Obsidian is the dominant IDE for LLM-maintained knowledge bases, anchored by Karpathy's reference architecture: Web Clipper ingestion into a raw/ directory, a compiler generating .md files with backlinks and categories, and Marp for slide outputs. The community standard is now "vault as foundation, Claude Code as engine" — plain-text markdown that any agent reads directly, with LLMs writing and maintaining all wiki data while humans rarely edit it. Query results file back into the wiki, compounding future exploration. Two MCP servers—smart-connections for semantic search and qmd for structured metadata retrieval—bridge agent and vault. Agents solve the maintenance burden that killed historical wikis by noticing contradictions, flagging out-of-sync specs, and proposing structural changes; brain-ingest extracts 12-18 claims and frameworks from 90-minute audio locally. Shipping products now implement this pattern: Cabinet packages document processing and scheduled agents operating markdown workspaces; Tolaria (10,000-note proof point, 100K+ LOC, 85% test coverage) layers Git versioning and an MCP server atop plain markdown, designed as a shared human/AI environment; ByteRover unifies fragmented notes across tools into a relevance-scored index. The architectural consensus adds HTML artifacts as interactive interface layers above the markdown foundation for dynamic workflows. Excalidraw (110K stars, end-to-end encrypted) is now the de-facto diagram primitive for plain-text stacks. Google's Open Knowledge Format standardizes storage as interlinked markdown files agents can query and edit programmatically, potentially displacing Obsidian as the storage layer while workflow patterns persist.