Back to directory

TheKnowledge

A personal knowledge base that stores markdown and YAML sources on disk and answers queries with ranked, cited context blocks, following a documented pattern for grounding AI assistants in a person's own notes.

TheKnowledge

TheKnowledge keeps sources as markdown and YAML files on the local filesystem and builds a citation graph over them, following what its documentation calls the LLM Wiki pattern. A ranked retrieval command returns bounded, cited context blocks for a query, and separate synthesis pages hold longer answers built from that retrieved context.

The project has three layers over the same data: the wiki itself, which is canonical; NotebookLM, used for heavier synthesis and linked back into the vault; and Obsidian, used to visualize the citation graph. It is meant to be used both interactively, through a command-line tool and documented operations, and by coding or MCP agents, which are pointed at a control-surface document and a status command before making changes.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.