← All comparisons

GNO vs Qmd

Both do local markdown search with MCP. GNO adds BM25+vector+rerank, PDF/Office/exports, a workspace UI, cited answers, skills, and optional gno.sh publishing.

Compare GNO and Qmd for local knowledge search. Both provide local hybrid search with MCP integration — the pattern Karpathy recommends for LLM Wikis. GNO adds multi-format support, a workspace UI, AI answers, agent skills, and optional hosted publishing.

Choose Qmd if
You only need markdown search, want a minimal single-purpose CLI, and prefer the smallest possible tool.
Choose GNO if
You want the full LLM Wiki stack — hybrid search over markdown and other formats, a browsable workspace, AI answers with citations, documented agent integrations, and optional hosted publishing when you need to share.

The LLM Wiki search layer

Karpathy’s LLM Wiki pattern needs a local search engine over markdown files with hybrid BM25 + vector retrieval and an MCP server so agents can query the compiled knowledge. Both Qmd and GNO fit this role. GNO goes further with multi-format indexing, a full workspace UI, AI-powered answers, and one-line agent skill install.

Format support

Retrieval

AI and agent access

Qmd provides an MCP server. GNO provides MCP and one-line agent skill install for Claude Code, Codex, OpenClaw, and Hermes — plus a loopback REST API and TypeScript SDK for custom tooling.

Beyond search

GNO is a full workspace — browsable collection tree, knowledge graph, safe editing, and optional hosted publishing via gno.sh. If you need a browsable tree, graph, and snapshot publishing, those are in GNO / gno.sh.

Keep comparing

More head-to-head pages.