Memstead documentation

Install expertise into your agent. Memstead packages what someone curated about one subject as a mem: a typed knowledge graph in plain markdown and git, validated on every write against a schema you control. New here? Start with the tutorial, then see Skills for what you actually run day to day — before diving into the concept and reference layers.

Guides

• Getting started — install, memstead quickstart, first entities, agent connect.
• Skills — the plugin roster as a job → command map: what to run for setup, capture, building, syncing, verifying.
• Author a schema — scaffold a custom schema and pin a mem to it.
• Publish a mem — share a mem through the memstead.io registry.
• Agent recipes — worked MCP tool-call sequences with real payloads.
• Back up a mem-repo — push mems to any git remote and recover them on another machine.

Concepts

• Glossary — normative definitions: mem, schema, workspace, mount, entity, and the rest. Built from the repository’s GLOSSARY.md on every deploy.
• The fidelity contract — what a verify run measures (coverage, accuracy, freshness), how it reports honestly, and what it deliberately does not measure yet.
• Vision — what Memstead is for and the design rationale.

Reference

Rendered from the engine sources of the commit this site was built from, at every build: every MCP tool, every CLI subcommand, every typed error code the engine, the CLI and the MCP server produce. The Surface Parity Matrix lines them up so cross-surface gaps are visible by inspection. The registry’s HTTP API is documented where it lives: the publishing guide on memstead.io.

• Skills — the shipped plugin roster, generated from the skill frontmatter.
• Binding format — the versioned source→mem binding: fields, operations, and the per-medium capability matrix.
• MCP tools
• CLI
• Registry HTTP API — not rendered here: the registry documents its own routes in the publishing guide on memstead.io.
• Surface Parity Matrix
• Error Code Index