Enzyme MCP Server

<div align="center">

🧬 Enzyme

</div>

Enzyme compiles your notes and other knowledge sources into a local index 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.

Enzyme saves an editable reading program. For a Markdown folder, the program currently uses a vault block; named workspace blocks describe Are.na and SQLite sources. Jev can generate the Markdown program 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"

For Markdown notes, run enzyme compile and review the settings file it saves before enzyme init builds the local index.

For Apple Notes, a preset builds a named workspace program from your Notes database. Review the saved .enzyme program before running init:

enzyme --collection apple-notes compile --preset apple-notes \
  "$HOME/Library/Group Containers/group.com.apple.notes/NoteStore.sqlite"
enzyme --collection apple-notes init

For Are.na, use enzyme --collection <name> compile --preset arena <channel-url> and then enzyme --collection <name> init. Run refresh with the same --collection name to pick up later changes.

Enzyme was built for knowledge bases that grow rapidly:

• Agent memory corpora
• Zettelkasten practices in Obsidian that accumulate new dated notes into singular folders
• Meeting transcriptions built around AI-native, Markdown CRM setups.

It's designed to support knowledge captures that might be later be important, even if they don't serve a current task. Enzyme is focused on doing one thing well: giving agents the tools to make ideas compound.

And it ships with a set of profiles designed around a personal knowledge base, that were refined over 2 years of personal use. Here are some examples of how they are used:

Read...	For...	Profile
Project notes	what's stuck and what keeps blocking	operational
Decision records	why a choice won, what would change it	decision_trace
Saved articles	connections to what you're already working on	resonance_trace
Journals	what keeps returning across entries	reflective
People notes	what matters in these relationships	relational
Feedback / activity logs	what works for you, under what constraints	preference_evidence
(default)	costs, assumptions, live tensions	tension_trace

Agent tools for retrieval

enzyme petri shows what Enzyme found worth asking about. In an interactive terminal it renders a tree; piped, it emits JSON:

enzyme petri | jq '.entities[:2]'

[
  {
    "name": "system-design",
    "type": "tag",
    "activity_trend": "active",
    "frequency_12m": 84,
    "catalysts": [
      {
        "text": "What does the commitment to simplicity cost when the pressure to ship keeps winning?",
        "context": "velocity vs craft in infrastructure",
        "era": "2024-Q3"
      },
      {
        "text": "Where does the analysis of user needs gather information that delays rather than clarifies the core value?",
        "context": "research as avoidance",
        "era": "2025-Q1"
      }
    ]
  },
  {
    "name": "working-with-others",
    "type": "tag",
    "activity_trend": "rising",
    "frequency_12m": 47,
    "catalysts": [
      {
        "text": "What assumptions about leadership are held by those who are good at building things?",
        "context": "craft vs delegation",
        "era": "2024-Q4"
      },
      {
        "text": "How does the goal of not depending on others shape the approach to collaboration?",
        "context": "independence vs team trust",
        "era": "2025-Q2"
      }
    ]
  }
]

Each entity carries catalysts spanning different eras — questions that cut across months of content.

enzyme catalyze "why we keep rewriting the auth layer"

{
  "query": "why we keep rewriting the auth layer",
  "results": [
    {
      "file_path": "retros/2024-q3-platform-retro.md",
      "content": "scoped auth extraction as a two-week project for the third time. real blocker wasn't the token service — nobody wanted to own the session model. every proposal added a layer instead of removing one.",
      "similarity": 1.46
    },
    {
      "file_path": "adrs/007-auth-service-extraction.md",
      "content": "the monolith's session handling has become the bottleneck for every team shipping independently. chose separation of concerns over the coordination cost of a new service boundary.",
      "similarity": 1.24
    },
    {
      "file_path": "reading/highlights-accelerate.md",
      "content": "'Teams that can deploy independently are twice as likely to be in the high-performer category.' — we keep choosing the rewrite over the boundary.",
      "similarity": 1.13
    }
  ],
  "top_contributing_catalysts": [
    {
      "entity": "system-design",
      "text": "What does the commitment to simplicity cost when the pressure to ship keeps winning?",
      "relevance_score": 0.74
    }
  ]
}

Output above is illustrative — it shows the shape of a result, not a captured run.

message archives (experimental)

Enzyme indexes SQLite tables alongside Markdown — iMessage, WhatsApp, Mail, or any table of dated rows.

Declare a source sqlite inside a named workspace program, then run init and periodic refresh. The SQLite source setup skill shows the source declaration and source-scoped readings.

None of these is a special case. A handle_id column is repeated person values across dated rows, the same way [[links]] are repeated person values across dated notes. Both collapse to entity occurrences with effective dates, and nothing downstream knows which one it came from: the same profiles, budgets, and catalysts apply to a message thread and a folder of meeting notes.

A source names columns by the role they play rather than by the app they came from:

Role	Means
id	the row's identity
who	participants; scalar, JSON array, or delimited
when	the row's timestamp
what	the text to read
where	the container the row belongs to (optional)
weight	numeric significance per occurrence (optional)

API keys

Enzyme needs an API key only for catalyst generation and for Markdown enzyme compile's selection step. Source preset compilation does not call a model. By default enzyme init uses Enzyme's hosted bootstrap and ignores inherited OPENAI_* variables so it does not spend your personal key. Credential resolution is explicit key → configured local model → anonymous brokered free config, with no additional configuration.

The first configured vault on a machine initializes without login. Refresh, publishing, account credits, and additional vaults require enzyme login.

To bring your own OpenAI-compatible key, pass --use-env-llm, which reads OPENAI_API_KEY plus optional OPENAI_BASE_URL and OPENAI_MODEL. Without any hosted or env key, catalyst generation is skipped and indexing, embedding, and local search still work.

Markdown enzyme compile is an explicit OpenRouter Decisions operation. It reuses the hosted lease from enzyme login and the free-config broker; an explicit OPENAI_API_KEY with OPENAI_BASE_URL=https://openrouter.ai/api/v1 takes precedence. Catalyst generation uses OPENAI_MODEL; Decisions uses ENZYME_JEV_MODEL (default typesafe/jev-1.13).