Enzyme MCP server

🧬 Enzyme

Enzyme introduces a compile step for your Markdown wiki that:

1. Uses temporally grounded context sampling that captures the contextual use of tags and wikilinks, or natural accumulation in folders (i.e. pseudo-Zettelkasten)
2. With this context, generate questions (called catalysts) and embed them as semantic routes to the whole knowledge base
3. Keeps refreshing, but separates new doc ingestion (local, fast) from catalyst evolution (cheap, periodic)

When your agent passes queries through the catalysts, it gets a more personalized way to get caught up on the knowledge base.

New: Enzyme relies on a program that Jev generates through a deterministic scan:

profile relationships {
  seek "what matters between people"
  notice ["meaningful exchanges", "shared interests", "unfinished conversations"]
}

vault "~/notes" {
  question budget 40
  sample across time
  favor recent periods

  learn questions from folder "people"
    including linked pages
    about relationships
  learn questions from folder "meetings" about operational
  learn questions from tags ["founding", "ai-ux"] about decisions
  learn questions from folder "inbox"

  project questions into "~/notes/Readwise"

  // Guidance compiled for your agent, not an enforced hook.
  when asked {
    "Use grep for names, titles, and exact phrases."
    retrieve passages through learned questions
    answer with sources
  }
}

Get started

Open your Markdown notes folder in an agent that can run terminal commands, such as Claude Code or Codex, and paste this prompt. If your agent is open elsewhere, replace the first sentence with the path to your notes.

Set up Enzyme for the Markdown notes folder I have open. If you cannot identify it, ask me for its path.

Install Enzyme if needed using https://raw.githubusercontent.com/byenzyme/enzyme/main/install.sh, and install the instructions for this agent. Read and follow the installed enzyme-workspace-setup skill.

You may use Enzyme's online service to suggest settings from my notes and prepare search. Show me what you propose to include or exclude, and let me correct it before building the local search index.

Then answer one useful question using my notes, with links to the sources, and suggest a question I can ask next. Keep my existing notes in place and unchanged. Ask separately before any cleanup, model download, or recurring task.

The agent installs Enzyme, reviews the settings with you, and demonstrates an answer from your own notes. You can keep writing and organizing your notes as you already do; cleanup is not a prerequisite.

Terminal setup

If you prefer to install it yourself:

curl -fsSL https://raw.githubusercontent.com/byenzyme/enzyme/main/install.sh | bash
cd /path/to/your/notes
enzyme install claude # or: codex, hermes, openclaw

Then use the prompt above. For setup without an agent:

enzyme compile -v
# Review the .enzyme settings file at the path printed by compile.
enzyme init --quiet
enzyme doctor
enzyme petri --query "a question about your notes"
enzyme catalyze "a question about your notes"

compile uses online selection and saves proposed settings under ~/.enzyme/configs/. Review that file before init builds the local index.

Shortened. The full README is on GitHub.