iwe vs SSTorytime
Markdown notes as a knowledge graph: an LSP for VS Code, Neovim, Zed and Helix, plus CLI and MCP so AI agents query the same files by structure. Rust, local-first, OKF-compatible. — 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.
Both turn hand-written notes into a queryable knowledge graph; SSTorytime compiles N4L notes into a spacetime graph on Postgres, IWE keeps plain Markdown files and derives the graph from links.
| iwe | SSTorytime | |
|---|---|---|
| Stars | 1.7k | 259 |
| Forks | 90 | 41 |
| Language | Rust | Go |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 2 days ago | yesterday |
| Topics | knowledge-graphs, memory | knowledge-graphs |
| Curated connections | 4 | 3 |
iwe — the curator's take
The best fit for people who already live in Markdown and want their agent to share that brain: inclusion links give notes a real hierarchy, the LSP adds rename, refactor and search in your editor, and the CLI and MCP let Claude or Codex navigate by structure (parent context, subtrees, frontmatter filters) instead of similarity guesses. No database, no cloud; git is the sync. IWE has no AI of its own, so it will not write or summarize notes for you (that is LLM Wiki's job), and its payoff scales with how carefully you link. It speaks Google's OKF, so notes stay portable.
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.