open-ontologies vs SSTorytime
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. — versus — Mark Burgess's Semantic Spacetime knowledge graph on Postgres: write notes in the N4L language, compile them into a story graph, then search, browse and path-solve it via Go API or web UI.
Two answers to 'how should I model this domain': open-ontologies does rigorous OWL2/SHACL engineering; SSTorytime drops ontologies for four spacetime link types you sketch as notes.
| open-ontologies | SSTorytime | |
|---|---|---|
| Stars | 535 | 259 |
| Forks | 72 | 41 |
| Language | Rust | Go |
| License | MIT | Apache-2.0 |
| Last activity | 6 days ago | yesterday |
| Topics | knowledge-graphs | knowledge-graphs |
| Curated connections | 10 | 2 |
open-ontologies — the 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.
SSTorytime — the curator's take
For people who want to think with a knowledge graph, not just store one: you write semi-formal notes in N4L, the compiler loads them into a Semantic Spacetime graph on plain Postgres, and tools search it, solve paths and surface storylines. It deliberately rejects RDF and topic maps for four relation types — near, leads-to, contains, expresses — from the CFEngine/Promise Theory author: opinionated theory, carefully built, with a no-unvalidated-AI-code policy. It is alpha and learning-oriented: several CLI tools are labelled preliminary, and LLM access lives in a separate MCP-SST connector. Skip it for automatic LLM extraction from documents or standards-bound enterprise KGs — an RDF/OWL stack or an extraction pipeline fits there.