02%。这只是采用信号，不替代工程尽调。
采用检查：10k Fork 和 88k Watcher 反映项目被复用和关注的程度。许可证信号：Apache-2.0。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 473。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 Apache-2.0，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
88k 星标
复用
10k 复刻
关注
88k 关注者
维护
moderate
许可证
Apache-2.0
未解决 Issue
1.8k
RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines RAG with agent capabilities to create a context layer for LLMs. It provides a streamlined RAG workflow for enterprises, enabling developers to transform complex data into production-ready AI systems with high fidelity and precision.
核心特性
- Deep document understanding for knowledge extraction from unstructured data with complicated formats. - Template-based chunking with intelligent and explainable options. - Grounded citations with reduced hallucinations, including visualization of text chunking and traceable citations.
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
docker pull infiniflow/ragflow:v0.26.480
健康评分
一般
提交活跃度
Dec 12, 2023
创建于
Aug 14, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
infiniflow
GitHub 主页obra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
RAGFlow addresses the challenge of building accurate, context-aware AI applications by providing a robust RAG pipeline that handles document chunking, retrieval, and generation with high fidelity. It simplifies the integration of RAG with agent workflows, reducing the complexity of building enterprise-grade AI systems from unstructured data.
能力范围
Developers can build enterprise-scale RAG applications such as document Q&A systems, knowledge assistants, and agent-based workflows that leverage custom data sources. The framework supports deep document understanding, flexible chunking, and pre-built agent templates, enabling the creation of production-ready AI systems with high accuracy and efficiency. The ceiling includes complex multi-step reasoning and integration with various LLMs and data sources.
结论
RAGFlow is ideal for developers and enterprises needing a robust, open-source RAG engine with agent capabilities to build accurate, data-driven AI applications. It is not suitable for those seeking a lightweight, minimal solution or lacking infrastructure for self-hosting. The key trade-off is between its powerful features and the operational complexity of deployment.