Wordkeep

An AI-agnostic Model Context Protocol server that turns large codebases into high-signal, budgeted context for coding agents and humans. Built for engine-scale repos where grep and full-file reads do not scale.

The problem

Agents burn context on noise: whole files, stale indexes, and hand-rolled prompts. Wordkeep answers with structured tools: symbol maps, call graphs, knowledge search, defect tracking, and Tracy triage. The model sees what matters.

What we shipped

  • Rust MCP server with composable tools for repository mapping, symbol refs, call paths, test discovery, change-impact analysis, and session handoff.
  • Multi-language analysis via tree-sitter (C/C++, Rust, Python, C#, TypeScript, Svelte, GLSL, and more) with incremental reparsing and mtime-based caches.
  • Deterministic BM25 retrieval plus optional local semantic rerank; telemetry for latency, outcomes, and tokens saved.
  • Dark Amethyst wiki UI aligned with Arathyll design tokens for notes, defects, MCP savings dashboard, and garden health.

Results (measured on Betwixt)

In daily agent workflows on this engine repo, Wordkeep routinely cuts context payloads by 99%+ while keeping warm queries in the single-digit to low tens of milliseconds range; enough to stay on the critical path of interactive coding.

Public vs private

Production Wordkeep stays loopback-first: MCP over stdio in your editor, optional wiki GUI on 127.0.0.1:8787, no write API on the public internet.

This site hosts the Wordkeep Wiki lab: search, reader, MCP telemetry dashboard, and garden health over a read-only corpus. The demo treats Azera as the external consuming project (sanitized architecture notes under projects/azera/), plus Wordkeep MCP docs. Scrubbed mock MCP savings power the Dashboard tab. It is a portfolio demo, not a hosted Wordkeep instance and not a path into private Betwixt trees.

How the Lab demo is hosted

  • Corpus: wordkeep-demo/ in the Arathyll repo (Wordkeep docs + projects/azera/). Indexed at container start with WIKI_READ_ONLY=1.
  • Services: wordkeep-meili (Meilisearch) and wordkeep-wiki (Axum + Svelte UI) on the Dev Compose stack.
  • Proxy: SvelteKit same-origin proxy at /lab/wordkeep/ui/* (WORDKEEP_WIKI_URL). Cookie/auth headers are stripped.
  • Iframe: Lab overlay uses sandbox without allow-same-origin. The wiki UI falls back to in-memory storage when localStorage / sessionStorage are blocked.
  • Deploy: build context is /usr/deploy with sibling tools/wordkeep and arathyll/wordkeep-demo (Dockerfile.deploy). Staging/KVM Compose must include both Meili and wiki services.

See also

  • Lab: Wordkeep Wiki

    Interactive browser demo over the Azera + Wordkeep corpus.

  • Azera

    The external project represented in the demo tree.

  • GitHub

    Install, MCP config, and the wiki companion.

  • Services

    How we embed similar discipline on client codebases.