ai-agent

RAGFlow: Smarter LLM Context

Get a superior context layer for LLMs with RAGFlow, a retrieval-augmented generation engine, ideal for founders in AI.
advanced1-2 hours💵 Free (self-hosted)
90,435 stars10,684 forksGoGuide quality 9/10Updated 9/10/2026100% free · open source
What it is

Create a superior context layer for LLMs with RAGFlow, a tool that helps machines understand and generate human-like text.

Real use case example

"A founder building a conversational AI platform can use RAGFlow to improve the accuracy of their chatbot's responses, first they would integrate RAGFlow with their LLM, then they would fine-tune the model with their specific dataset, finally they would deploy the chatbot and see improved engagement from users."

When to use it
  • You need to improve the context understanding of your LLM application
  • You want to integrate Retrieval-Augmented Generation with agent capabilities
  • You're looking for an open-source AI infrastructure to power your LLM context management
Ready-to-paste prompt
python -m ragflow --query 'What are the latest developments in AI research?' --index 'my_index' --agent 'my_agent'
Heads up: Make sure you have the required Python version (3.8 or later) and the necessary dependencies installed, as specified in the RAGFlow README, before attempting to install or run RAGFlow
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/ragflow && curl -fsSL https://workflowstacks.com/api/skills/ragflow/claude-skill -o ~/.claude/skills/ragflow/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How RAGFlow: Smarter LLM Context works
Codeflow
Free to inspect

RAGFlow: Smarter LLM Context is a very large Go project (~1M lines across 4077 code files, plus 498 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~1M lines · 4077 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Go · Python · Docker
No API keys detected
Go 46%Python 31%TypeScript 18%C++ 4%
What happens, step by step

AI tool processes data

You give
user data
1Read Input
Reads user data
2Process Data
Processes data with RAG
internal/cli/cli.go
3Generate Output
Generates results
You get
processed results
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/.gitkeep
    Where the program starts running
  4. 4
    go.mod
    Dependencies and the commands it exposes
  5. 5
    internal/cli/cli.go
    Inside internal/ — the main logic begins here
What's in each folder
internal/Core code — the actual logic2158 files
agent/Prompts, skills & agent definitions150 files
web/Frontend / UI1748 files
api/Backend / API160 files
cmd/Command-line entry points2 files
bin/Command-line entry points1 files
docs/Documentation143 files
example/Examples you can copy11 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
infiniflow
Language
Go
Category
ai-agent
Published
12/12/2023

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.