mcp-server

haiku.rag: AI Powered RAG

Get opinionated agentic RAG with haiku.rag.
567 stars35 forksPythonGuide quality 8/10Updated 8/7/2026100% free · open source
What it does

Haiku.rag provides an opinionated agentic RAG solution for founders, integrating Python and machine learning capabilities powered by LanceDB, Pydantic AI, and Docling.

When to use it
  • When building AI solutions that require Python and ML integration
  • For projects needing an opinionated agentic RAG with a Python interface
  • When a startup requires a solution that leverages LanceDB, Pydantic AI, and Docling
Ready-to-paste prompt
python haiku_rag.py --help
Heads up: Ensure that the Python environment meets the version requirements specified in the haiku.rag repository, as it may require a specific version of Python or additional dependencies
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/haiku-rag && curl -fsSL https://workflowstacks.com/api/skills/haiku-rag/claude-skill -o ~/.claude/skills/haiku-rag/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.

Quick Actions
Details
Creator
ggozad
Language
Python
Category
mcp-server
Published
10/13/2024

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