MCP Server · RDF/SPARQL · Open Source

Your codebase as a
knowledge graph

Most MCP servers give AI tools.
OpenTology gives AI understanding — persistent memory, dependency awareness, and impact analysis across every session.

GitHub npm
$ npm install -g opentology click to copy
Scroll to explore
OpenTology scanning itself — 67 modules, 234 call relations

Stats

-
Modules
-
Symbols
-
Calls
-
Sessions

Legend

  • Commands
  • Libraries
  • MCP Server
  • Classes / Interfaces
  • Call Relations
  • Templates / Tests

Node Detail

Click a node to inspect

Sessions

Why OpenTology?

Not just tools — a fundamentally different way for AI to understand your project.

🧠

Persistent Memory

Decisions, issues, and knowledge persist across sessions in an RDF graph. Your AI remembers what it learned yesterday.

💥

Impact Analysis

Before editing, AI checks the dependency graph to understand blast radius. No more accidental breakage of dependent modules.

🔍

6 Language Support

Symbol-level scanning for TypeScript, Python, Go, Rust, Java, and Swift. Classes, functions, methods, and call graphs.

Zero Docker

Oxigraph runs as WebAssembly. No containers, no native builds. Works everywhere Node.js runs.

🤖

Behavioral Instructions

Automatically injects CLAUDE.md so AI checks impact, searches context, and records decisions without being asked.

🌐

Standard-Based

Built on RDF, SPARQL, RDFS reasoning, and SHACL validation. Query your graph with any SPARQL-compatible tool.

See the difference

Real experiment on this codebase. Watch both approaches run.

"What breaks if I change store-adapter.ts?"

grep / ripgrep
OpenTology
6x
fewer tool calls
6 calls → 1 call
6x
less token usage
~2.1k → ~350
+29%
more results found
7 files → 9 dependents

Get Started in 30 Seconds

Three commands. That's it.

1

Add to MCP config

Point your AI assistant to OpenTology.

"command": "npx",
"args": ["-y", "opentology", "mcp"]
2

Initialize

Creates graph, hooks, and AI instructions.

opentology context init
3

Scan codebase

Builds the knowledge graph from your code.

opentology context scan