StackMap
Subscribe
Explore / open-ontologies
fabio-rovai

open-ontologies

Rust MCP server + desktop Studio for AI-native ontology engineering: 70+ tools over an in-memory Oxigraph store — OWL2-DL tableaux reasoning, SHACL, SPARQL, versioning. Single binary, no JVM.

315 39 Rust MITupdated 2 days ago
knowledge-graphs
View on GitHubDispute this mapping →
Curator's take

Protégé for the agent era, with the right division of labor: the server validates, reasons and scaffolds; the LLM connected over MCP does the intelligence — no internal API keys. A DL tableaux reasoner in a single binary is legitimately rare. When NOT: ★315 with an enormous surface (70+ tools, Studio, planner, causal layer) on one maintainer's velocity — expect edges to move; if you only need graph retrieval, this is over-engineering.

Mapped by ShipWithAI editors · links verified
README.md

Open Ontologies

Open Ontologies

A Terraforming MCP for Knowledge Graphs
Validate, classify, and govern AI-generated ontologies. Written in Rust. Ships as a single binary.

CI MIT Open MCP PitchHut ClawHub

Quick Start · Studio · Benchmarks · IES · Tools · Architecture · Docs

Open Ontologies is a Rust MCP server and desktop Studio for AI-native ontology engineering. It exposes 70+ tools that let Claude build, validate, query, diff, lint, version, reason over, align, plan, certify, and govern RDF/OWL ontologies using an in-memory Oxigraph triple store — with a full three-layer Dynamics → Causal → Planner architecture, a marketplace of 33 standard ontologies, clinical crosswalks, semantic embeddings, and a full lineage audit trail.

The Studio wraps the engine in a visual desktop environment: virtualized ontology tree with hierarchy lines, breadcrumb navigation, and connection explorer; AI chat panel with /build (IES-level deep) and /sketch (quick prototype) commands; Protégé-style property inspector; and lineage viewer.

No JVM. No Protégé.

What's New (three-layer architecture + 13 new primitives)

The full Dynamics → Causal → Planner stack plus 13 new primitives. Every piece holds the MCP-native convention: the server provides validation and scaffolding, the connected LLM (Claude over MCP) does the intelligence. No internal LLM clients, no API keys, no provider abstractions.

Three-layer architecture

Layer What it ships
Dynamics ActionSchema + 4 MCP tools: onto_action_register / _applicable / _apply / _list. Concurrent atomic ticks, static causal laws (invariants), default-value laws, ramification via OWL-RL closure, non-deterministic outcomes with reproducible seed.
Causal onto_certify_action with optional PyWhy backdoor identification (opt-in via causal-pywhy feature). Structural-proxy default + do-calculus opt-in + graceful fallback.
Planner onto_plan_compile_pddl + onto_plan_classical (Fast Downward subprocess) + onto_plan_validate (sandbox-simulate). Solver stays client-side; server compiles + validates.

13 new primitives

  • onto_owl_shacl_coevolve_check + onto_owl_shacl_coevolve_incremental — SHACL validation against the OWL-RL closure, with dependency-graph routing so only shapes touching changed IRIs revalidate.
  • onto_segment_retrieve — TBox-slice retrieval for ontology-grounded RAG.
  • onto_extract_scaffold + onto_extract_validate — schema-guided structured extraction with typed datatype validation + conformance scoring.
  • onto_cq_run + onto_verify_cq + onto_cq_verdicts_list — co

Continue your stack

What teams reach for next — and why each earns a place beside open-ontologies. Ranked by curator confidence.