xoai/sage-wiki: README-based editorial guide

xoai/sage-wiki describes itself in the README as "sage-wiki is a graph memory and knowledge base that AI agents and humans build and query together. Drop in documents; an LLM compiler turns them into an interlinked wiki with a knowledge graph.". This article keeps to facts that can be checked in the repository. Stars, forks, and promotional badges are signals of attention, not proof of quality. Under "sage-wiki", the README says: sage-wiki is a graph memory and knowledge base that AI agents and humans build and query together. Drop in documents; an LLM compiler turns them into an interlinked wiki with a knowledge graph , agents query it through MCP, humans browse. That establishes the project's stated boundary, not a production test.

The README's "sage-wiki" section gives a useful starting point for deciding whether the project fits: Built for agents and humans. 19 MCP tools plus generated skill files teach agents when to search, capture, and compile; humans get Obsidian-native markdown, a TUI, and a web UI over the same data.. If that problem is not yours, popularity is a poor reason to adopt it. Project names, commands, and component names are kept as written so a reader can return to the primary source without guessing at terminology. Another checkable README item is: Graph memory with citations. Ask relational questions through wikigraphquery , answers are grounded only in serialized graph edges; with the evidenced graph enabled, each citation carries its source document and confidence.. It can shape a first test, but it does not replace testing in the intended environment.

The operating model is spread across sections such as "Knowledge graph & graph memory". The source evidence includes: Vector search retrieves passages that look like the query. A graph also records how things relate, so a question needing two or three hops is answered by traversal instead of hoping one chunk happens to contain the whole chain.. This article does not turn missing architecture, performance, or security details into claims. A real deployment still needs a look at the repository layout, configuration files, and release history.