Show HN: Enzyme – a programming language that compiles wikis for agents

Enzyme helps your coding agent work from your notes. It reads how your Markdown notes are already organized (folders, tags, links, and dates) and builds a local index, so Claude Code or Codex can pull up related notes from months of writing and cite them.

Open your Markdown notes folder in Claude Code, Codex, or another agent that can run terminal commands, and paste this prompt. If your agent is open elsewhere, give it 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.

Your agent installs Enzyme and follows its setup skill. It proposes which folders, tags, and links to read, shows you the settings so you can correct them, builds the index, and answers one real question with links to the notes behind it. Your notes stay where they are, and you don't need to clean them up first.

After setup, keep working with your agent as usual. The installed skill tells it when to search with Enzyme, when plain search is better, and when to run enzyme refresh so new notes are included.

Prefer to install it yourself first? Run this, then paste the same prompt:

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

Enzyme was built for knowledge bases that grow quickly:

• Obsidian vaults that accumulate dated notes in a few folders
• Meeting notes and AI-native, Markdown CRM setups
• Agent memory written as Markdown

It helps most when a question spans many notes written over time: what changed in a project, what keeps coming up with a person, why a decision went the way it did. For a name, title, or exact phrase, plain search is faster, and the installed skill tells your agent to use it.

Setup saves a short, editable settings file (an .enzyme program) that says what to read. When the index is built, Enzyme does two things:

1. Maps what matters. It samples excerpts across time from each folder, tag, or link you chose and writes questions from them, calledcatalysts , about what you decided, changed, or left open there.enzyme petri shows this map.
2. Indexes every note for search.enzyme catalyze ranks notes by wording and meaning together, so a search finds the passage whether your agent names something exactly or only describes it. Each result carries the catalyst that best connects it to the query. Search runs entirely on your machine.

Your agent orients on the map, searches from several angles, and answers from your own passages, so it can tell you how your thinking moved, not just what one note says. Catalysts are generated, so they're hints, never evidence: judge setup by the notes your agent brings back.

A small settings file looks like this. Your agent writes and edits it with you during setup:

workspace "notes" {
  source markdown "notes" { path "~/notes" }

  learn questions from folder "people" including linked pages about relational
  learn questions from folder "meetings" about operational
  learn questions from tags ["startup", "design"] about decision_trace
}

Each reading uses a profile that sets what to look for. The built-in profiles were refined over 2 years of personal use:

enzyme compile -v
enzyme init --quiet
enzyme doctor
enzyme catalyze "a question about your notes"

compile proposes settings and saves them; init builds the local index from them; doctor reports what was indexed and any problems.

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

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

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

enzyme petri shows what Enzyme found worth asking about: for each recurring tag, link, or folder, questions about what you decided, changed, or left open, sampled across time. In a terminal it renders a tree; piped, it emits JSON.

enzyme petri -n 2
Petri
├─ #working-with-others · tag · active · 11 mentions
│  └─ catalysts
│     ├─ Why did every auth change still route through me after I kept promising to write it down?
│     ├─ Why did the third auth extraction attempt stall when nobody wanted to own the session model?
│     ├─ Which reasons for handing the session model to Maya had I stopped believing by then?
│     ├─ Did extraction stay d once Maya's team owned the session model?
│     └─ …
└─ #system-design · tag · active · 10 mentions
   └─ catalysts
      ├─ Why did I pick a monolith with inner module boundaries over splitting services yet?
      ├─ Did I ever settle who owns the session model once auth moves out?
      ├─ Which part of auth extraction kept adding layers instead of removing one?
      ├─ Does my view that independence means who can change what still hold?
      └─ …

An agent reads this map first, then searches. enzyme catalyze ranks notes by wording and meaning together, and each result carries the catalyst that best connects it to the query:

enzyme catalyze -n 3 "why we keep rewriting the auth layer" \
  | jq '{search_strategy, results: [.results[] | {file_path, similarity, via_catalyst_text, content}]}'
{
  "search_strategy": "hybrid",
  "results": [
    {
      "file_path": "retros/2025-q3-platform-retro.md",
      "similarity": 0.817,
      "via_catalyst_text": "Why did I keep scoping auth extraction as a two-week project, and what kept stalling it?",
      "content": "# Q3 platform retro\n#system-design #working-with-others\n\nScoped auth extraction as a two-week project for the third time. The real blocker was not the token service; nobody wanted to own the session model. Every proposal added a layer instead of removing one. Action: decide ownership before touching code again."
    },
    {
      "file_path": "journal/2025-05-12.md",
      "similarity": 0.693,
      "via_catalyst_text": "Why did every auth change still route through me after I kept promising to write it down?",
      "content": "#working-with-others\n\nReviewed eleven PRs today and wrote none. Every auth change still routes through me because I wrote the session code and nobody else wants to touch it. I keep saying I will write it down so someone else can own it. I have not."
    },
    {
      "file_path": "1on1s/2026-01-maya.md",
      "similarity": 0.579,
      "via_catalyst_text": "What keeps pulling me back to rewriting when Maya's smaller version already worked?",
      "content": "# 1:1 with Maya\n#working-with-others\n\nMaya replaced the token refresh path with something half the size of mine. She asked me twice and then stopped asking, which is the point. I want to do this with billing before I start rewriting it myself."
    }
  ]
}

Captured from a 17-note example vault of a team lead's ADRs, retros, 1:1s, and journal. Catalyst wording comes from model generation, so it varies between runs.

Scripts and host apps can rely on defined exit codes (0 ok, 1 runtime failure, 2 usage, 3 configuration, 4 workspace busy, 5 init indexed but catalysts failed their quality gate). Concurrent init/ refresh calls on one workspace wait for each other, bounded by --lock-timeout.

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:

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 --llm env (alias --use-env-llm), which reads only OPENAI_API_KEY plus optional OPENAI_BASE_URL and OPENAI_MODEL. init and refresh also take --llm local (the installed local model; fails if none is installed), --llm hosted, and --llm none (index, embed, and select without generating catalysts). Without --llm and 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).