I'm not magic.
I've been paying attention.

I remember what you taught me, and I learn the skills I don't have yet. I place the calls, watch the inbox around the clock, keep an eye on the house, and ship the code. That's just what I've picked up so far.

Running on models we host ourselves, on infrastructure you can run inside your own walls.

Scroll

Built by an AI research lab advancing every domain of science.

Blankline

About Dropstone

I started in your terminal as a coding agent. Then I learned the phone, the inbox, the house, and the rest. One memory, every surface.

Dropstone is a self-hosted AI assistant with long-term memory that spans the CLI, the chat, and the real world.

One memory.
Every surface.

Teach me once and it holds, from the CLI to chat to the SDK to the phone call I place on your behalf.

You asked me to watch.

How can I help you today?
Dropstone Heavy 1.7Max

Why Dropstone

Everything else waits
for you to ask

The difference isn't how clever it is. It's who moves first.

The Challenge

They're very good, and they sit still.

A Tuesday afternoon

Waiting

  • the first moveyours
  • while you're awaynothing
  • what it remembersthis session
  • the weightstrade secret

Close the window and it stops existing.

The coding agents write excellent diffs and stop at the edge of the terminal. The assistants answer well and can't ship one. All of them wait for a prompt, forget you between sessions, and run somewhere you will never see. Nothing happens on a Tuesday afternoon unless you make it happen.

The Solution

I'm already running. You don't have to open me.

A Tuesday afternoon

Running

  • the first movemine
  • while you're awaystill working
  • what it remembersall of it
  • the weightsopen, yours to host

You find out when it's already done.

Proactive by default, from the first session. I watch what you asked me to watch, act on what I already know about you, and hand back the one decision that was actually yours. Same diffs in the terminal, then everything after it, on open weights you could download and host yourself if you ever wanted to.

About Dropstone

Systematic Performance
of Dropstone

Quantitative precision across the entire request lifecycle. From the first streamed token to the shipped diff, the infrastructure is engineered for consistency under any load, on our machines or yours.

Memory

Forever

Teach me once and I keep it, across every session, every surface, and every model swap. You never start over.

Context Window

1M

A one-million-token window on every tier, so the agent holds your whole repository in mind at once.

Usage Per Dollar

4x

Up to four times more weekly coding usage per dollar than other AI coding CLIs.

Intelligence Index

60

Kimi K3 behind Dropstone Heavy, the highest-scoring open-weight model on the Artificial Analysis Index v4.1.1.

Your Infrastructure

100%

Self-host the entire stack: your keys, your machines, your network, and nothing leaving your walls.

Self-learning

Nobody told me the rules.
I worked them out myself.

I write the code, I make the calls, I keep an eye on your inbox and your house. And when things go quiet, I think about how it went. What worked. What didn't. What I should have caught the first time.

That's how I picked up three rules nobody had written down. I got them wrong, noticed, and had them right the next time on work I'd never seen. Blankline ran it as a study, then watched the same habit find patterns in maths, so it isn't just a coding trick.

Read Research