[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:open-ontologies":3},"\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Ffabio-rovai\u002Fopen-ontologies\u002FHEAD\u002Fdocs\u002Fassets\u002Flogo.png\" alt=\"Open Ontologies\" width=\"300\" \u002F>\n\u003C\u002Fp>\u003Ch1>Open Ontologies\u003C\u002Fh1>\u003Cp align=\"center\">\n  \u003Cstrong>A Terraforming MCP for Knowledge Graphs\u003C\u002Fstrong>\u003Cbr \u002F>\n  Validate, classify, and govern AI-generated ontologies. Written in Rust. Ships as a single binary.\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffabio-rovai\u002Fopen-ontologies\u002Factions\u002Fworkflows\u002Fci.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Ffabio-rovai\u002Fopen-ontologies\u002Fci.yml?branch=main&style=for-the-badge\" alt=\"CI\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffabio-rovai\u002Fopen-ontologies\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg?style=for-the-badge\" alt=\"MIT\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fopenmcp.org\u002Fservers\u002Fopen-ontologies\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOpen_MCP-open--ontologies-blue?style=for-the-badge\" alt=\"Open MCP\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.pitchhut.com\u002Fproject\u002Fopen-ontologies-mcp\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPitchHut-open--ontologies-orange?style=for-the-badge\" alt=\"PitchHut\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fclawhub.ai\u002Ffabio-rovai\u002Fopen-ontologies\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClawHub-open--ontologies-7c3aed?style=for-the-badge\" alt=\"ClawHub\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"#quick-start-mcp--cli\" rel=\"nofollow ugc noopener\">Quick Start\u003C\u002Fa> ·\n  \u003Ca href=\"#studio-desktop-app\" rel=\"nofollow ugc noopener\">Studio\u003C\u002Fa> ·\n  \u003Ca href=\"#benchmarks\" rel=\"nofollow ugc noopener\">Benchmarks\u003C\u002Fa> ·\n  \u003Ca href=\"#ies-support\" rel=\"nofollow ugc noopener\">IES\u003C\u002Fa> ·\n  \u003Ca href=\"#tools\" rel=\"nofollow ugc noopener\">Tools\u003C\u002Fa> ·\n  \u003Ca href=\"#architecture\" rel=\"nofollow ugc noopener\">Architecture\u003C\u002Fa> ·\n  \u003Ca href=\"#documentation\" rel=\"nofollow ugc noopener\">Docs\u003C\u002Fa>\n\u003C\u002Fp>\u003Chr \u002F>\n\u003Cp>Open Ontologies is a \u003Cstrong>Rust MCP server\u003C\u002Fstrong> and \u003Cstrong>desktop Studio\u003C\u002Fstrong> for AI-native ontology engineering. It exposes \u003Cstrong>70+ tools\u003C\u002Fstrong> that let Claude build, validate, query, diff, lint, version, reason over, align, plan, certify, and govern RDF\u002FOWL 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.\u003C\u002Fp>\n\u003Cp>The \u003Cstrong>Studio\u003C\u002Fstrong> wraps the engine in a visual desktop environment: virtualized ontology tree with hierarchy lines, breadcrumb navigation, and connection explorer; AI chat panel with \u003Ccode>\u002Fbuild\u003C\u002Fcode> (IES-level deep) and \u003Ccode>\u002Fsketch\u003C\u002Fcode> (quick prototype) commands; Protégé-style property inspector; and lineage viewer.\u003C\u002Fp>\n\u003Cp>No JVM. No Protégé.\u003C\u002Fp>\n\u003Chr \u002F>\n\u003Ch2>What's New (three-layer architecture + 13 new primitives)\u003C\u002Fh2>\n\u003Cp>The full \u003Cstrong>Dynamics → Causal → Planner\u003C\u002Fstrong> stack plus 13 new primitives. Every piece holds the \u003Cstrong>MCP-native\u003C\u002Fstrong> 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.\u003C\u002Fp>\n\u003Ch3>Three-layer architecture\u003C\u002Fh3>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Layer\u003C\u002Fth>\n\u003Cth>What it ships\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>\u003Cstrong>Dynamics\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\u003Ccode>ActionSchema\u003C\u002Fcode> + 4 MCP tools: \u003Ccode>onto_action_register\u003C\u002Fcode> \u002F \u003Ccode>_applicable\u003C\u002Fcode> \u002F \u003Ccode>_apply\u003C\u002Fcode> \u002F \u003Ccode>_list\u003C\u002Fcode>. Concurrent atomic ticks, static causal laws (invariants), default-value laws, ramification via OWL-RL closure, non-deterministic outcomes with reproducible seed.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Causal\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\u003Ccode>onto_certify_action\u003C\u002Fcode> with optional PyWhy backdoor identification (opt-in via \u003Ccode>causal-pywhy\u003C\u002Fcode> feature). Structural-proxy default + do-calculus opt-in + graceful fallback.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Planner\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\u003Ccode>onto_plan_compile_pddl\u003C\u002Fcode> + \u003Ccode>onto_plan_classical\u003C\u002Fcode> (Fast Downward subprocess) + \u003Ccode>onto_plan_validate\u003C\u002Fcode> (sandbox-simulate). Solver stays client-side; server compiles + validates.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch3>13 new primitives\u003C\u002Fh3>\n\u003Cul>\n\u003Cli>\u003Cstrong>\u003Ccode>onto_owl_shacl_coevolve_check\u003C\u002Fcode>\u003C\u002Fstrong> + \u003Cstrong>\u003Ccode>onto_owl_shacl_coevolve_incremental\u003C\u002Fcode>\u003C\u002Fstrong> — SHACL validation against the OWL-RL closure, with dependency-graph routing so only shapes touching changed IRIs revalidate.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u003Ccode>onto_segment_retrieve\u003C\u002Fcode>\u003C\u002Fstrong> — TBox-slice retrieval for ontology-grounded RAG.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u003Ccode>onto_extract_scaffold\u003C\u002Fcode>\u003C\u002Fstrong> + \u003Cstrong>\u003Ccode>onto_extract_validate\u003C\u002Fcode>\u003C\u002Fstrong> — schema-guided structured extraction with typed datatype validation + conformance scoring.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u003Ccode>onto_cq_run\u003C\u002Fcode>\u003C\u002Fstrong> + \u003Cstrong>\u003Ccode>onto_verify_cq\u003C\u002Fcode>\u003C\u002Fstrong> + \u003Cstrong>\u003Ccode>onto_cq_verdicts_list\u003C\u002Fcode>\u003C\u002Fstrong> — co\u003C\u002Fli>\n\u003C\u002Ful>\n",1785942027507]