Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
UltraRAG
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
5.6kstars
427forks
Python
deepseekdemoeasyembeddingflaskgpthuggingface-transformersllmmcpmultimodalopenaiqwen
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Low-code framework for building and orchestrating complex RAG pipelines using MCP servers and YAML configs.
Use this when
- Need to chain retrieval and generation steps with loops or conditions
- Want to prototype RAG ideas quickly without writing boilerplate
- Evaluating RAG pipelines against standard benchmarks
- Integrating custom retrievers or generators into a workflow
- Debugging RAG logic via a visual pipeline builder
Don't use when
- Building a simple single-step Q&A system
- Need a turnkey chatbot without custom logic
- Working with non-MCP compatible tools
Capabilities
- Orchestrate RAG workflows with YAML (loops, branches, sequences)
- Modular MCP servers for retrievers, generators, and tools
- Built-in evaluation pipelines with standardized benchmarks
- Visual IDE for drag-and-drop pipeline construction
- One-click conversion of pipelines to interactive web UIs
- Real-time sync between canvas and code for live adjustments
InstallMCPRun via uvx (Python)
Universal installANY TOOL
$ npx skillcity@latest OpenBMB/UltraRAGAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
uvx ultrarag
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"ultrarag": {
"command": "uvx",
"args": [
"ultrarag"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
ultrarag — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt