ontologylab

dltdnfrk/ontologylab

★ 0 stars Python AI/LLM Updated today

Local-first knowledge-graph pipeline: collect -> extract (LLM) -> verify (human) -> knowledge pack -> local MCP server

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

Or install with pip: pip install ontologylab

README Excerpt

Local-first, single-user **knowledge-graph pipeline**: ``` collect → extract (LLM) → verify (human) → knowledge pack → local MCP server ``` **The AI proposes; a human decides; only verified facts ship.** Every extracted node/edge is born `proposed` and becomes `verified` only through an explicit human approval. Packs are immutable, verified-only snapshots, and the

ontologylab

Quick Install

README Excerpt

Related AI/LLM Servers