Enables AI assistants to build and maintain a shared, git-backed Markdown wiki: they search, file, update and link notes with YAML frontmatter, keep verbatim sources, and optionally read code repos, so knowledge one assistant records is available to all the others. Runs without LLM calls, embeddings or a database, with the vault's own files defining page types, instructions and tools.
MindBase implements Karpathy's "LLM wiki" pattern as an MCP server. Instead of retrieving chunks at query time (RAG), the LLM maintains a persistent wiki between your conversations: it reads every source you feed it, cross-references pages with [[wikilinks]], flags contradictions between sources, and keeps a context.md that reflects your current synthesized thinking.
Enables an LLM to autonomously maintain a Markdown-based wiki with YAML frontmatter, using hybrid BM25 and local CPU vector search for fully offline retrieval without external APIs or databases.
MCP server for persistent, compounding markdown wikis maintained by LLMs. Enables incremental knowledge base building with interlinked pages, search, and raw source management.
Enables AI-powered knowledge base management with automated wiki-linking, content generation from titles, web research summarization, and knowledge graph integrity maintenance for Markdown files.