Other Minds — Godfrey-Smith"The octopus has 350 million neurons in its arms. The arms think for themselves." #distributed-cognition The Use of Knowledge in Society"Hayek, 1945: 'the knowledge of which we must make use never exists in concentrated or integrated form'" #local-knowledge Lecture note"Gödel: any formal system rich enough to express arithmetic contains true statements it cannot prove" #incompleteness Arbesman — The Half-Life of Facts"half-life of a fact in physics: ~13 years. in surgery, closer to 7" #epistemology Women, Fire and Dangerous Things"Lakoff: human categories organize around prototypes, not necessary and sufficient conditions" #cognition

Other Minds — Godfrey-Smith"The octopus has 350 million neurons in its arms. The arms think for themselves." #distributed-cognitionThe Use of Knowledge in Society"Hayek, 1945: 'the knowledge of which we must make use never exists in concentrated or integrated form'" #local-knowledgeLecture note"Gödel: any formal system rich enough to express arithmetic contains true statements it cannot prove" #incompletenessArbesman — The Half-Life of Facts"half-life of a fact in physics: ~13 years. in surgery, closer to 7" #epistemologyWomen, Fire and Dangerous Things"Lakoff: human categories organize around prototypes, not necessary and sufficient conditions" #cognition

Research How Enzyme compares to Mem0, Honcho, Zep, and Letta on token efficiency →

Memory retrieval tuned to your knowledge base.

Your users bring collections. Enzyme makes your agent fluent in what they care about — faster and at a fraction of the tokens.

Terminal

$ curl -fsSL enzyme.garden/install.sh | bash

Copy

Full setup guide →

42,000+ downloads · Local CLI · Hosted workflows

scroll to discover

Most memory layers start empty.

Yours doesn't have to.

You've captured thousands of ideas. Enzyme treatsyour knowledge base as the memory layer. It reads thestructure you already created—tags, folders, links, temporality—andlearns connections from it.

Other memory layers build a graph from conversations. Enzyme learns the graph from your data.

SETUP

Point it at a folder.

› enzyme init

Indexed: 1,247 discovered, 1,247 new

Catalysts: 84 generated

Discovering entities [14/14]

~ #user-interviews → What does the recurring mention of ‘trust’ across interviews reveal…

~ / investor-updates → How does the framing of retention shift between Q2 and Q3…

~ [[retention]] → What assumption about churn is contradicted by the onboarding…

~ #product-decisions → What does the gap between stated priorities and actual velocity…

Embedded: 980 docs (1,948 docs/sec)

Similarities: 84 catalysts × 980 documents

Done! (14.2s)

Tags, folders, links, timestamps—whatever structure you already have. No configuration.

IN SESSION

The right context, before the first question.

User

“Why is retention dropping if onboarding scores are up?”

agent ▸ enzyme catalyze "retention onboarding"

matched catalyst · [[retention]]

“What assumption about churn is contradicted by the onboarding data in the Q3 investor update?”

→ investor-updates/q3.md

→ interviews/user-12.md

→ journal/aug-04.md

result

The Q3 investor update frames churn as an activation problem. But user 12’s interview says the opposite—they activated fine, then left because the product didn’t match what onboarding promised.

Enzyme connected an investor update and a user interview that never reference each other.

How did it find that? →

Fastest memory layer. Period.

Connections are pre-computed at init. Queries are a database lookup—not a vector search, not an LLM call. The embedding model is compiled into a single ~30MB binary. Everything runs on CPU, on your infrastructure.

<20s 1k+ doc init

1.6ms local query P50

0 search LLM calls

~30MB single binary

Sublinear indexing. Constant-time refresh. Your archive can grow 20x without making every update 20x slower.

Works with Claude Code · Cursor · Obsidian · Hermes · more coming

How is this so fast? →

Early adopters

Thinkers using Enzyme to surface what matters in their notes.

"Enzyme can surface connections I'd only make if I had instant recall... freeing me to use that energy to create and write... I think this is just the beginning."

life coach (NYC)

"Enzyme helps me build richer, more cohesive themes and think more deeply."

HCI researcher, ex-Spotify (Zurich)

"I have a workflow that I love with Readwise, Snipd, and Obsidian. Enzyme beats inertia by quickly drawing me deeper into the meaning of what I'm doing."

songwriter and pastor (NYC)

Build products on what your users have captured.

Your users bring collections. Enzyme gives your agent their conceptual landscape from the first session.

Reading & highlights app Kindle highlights, podcast clips, article saves

Generate writing prompts from two years of reading — grounded in connections the user was already building.

Design tool Exploration sessions, chosen vs. rejected options, revision history

A conversational agent that knows the user's taste — helps them build with their own preferences, not generic defaults.

Engineering assistant ADRs, retros, decision logs, Slack digests

Onboard new engineers with answers that carry the full institutional reasoning, not just the current state.

Talk about your corpus →

Try it on your own vault.

Terminal

Copy

Local-first indexing with hosted memory workflows when you need them.

Building a product on imported content?

Let's talk about your corpus →

Not ready for the CLI? More integrations coming.

Notify me