ragi

hedypamungkas/ragi

★ 0 stars Python AI/LLM Updated today

ragi — Retrieval that rises. Eval-first, agent-agnostic RAG toolkit: define, measure, iterate, ship as a portable retrieval contract (Python lib / MCP server) any agent consumes.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "ragi": {
      "command": "uvx",
      "args": [
        "ragi"
      ]
    }
  }
}

Or install with pip: pip install ragi

README Excerpt

> ***Retrieval that rises.*** — named for the **sourdough starter** (*ragi*, Indonesian): a > living culture you **cultivate**, **measure before you bake**, and **share**. Tend your RAG the > same way — feed it data, measure it honestly, then ship the tuned stack to any agent. **Eval-first, agent-agnostic RAG toolkit.** Define a retrieval stack, measure it on a

Topics

bm25eval-firstinformation-retrievalmcp-serverpythonragrag-evaluationretrieval-augmented-generation

ragi

Quick Install

README Excerpt

Topics

Related AI/LLM Servers