your server. your keys. your house.

New hires that never leave the building.
Neither does your data.

Lares is an open-source platform for running a small team of AI agents inside your business. They read the inbox, keep the calendar, draft the follow-ups, and ask before anything goes out. Your server or ours, your keys, your rules.

how it works

It comes to you. Where you already are.

No dashboard to log into. The morning brief arrives in the chat you already use. You answer in one tap. The agent does the rest and keeps a receipt of what it did and who said yes.

  • Slack
  • Telegram
  • Email
  • Web chat
  • WhatsApp
  • Teams
#officeillustrative example
Agent 07:30 · inbox + calendar

Morning. Two things need you. The rest is handled.

needs you · email draft

Follow-up to Kari after yesterday's meeting. Draft ready.

needs you · calendar

Thursday has two overlapping calls. Move the 14:00?

You 07:41

Send it. Move the 14:00.

Agent 07:41

Sent to Kari. 14:00 moved to 15:30, both invited. Receipt saved.

What it does before you ask

01

It comes to you

Start with a brief of your inbox, upcoming plans and the decisions that need you. Less babysitting, not more.

02

It asks first

Review an action before it goes out. Set what each agent may do, and when it must ask.

03

It stays put

Your server, your keys, your data. One official, private place for the work people are already pasting into chatbots.

04

Make each agent yours

Choose a purpose, give it a name, and set its access. Keep its work and permissions in one place.

Three ways in.

one platform. different levels of help.
Self-host

Take the code home.

Install on your own server today. Your keys, your rules, your agents. Open source, Docker, one command.

Install guide
Cloud coming soon

Same platform. We keep the lights on.

A standard installation on a server we run and update, in a region you choose. Opens when enough of you ask.

then three short questions about your setup

Managed service

We run it. You read the brief.

Set up and cared for by us, on our servers or inside your own infrastructure. Starts with a conversation.

Care f**k all about agents? Fine.

You want the manual work gone, not a new system to learn. Tell us what it is. We'll say honestly whether lares can do it yet, and what it would take.

Send an email

Email opens in your mail app. Booking opens a small calendar window.

under the hood
memory

Memory you can open

What agents learn is Markdown in git, readable in any editor. Dated facts sit in a database and every one can be exported.

learning

It learns by asking

An agent may add to what it knows. Changing or forgetting something needs your yes. Nothing read in an email can become a memory.

updates

Updates with a way back

Dated monthly releases. A backup before every update, a fix shipped with every breaking change, one command to roll back.

backups

Backups you can prove

Nightly, encrypted. A monthly restore drill. Export everything, or erase one person's data on request.

models

Your keys, your caps

Bring your own model keys. A gateway on your server maps each job to a model, and every agent has a daily spend cap.

network

Nothing phones home

Runs on your own server, or ours in a region you choose. Outbound traffic goes through an allow-list. No telemetry.

straight answers

What does it do?

Several people on one installation, each with private and shared areas. Mail and calendar on Google or Microsoft 365. Briefs, drafts and approvals in Slack, Telegram or web chat. Tracks for what matters, without a CRM.

describes the coming release

Which models does it use?

Whatever you give it keys for. The engine does not bundle a model or a subscription.

Where does my data go?

It stays on the server you chose. The model provider sees what you send it, and only that. No telemetry.

What does it cost?

Self-host is free and open source; you pay your model provider. Cloud and managed pricing is still being set.

the name

The Roman lares were the spirits that kept a house running and kept bad things out. They were tended daily and never worshipped; the shrine was a practical fixture in the wall, a config file. A Greek daimon became a Unix daemon. Lares are trusted daemons in your house.