autokg

kaushikthakur97/autokg

★ 0 stars Python Data/Analytics Updated 5d ago

autokg — One Build. Infinite Questions. Transform silver-layer tables into a governed RDF knowledge graph with MCP server support. Any AI agent queries it naturally. Relationships live in the data, not SQL.

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": {
    "autokg": {
      "command": "uvx",
      "args": [
        "autokg"
      ]
    }
  }
}

Or install with pip: pip install autokg

README Excerpt

**Turn warehouse/lakehouse tables into a governed knowledge graph for AI agents.** `autokg` builds an explicit entity-relationship graph from Parquet, Delta, CSV, SQL, dbt-style config, or DataFrames, then exposes it through **MCP**, SPARQL, JSON-LD, and Python APIs. Agents can answer multi-table business questions without hard-coded SQL joins or giant schema prompts — with lineage, PII masking, and audit trails built in.

Tools (2)

customersorders

📊

Working with market or time-series data?

The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.

View dataset →

autokg

Quick Install

README Excerpt

Tools (2)

Related Data/Analytics Servers