I truly don't understand why nobody is using this setup graphify, a tool that turns any folder into a knowledge graph your agent can query, just passed 126k stars on github and got into Y Combinator. people stopped asking ai questions. they're giving it a desk, a memory and... a job. you give Claude Code one folder, plug in your email, calendar and a browser, and it turns into an agent. it reads, remembers, acts, and checks itself before it does anything stupid. doesn't matter if you're a founder, a marketer or a student, you need this the full setup: > create a folder called AGENT, open Claude Code inside it and add a CLAUDE.md with one rule: "save every decision, person and project to memory/" > run npm install -g @googleworkspace/cli, then gws auth setup. now it reads your Gmail, Calendar and Drive > run claude mcp add playwright npx @playwright/mcp@latest. it gets its own browser to open sites, fill forms and pull data for you > run uv tool install graphifyy, then graphify install, then type /graphify .. everything in the folder becomes a knowledge graph it queries in seconds instead of digging file by file > run npm i -g jev-guard, jev-guard key "...", jev-guard install claude. a tiny model called Jev scores every action before it runs. rm -rf gets blocked, a poisoned email gets flagged, for about 4 cents per 1,000 checks > type /schedule and tell it "every morning at 7:30, send me what came in, what you drafted and what waits for my yes". from now on it works on a routine 15 minutes to set up, and you never start from a blank chat again. every repo is below: -> -> -> -> bookmark thisshow more

the graphify + CLAUDE.md memory folder is the part that actually sticks. without it you still start from zero every session. how stable has the morning routine been for you so far?

That why it needs optimization

persistent memory is the actual unlock

Using it myself too

i know what ill do todays evening

Hah same here

Giving the agent a queryable folder graph beats paste-the-readme every session. We've been pushing structure into CLAUDE.md + a local memory file for the same reason — once the desk exists, questions get shorter and answers stay grounded.

Exactly ma friend

Thanks for sharing

Welcome bro

I am using it plus obsidian

The real upgrade is persistent memory plus controlled access to tools, not just connecting more integrations. But email, browser actions, and scheduled jobs need strict permissions and a reliable approval layer before this becomes something you can safely leave running.

Agree

the goal isn't just an agent that remembers, it's one that can show its work

I felt like trying to use this

Using it already

Giving AI a structured knowledge base instead of relying on isolated prompts can make a huge difference. Persistent context is what makes agents genuinely useful for complex work.

This is the way

what a gem

Likewise

Having the drafts ready but unsent is the bit I like. You save the preparation time without handing over the send button.

Doing it too

图谱画出来容易，后面文件改了能自动跟上吗

Easy

the setup alone is a job

126k github stars and no one's using it? half those stars are just bookmarked for later.

Biến một thư mục thành đồ thị tri thức để tác tử tra cứu là hướng hay: bộ nhớ có cấu trúc giúp trả lời đúng ngữ cảnh hơn là hỏi đáp rời rạc. Bạn nghĩ chi phí cập nhật đồ thị khi dữ liệu đổi thì sao?

I love how creative people are getting with these tools.