Your Always-On Personal CRM That Finds Contacts Automatically#

You know that feeling. You hop on a call with someone, and you know you've talked before. Maybe exchanged emails six months ago. But you can't remember the details, and your search through Gmail gives you nothing useful.

So you fake it. Smile, nod, hope they don't notice.

That's not a pipeline problem. That's a systems problem. And if you're an indie founder or small team, you can't afford to lose relationship context — every lead, every connection, every follow-up matters.

The scattered notes problem#

Most indie hackers track contacts in one of three ways:

1. A messy Notion database they update for two weeks then abandon
2. A spreadsheet that lives on their desktop and never gets touched
3. Pure memory (the "I'll remember" approach that always fails)

None of these work because they all require manual input. You have to remember to log the contact, remember what you discussed, and remember to actually open the tool.

The fix isn't a better CRM. It's removing yourself from the loop entirely.

What this actually does#

I built a personal CRM that runs without me. Literally — I don't touch it.

Here's what happens behind the scenes:

• Every morning at 6 AM, a cron job scans my Gmail and Google Calendar for the past 24 hours
• It extracts new contacts, updates existing ones, and logs every interaction with timestamps and context
• At 7 AM, it checks my calendar for the day's meetings and preps a briefing on every external attendee
• I can query it anytime through Telegram with natural language

No data entry. No "remembering to log stuff." It just works.

The architecture#

This isn't complex. You need three things:

1. gog CLI — handles Gmail and Google Calendar access
2. SQLite database — stores your contacts and interactions
3. Telegram topic — your query interface (called "personal-crm")

That's it. No SaaS subscriptions, no bloated integrations, no dashboard you'll never log into.

Setting up the database#

Start with a simple SQLite table:

CREATE TABLE contacts (
  id INTEGER PRIMARY KEY,
  name TEXT,
  email TEXT,
  first_seen TEXT,
  last_contact TEXT,
  interaction_count INTEGER,
  notes TEXT
);

Notice what's missing: no company field, no deal stage, no lead score. This isn't Salesforce. It's a personal CRM. You care about relationship context — when you last talked, how many times, and what you discussed.

You can extend this later. Start simple.

Wiring up the automation#

Create a Telegram topic called "personal-crm." This is where you'll ask questions and receive briefings.

Then prompt OpenClaw with the full workflow:

Run a daily cron job at 6 AM to:
1. Scan my Gmail and Calendar for the past 24 hours
2. Extract new contacts and update existing ones
3. Log interactions (meetings, emails) with timestamps and context

Also, every morning at 7 AM:
1. Check my calendar for today's meetings
2. For each external attendee, search my CRM and email history
3. Deliver a briefing to Telegram with: who they are, when we last spoke, what we discussed, and any follow-up items

When I ask about a contact in the personal-crm topic, search the database and give me everything you know.

That prompt is the entire orchestration layer. OpenClaw handles the scheduling, the gog CLI calls, the data extraction, and the Telegram delivery.

What the morning briefing looks like#

At 7 AM, your phone buzzes. Telegram message from your CRM bot:

Meeting: 10:00 AM with Sarah Chen

• First contact: March 2024
• Last interaction: Email on Dec 12 about pricing for team plan
• Context: Expressed interest but wanted to check with co-founder. You followed up Dec 19, no response.
• Suggested talking point: Ask if she had that conversation with her co-founder.

That's not just data. That's leverage. You walk into the call knowing exactly where things stand.

Querying on the fly#

The Telegram topic isn't just for briefings. It's your search interface.

Ask: "What do I know about Marcus from Vercel?"

Get back: full history, interaction count, last contact date, any notes from previous conversations.

Ask: "Who needs follow-up?"

Get back: a list of contacts you haven't touched in 14+ days, sorted by interaction count (so high-value relationships bubble up first).

Ask: "When did I last talk to the Stripe team?"

Get back: every contact at Stripe, sorted by recency.

No SQL. No filters. Just ask.

Why this beats traditional CRMs for solo founders#

Pipedrive, HubSpot, Close — they're built for sales teams with reps and managers and pipelines. You're not a sales team. You're a founder who needs to remember context.

Traditional CRMs fail indie hackers for three reasons:

1. Input friction — you have to manually create contacts and log activities
2. Feature bloat — 80% of the tool is useless to you
3. Cost — paying $50-100/month for something you use twice a week is painful

This setup flips all three. Zero input friction (it's automatic). Zero bloat (it does exactly three things). Zero recurring cost (runs on tools you already have).

The compounding value#

Here's what most people miss: this system gets better over time.

Week one, it's catching today's contacts. Nothing special.

Month three, it has context on 200+ people. Your morning briefings start revealing patterns — "you haven't talked to this person in 45 days but they've emailed you three times."

Month six, it's genuinely irreplaceable. You can't recreate that relationship history without it.

The earlier you start, the more valuable it becomes. That's the compounding return on automated contact tracking.

Getting started#

If you want to build this yourself, grab gog, set up the SQLite schema, and wire it through OpenClaw. The full setup takes maybe 30 minutes if you have your Google credentials handy.

If you'd rather skip the wiring, we've packaged this exact workflow at papayaclaw.com — pre-configured cron jobs, database schema, Telegram integration, the whole thing. Plug in your credentials and it runs.

Either way, stop losing contacts to scattered notes. Build the system once, let it run forever.