The deterministic enterprise AI agent platform.
Neuro-symbolic architecture for the Agentic Web — OntoCore • OntoMCP • OntoStore
Overview • Getting Started • Roadmap • Philosophy
OntoSkills transforms natural language skill definitions into validated OWL 2 ontologies — queryable knowledge graphs that enable deterministic reasoning for AI agents.
The problem: LLMs read skills probabilistically. Same query, different results. Long skill files burn tokens and confuse smaller models.
The solution: Compile skills to ontologies. Query with SPARQL. Get exact answers, every time.
flowchart LR
CORE["OntoCore<br/>━━━━━━━━━━<br/>SKILL.md → .ttl<br/>LLM + SHACL"] -->|"compiles"| CENTER["OntoSkills<br/>━━━━━━━━━━<br/>OWL 2 Ontologies<br/>.ttl artifacts"]
CENTER -->|"loads"| MCP["OntoMCP<br/>━━━━━━━━━━<br/>Rust SPARQL<br/>in-memory graph"]
MCP <-->|"queries"| AGENT["AI Agent<br/>━━━━━━━━━━<br/>Deterministic<br/>reasoning"]
style CORE fill:#e91e63,stroke:#2a2a3e,color:#f0f0f5
style CENTER fill:#abf9cc,stroke:#2a2a3e,color:#0d0d14
style MCP fill:#92eff4,stroke:#2a2a3e,color:#0d0d14
style AGENT fill:#6dc9ee,stroke:#2a2a3e,color:#0d0d14
| Problem | Solution |
|---|---|
| LLMs interpret text differently each time | SPARQL returns exact answers |
| 50+ skill files = context overflow | Query only what's needed |
| No verifiable structure for relationships | OWL 2 formal semantics |
| Small models can't read complex skills | Democratized intelligence via graph queries |
For 100 skills: ~500KB text scan → ~1KB query
# Install
pip install ontoskills
# Compile skills to ontology
ontoskills init-core
ontoskills compile
# Query the knowledge graph
ontoskills query "SELECT ?skill WHERE { ?skill oc:resolvesIntent 'create_pdf' }"Or use npx ontoskills without installing.
| Component | Language | Status | Description |
|---|---|---|---|
| OntoCore | Python | ✅ Ready | Skill compiler to OWL 2 ontology |
| OntoMCP | Rust | ✅ Ready | MCP server for semantic skill discovery |
| OntoStore | TBD | 📋 Planned | Versioned skill registry |
skills/ |
Markdown | Input | Human-authored skill definitions |
ontoskills/ |
Turtle | Output | Compiled, self-contained ontologies |
- Overview — What is OntoSkills and why it matters
- Getting Started — Installation and first steps
- Architecture — How the system works
- Knowledge Extraction — Extracting value from skills
- Registry & Packages — Package distribution and import
- Roadmap — Development phases
MIT License — see LICENSE for details.
© 2026 Marea Software